BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//171.67.215.200//NONSGML kigkonsult.se iCalcreator 2.26.9//
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-FROM-URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20231105T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20241103T020000
TZNAME:PST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20250309T020000
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:ai1ec-2677@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:Canary Center
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://www.earlydetectio
nresearch.com/
DESCRIPTION:Cancer Research UK\, OHSU Knight Cancer Institute and the Canar
y Center at Stanford\, present the Early Detection of Cancer Conference se
ries. The annual Conference brings together experts in early detection fro
m multiple disciplines to share ground breaking research and progress in t
he field.\nThe Conference is part of a long-term commitment to invest in e
arly detection research\, to understand the biology behind early stage can
cers\, find new detection and screening methods\, and enhance uptake and a
ccuracy of screening.\nThe 2021 conference will take place October 6-8 vir
tually. For more information visit the website: http://earlydetectionresea
rch.com/\nTickets: https://www.earlydetectionresearch.com/virtual-experien
ce/.
DTSTART;VALUE=DATE:20211006
DTEND;VALUE=DATE:20211009
LOCATION:Virtual Event
SEQUENCE:0
SUMMARY:Early Detection of Cancer Conference
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/early-de
tection-of-cancer-conference-2/
X-COST-TYPE:external
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/EDx21_300x300-150x150.jpg\;150\;150\;1
\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-cont
ent/uploads/2019/10/EDx21_300x300.jpg\;300\;300\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n
\\n\\n\\n
Cancer Research UK\, OHSU Knight Cancer
Institute and the Canary Center at Stanford\, present the Early Detection
of Cancer Conference series. The annual Conference brings together experts
in early detection from multiple disciplines to share ground breaking res
earch and progress in the field.
\n
The Conference is part of a long-
term commitment to invest in early detection research\, to understand the
biology behind early stage cancers\, find new detection and screening meth
ods\, and enhance uptake and accuracy of screening.
X-TICKETS-URL:https://www.earlydetectionresearch.com/virtual-experience/
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2033@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:MIPS\,MIPS Seminar
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://med.stanford.edu/
mips/events.html
DESCRIPTION:MIPS Seminar Series: Emerging nanophotonic platforms for infect
ious disease diagnostics: Re-imagining the conventional microbiology toolk
it\nJennifer Dionne\, PhD\nSenior Associate Vice Provost for Research Plat
forms/Shared Facilities\nAssociate Professor of Material Science and Engin
eering and\, by courtesy\, of Radiology (Molecular Imaging Program at Stan
ford)\nStanford University\n \nLocation: Zoom\nWebinar URL: https://stanfo
rd.zoom.us/j/95883654314\nDial: +1 650 724 9799 or +1 833 302 1536\nWebina
r ID: 958 8365 4314\nPasscode: 105586\n12:00pm – 12:45pm Seminar & Discuss
ion\nRSVP Here\n \nABSTRACT\nWe present our research controlling light at
the nanoscale for infectious disease diagnostics\, including detecting bac
teria at low concentration\, sensing COVID gene sequences\, and visualizin
g in-vivo inter-cellular forces. First\, we combine Raman spectroscopy and
deep learning to accurately classify bacteria by both species and antibio
tic resistance in a single step. We design a convolutional neural network
(CNN) for spectral data and train it to identify 30 of the most common bac
terial strains from single-cell Raman spectra\, achieving antibiotic treat
ment identification accuracies exceeding 99% and species identification ac
curacies similar to leading mass spectrometry identification techniques. O
ur combined Raman-CNN system represents a proof-of-concept for rapid\, cul
ture-free identification of bacterial isolates and antibiotic resistance.
Second\, we describe resonant nanophotonic surfaces\, known as “metasurfa
ces” that enable multiplexed detection of SARS-CoV-2 gene sequences. Our m
etasurfaces utilize guided mode resonances excited in high refractive inde
x nanostructures. The high quality factor modes produce a large amplificat
ion of the electromagnetic field near the nanostructures that increase the
response to targeted binding of nucleic acids\; simultaneously\, the opti
cal signal is beam-steered for multiplexed detection. We describe how this
platform can be manufactured at scale for portable\, low-cost assays. Fin
ally\, we introduce a new class of in vivo optical probes to monitor biolo
gical forces with high spatial resolution. Our design is based on upconver
ting nanoparticles that\, when excited in the near-infrared\, emit light o
f a different color and intensity in response to nano-to-microNewton force
s. The nanoparticles are sub-30nm in size\, do not bleach or photoblink\,
and can enable deep tissue imaging with minimal tissue autofluorescence. W
e present the design\, synthesis\, and characterization of these nanoparti
cles both in vitro and in vivo\, focusing on the forces generated by the r
oundworm C. elegans as it feeds and digests its bacterial food.\n \nABOUT
\nJennifer Dionne is the Senior Associate Vice Provost of Research Platfor
ms/Shared Facilities and an associate professor of Materials Science and E
ngineering and\, by courtesy\, of Radiology at Stanford. She is also an As
sociate Editor of Nano Letters\, director of the DOE-funded Photonics at T
hermodynamic Limits Energy Frontier Research Center\, and an affiliate fac
ulty of the Wu Tsai Neurosciences Institute\, the Institute for Immunity\,
Transplantation\, and Infection\, and Bio-X. Jen received her B.S. degree
s in Physics and Systems Science and Mathematics from Washington Universit
y in St. Louis\, her Ph. D. in Applied Physics at the California Institute
of Technology in 2009\, and her postdoctoral training in Chemistry at Ber
keley. Her research develops nanophotonic methods to observe and control
chemical and biological processes as they unfold with nanometer scale reso
lution\, emphasizing critical challenges in global health and sustainabili
ty. Her work has been recognized with the Alan T. Waterman Award\, a NIH D
irector’s New Innovator Award\, a Moore Inventor Fellowship\, the Material
s Research Society Young Investigator Award\, and the Presidential Early C
areer Award for Scientists and Engineers\, and was featured on Oprah’s lis
t of “50 Things that will make you say ‘Wow’!”. Beyond the lab\, Jen enjo
ys exploring the intersection of art and science\, long-distance cycling\,
and reliving her childhood with her two young sons.\n \nHosted by: Kather
ine Ferrara\, PhD\nSponsored by: Molecular Imaging Program at Stanford & t
he Department of Radiology\nTickets: https://stanford.zoom.us/webinar/regi
ster/7416069513520/WN_LIAnoCzYR8yLOnO-CDPgIQ.
DTSTART;TZID=America/Los_Angeles:20210422T120000
DTEND;TZID=America/Los_Angeles:20210422T124500
LOCATION:Zoom - See Description for Zoom Link
SEQUENCE:0
SUMMARY:MIPS Seminar – Jennifer Dionne\, PhD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/mips-sem
inar-jennifer-dionne-phd/
X-COST-TYPE:external
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/jennifer-dionne_profilephoto-150x150.j
pg\;150\;150\;1\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radc
alendar/wp-content/uploads/2019/10/jennifer-dionne_profilephoto-300x300.jp
g\;300\;300\;1\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcal
endar/wp-content/uploads/2019/10/jennifer-dionne_profilephoto.jpg\;350\;35
0\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
MIPS Semi
nar Series: Emerging nanophotonic platforms for infectious di
sease diagnostics: Re-imagining the conventional microbiology toolkit
\n
Jennifer
Dionne\, PhD \nSenior Associate Vice
Provost for Research Platforms/Shared Facilities \nAssociate Professor of Material Science and Engineering a
nd\, by courtesy\, of Radiology (Molecular Imaging Program at Stanford) \nStanford University
12:00pm – 12:45pm Seminar & Discussion \nRSVP Here
\n
\n
ABSTRACT \nWe present our research controlling light at the nanoscale for infecti
ous disease diagnostics\, including detecting bacteria at low concentratio
n\, sensing COVID gene sequences\, and visualizing in-vivo inter-cellular
forces. First\, we combine Raman spectroscopy and deep learning to accurat
ely classify bacteria by both species and antibiotic resistance in a singl
e step. We design a convolutional neural network (CNN) for spectral data a
nd train it to identify 30 of the most common bacterial strains from singl
e-cell Raman spectra\, achieving antibiotic treatment identification accur
acies exceeding 99% and species identification accuracies similar to leadi
ng mass spectrometry identification techniques. Our combined Raman-CNN sys
tem represents a proof-of-concept for rapid\, culture-free identification
of bacterial isolates and antibiotic resistance. Second\, we describe res
onant nanophotonic surfaces\, known as “metasurfaces” that enable multiple
xed detection of SARS-CoV-2 gene sequences. Our metasurfaces utilize guide
d mode resonances excited in high refractive index nanostructures. The hig
h quality factor modes produce a large amplification of the electromagneti
c field near the nanostructures that increase the response to targeted bin
ding of nucleic acids\; simultaneously\, the optical signal is beam-steere
d for multiplexed detection. We describe how this platform can be manufact
ured at scale for portable\, low-cost assays. Finally\, we introduce a new
class of in vivo optical probes to monitor biological forces wit
h high spatial resolution. Our design is based on upconverting nanoparticl
es that\, when excited in the near-infrared\, emit light of a different co
lor and intensity in response to nano-to-microNewton forces. The nanoparti
cles are sub-30nm in size\, do not bleach or photoblink\, and can enable d
eep tissue imaging with minimal tissue autofluorescence. We present the de
sign\, synthesis\, and characterization of these nanoparticles both in vit
ro and in vivo\, focusing on the forces generated by the roundworm C.
elegans as it feeds and digests its bacterial food.
\n
\n
ABOUT \nJennifer Dionne is the Senior Associate Vic
e Provost of Research Platforms/Shared Facilities and an associate profess
or of Materials Science and Engineering and\, by courtesy\, of Radiology a
t Stanford. She is also an Associate Editor of Nano Letters\, director of
the DOE-funded Photonics at Thermodynamic Limits Energy Frontier Research
Center\, and an affiliate faculty of the Wu Tsai Neurosciences Institute\,
the Institute for Immunity\, Transplantation\, and Infection\, and Bio-X.
Jen received her B.S. degrees in Physics and Systems Science and Mathemat
ics from Washington University in St. Louis\, her Ph. D. in Applied Physic
s at the California Institute of Technology in 2009\, and her postdoctoral
training in Chemistry at Berkeley. Her research develops nanophotonic me
thods to observe and control chemical and biological processes as they unf
old with nanometer scale resolution\, emphasizing critical challenges in g
lobal health and sustainability. Her work has been recognized with the Ala
n T. Waterman Award\, a NIH Director’s New Innovator Award\, a Moore Inven
tor Fellowship\, the Materials Research Society Young Investigator Award\,
and the Presidential Early Career Award for Scientists and Engineers\, an
d was featured on Oprah’s list of “50 Things that will make you say ‘Wow’!
”. Beyond the lab\, Jen enjoys exploring the intersection of art and scie
nce\, long-distance cycling\, and reliving her childhood with her two youn
g sons.
\n
\n
Hosted by: Katherine Ferrara\, PhD \nSponsored by: Molecular Imaging Program at Stanford & the Departmen
t of Radiology
X-TICKETS-URL:https://stanford.zoom.us/webinar/register/7416069513520/WN_LI
AnoCzYR8yLOnO-CDPgIQ
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2417@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:Canary Center\,IBIIS\,MIPS\,PHIND\,Radiology\,RSL
CONTACT:Marta Flory\; flory@stanford.edu
DESCRIPTION:Targeted violence continues against Black Americans\, Asian Ame
ricans\, and all people of color. The department of radiology diversity co
mmittee is running a racial equity challenge to raise awareness of systemi
c racism\, implicit bias and related issues. Participants will be provided
a list of resources on these topics such as articles\, podcasts\, videos\
, etc.\, from which they can choose\, with the “challenge” of engaging wit
h one to three media sources prior to our session (some videos are as shor
t as a few minutes). Participants will meet in small-group breakout sessio
ns to discuss what they’ve learned and share ideas.\nPlease reach out to M
arta Flory\, flory@stanford.edu with questions. For details about the sess
ion\, including recommended resources and the Zoom link\, please reach out
to Meke Faaoso at mfaaoso@stanford.edu.\nTickets: https://docs.google.com
/spreadsheets/d/1ehKqHm32peHcm7NQJ427OaKIa9JpfHVunjBk66etZGc/edit?usp=shar
ing.
DTSTART;TZID=America/Los_Angeles:20210430T120000
DTEND;TZID=America/Los_Angeles:20210430T130000
LOCATION:Zoom
SEQUENCE:0
SUMMARY:Racial Equity Challenge: Race in society
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/racial-e
quity-challenge-race-in-society/
X-COST-TYPE:external
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2021/04/shield-150x150.png\;150\;150\;1\,mediu
m\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upl
oads/2021/04/shield.png\;225\;225\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
Targeted violence continues against Black Ameri
cans\, Asian Americans\, and all people of color. The department of radiol
ogy diversity committee is running a racial equity challenge to raise awar
eness of systemic racism\, implicit bias and related issues. Participants
will be provided a list of resources on these topics such as articles\, po
dcasts\, videos\, etc.\, from which they can choose\, with the “challenge”
of engaging with one to three media sources prior to our session (some vi
deos are as short as a few minutes). Participants will meet in small-group
breakout sessions to discuss what they’ve learned and share ideas.
\n<
p>Please reach out to Marta Flory\, fl
ory@stanford.edu with questions. For details about the session\, inclu
ding recommended resources and the Zoom link\, please reach out to Meke Fa
aoso at mfaaoso@stanford.edu.\n
X-TICKETS-URL:https://docs.google.com/spreadsheets/d/1ehKqHm32peHcm7NQJ427O
aKIa9JpfHVunjBk66etZGc/edit?usp=sharing
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-1757@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:Canary Center\,Early Cancer Detection Seminar Ser
ies
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://canarycenter.stan
ford.edu/seminars.html
DESCRIPTION:CEDSS: “Building a Scalable Clinical Genomics Program: How tumo
r\, normal\, and plasma DNA sequencing are informing cancer care\, cancer
risk\, and cancer detection”\n \nMichael Berger\, Ph.D.\nElizabeth and Fel
ix Rohatyn Chair & Associate Director of the Marie-Josée and Henry R. Krav
is Center for Molecular Oncology\nMemorial Sloan Kettering Cancer Center\n
\nZoom Details\nMeeting URL: https://stanford.zoom.us/s/92559505314\nDial
: US: +1 650 724 9799 or +1 833 302 1536 (Toll Free)\nMeeting ID: 925 595
0 5314\nPasscode: 418727\n11:00am – 12:00pm Seminar & Discussion\nRSVP Her
e\n \nABSTRACT\nTumor molecular profiling is a fundamental component of pr
ecision oncology\, enabling the identification of oncogenomic mutations th
at can be targeted therapeutically. To accelerate enrollment to clinical t
rials of molecularly targeted agents and guide treatment selection\, we ha
ve established a center-wide\, prospective clinical sequencing program at
Memorial Sloan Kettering Cancer Center using a custom\, paired tumor-blood
normal sequencing assay (MSK-IMPACT)\, which we have used to profile more
than 50\,000 patients with solid tumors. Yet beyond just the characteriza
tion of tumor-specific alterations\, the inclusion of blood DNA has readil
y enabled the identification of germline risk alleles and somatic mutation
s associated with clonal hematopoiesis. To complement this approach\, we h
ave also implemented a ‘liquid biopsy’ cfDNA panel (MSK-ACCESS) for cancer
detection\, surveillance\, and treatment selection and monitoring. In my
talk\, I will describe the prevalence of somatic and germline genomic alte
rations in a real-world population\, the clinical benefits of cfDNA assess
ment\, and how clonal hematopoiesis can inform cancer risk and confound li
quid biopsy approaches to cancer detection.\n \nABOUT\nMichael Berger\, Ph
D\, holds the Elizabeth and Felix Rohatyn Chair and is Associate Director
of the Marie-Josée and Henry R. Kravis Center for Molecular Oncology at Me
morial Sloan Kettering Cancer Center\, a multidisciplinary initiative to p
romote precision oncology through genomic analysis to guide the diagnosis
and treatment of cancer patients. He is also an Associate Attending Geneti
cist in the Department of Pathology with expertise in cancer genomics\, co
mputational biology\, and high-throughput DNA sequencing technology. His l
aboratory is developing experimental and computational methods to characte
rize the genetic makeup of individual cancers and identify genomic biomark
ers of drug response and resistance. As Scientific Director of Clinical NG
S in the Molecular Diagnostics Service\, he oversees the development and b
ioinformatics associated with clinical sequencing assays\, and he helped l
ead the development and implementation of MSK-IMPACT\, a comprehensive FDA
-authorized tumor sequencing panel that been used to profile more than 60\
,000 tumors from advanced cancer patients at MSK. The resulting data have
enabled the characterization of somatic and germline biomarkers across man
y cancer types and the identification of mutations associated with clonal
hematopoiesis. Dr. Berger also led the development of a clinically validat
ed plasma cell-free DNA assay\, MSK-ACCESS\, which his laboratory is using
to explore tumor evolution\, acquired drug resistance\, and occult metast
atic disease. He received his Bachelor’s Degree in Physics from Princeton
University and his Ph.D. in Biophysics from Harvard University.\n \nHosted
by: Utkan Demirci\, Ph.D.\nSponsored by: The Canary Center & the Departme
nt of Radiology \nStanford University – School of Medicine\nTickets: https
://stanford.zoom.us/webinar/register/5516153318622/WN_MT7TTEciRoWmLVP9GlsJ
RA.
DTSTART;TZID=America/Los_Angeles:20210511T110000
DTEND;TZID=America/Los_Angeles:20210511T120000
LOCATION:Zoom - See Description for Zoom Link
SEQUENCE:0
SUMMARY:Cancer Early Detection Seminar Series – Michael Berger\, Ph.D.
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/cancer-e
arly-detection-seminar-series-michael-f-berger-ph-d/
X-COST-TYPE:external
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/berger_160204_07-2_3x2-150x150.jpg\;15
0\;150\;1\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalenda
r/wp-content/uploads/2019/10/berger_160204_07-2_3x2-300x200.jpg\;300\;200\
;1\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-con
tent/uploads/2019/10/berger_160204_07-2_3x2.jpg\;600\;400\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
CEDSS: “Building a
Scalable Clinical Genomics Program: How tumor\, normal\, and plasma DNA se
quencing are informing cancer care\, cancer risk\, and cancer detection”
em>
Elizabeth and Fel
ix Rohatyn Chair & Associate Director of the Marie-Josée and Henry R. Krav
is Center for Molecular Oncology \nMemorial Sloan Kettering Cancer Ce
nter
11:00am – 12:00pm Seminar & Discussio
n \nRSVP Here
\n
\n
ABSTRAC
T \nTumor molecular profiling is a fundamental component of
precision oncology\, enabling the identification of oncogenomic mutations
that can be targeted therapeutically. To accelerate enrollment to clinical
trials of molecularly targeted agents and guide treatment selection\, we
have established a center-wide\, prospective clinical sequencing program a
t Memorial Sloan Kettering Cancer Center using a custom\, paired tumor-blo
od normal sequencing assay (MSK-IMPACT)\, which we have used to profile mo
re than 50\,000 patients with solid tumors. Yet beyond just the characteri
zation of tumor-specific alterations\, the inclusion of blood DNA has read
ily enabled the identification of germline risk alleles and somatic mutati
ons associated with clonal hematopoiesis. To complement this approach\, we
have also implemented a ‘liquid biopsy’ cfDNA panel (MSK-ACCESS) for canc
er detection\, surveillance\, and treatment selection and monitoring. In m
y talk\, I will describe the prevalence of somatic and germline genomic al
terations in a real-world population\, the clinical benefits of cfDNA asse
ssment\, and how clonal hematopoiesis can inform cancer risk and confound
liquid biopsy approaches to cancer detection.
\n
\n
AB
OUT \nMichael Berger\, PhD\, holds the Elizabeth and Felix R
ohatyn Chair and is Associate Director of the Marie-Josée and Henry R. Kra
vis Center for Molecular Oncology at Memorial Sloan Kettering Cancer Cente
r\, a multidisciplinary initiative to promote precision oncology through g
enomic analysis to guide the diagnosis and treatment of cancer patients. H
e is also an Associate Attending Geneticist in the Department of Pathology
with expertise in cancer genomics\, computational biology\, and high-thro
ughput DNA sequencing technology. His laboratory is developing experimenta
l and computational methods to characterize the genetic makeup of individu
al cancers and identify genomic biomarkers of drug response and resistance
. As Scientific Director of Clinical NGS in the Molecular Diagnostics Serv
ice\, he oversees the development and bioinformatics associated with clini
cal sequencing assays\, and he helped lead the development and implementat
ion of MSK-IMPACT\, a comprehensive FDA-authorized tumor sequencing panel
that been used to profile more than 60\,000 tumors from advanced cancer pa
tients at MSK. The resulting data have enabled the characterization of som
atic and germline biomarkers across many cancer types and the identificati
on of mutations associated with clonal hematopoiesis. Dr. Berger also led
the development of a clinically validated plasma cell-free DNA assay\, MSK
-ACCESS\, which his laboratory is using to explore tumor evolution\, acqui
red drug resistance\, and occult metastatic disease. He received his Bache
lor’s Degree in Physics from Princeton University and his Ph.D. in Biophys
ics from Harvard University.
\n
\n
Hosted by: Utkan Demirc
i\, Ph.D. \nSponsored by
: The Canary Center & the Department of Radiology \nStanfor
d University – School of Medicine
X-TICKETS-URL:https://stanford.zoom.us/webinar/register/5516153318622/WN_MT
7TTEciRoWmLVP9GlsJRA
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2385@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:MIPS\,MIPS Seminar
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://med.stanford.edu/
mips/events.html
DESCRIPTION:MIPS Special Seminar: Jubilant Biosys: Drug discovery and contr
act research services\, from target discovery to candidate selection\n \nT
homas Haywood\, PhD\nHead of International Radiochemistry Collaborations\n
Stanford University\n \nSaurabh Kapure\, MBA\nVice President\, Business De
velopment (USA & APAC)\nJubilant Biosys Limited\n \nJay Sheth\, MBA\nManag
er Business Development\, Drug Discovery Services\, and CDMO\nJubilant Bio
sys Limited\n \nLOCATION: Zoom\nMeeting URL: https://stanford.zoom.us/j/98
108346345\nDial: +1 650 724 9799 or +1 833 302 1536\nMeeting ID: 981 0834
6345\nPasscode: 397741\n\n\nSCHEDULE\n9:00-9:15 AM\, PT – Thomas Haywood
– Stanford Radiology projects\n9:15-9:30 AM\, PT – Saurabh Kapure – Introd
uction to Jubilant Biosys\, Scale-up and GMP manufacturing\n9:30-9:40 AM\,
PT – Jay Sheth – How Jubilant Biosys works with academic partners: exampl
es and case-studies\n9:40-10:00 AM\, PT – Moderated by Jason Thanh Lee –
Discussion\n \nABOUT\nJubilant Biosys\, an integrated contract research or
ganization in India with business offices in Asia and North America\, is a
leading collaborator for biotechnology and pharmaceutical companies\, wit
h in-depth expertise in discovery informatics\, medicinal chemistry\, stru
ctural biology\, and in vitro pharmacology services. Jubilant Biosys provi
des comprehensive drug discovery services and contract research services\,
from target discovery to candidate selection and with flexible business m
odels (FFS\, FTE and risk shared). This seminar will showcase case studies
from recent Stanford projects and a discussion of future opportunities.\n
\nSponsored by: Molecular Imaging Program at Stanford\, Department of Rad
iology
DTSTART;TZID=America/Los_Angeles:20210512T090000
DTEND;TZID=America/Los_Angeles:20210512T100000
LOCATION:Zoom - See Description for Zoom Link
SEQUENCE:0
SUMMARY:MIPS Special Seminar – Jubilant Biosys
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/mips-spe
cial-seminar-jubilant-biosys/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/Headshots-for-Calendar-150x150.jpg\;15
0\;150\;1\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalenda
r/wp-content/uploads/2019/10/Headshots-for-Calendar.jpg\;210\;209\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
MIPS Special Seminar: <
/strong>Jubilant Biosys: Drug discovery and contract research services
\, from target discovery to candidate selection
\n
\n
Thomas Haywood\, PhD \nHead of International Radiochemi
stry Collaborations \nStanford University
\n
\n
S
aurabh Kapure\, MBA \nVice President\, Business Development
(USA & APAC) \nJubilant Biosys Limited
\n
\n
Jay
Sheth\, MBA \nManager Business Development\, Drug Discovery
Services\, and CDMO \nJubilant Biosys Limited
9:15-9:30 AM\, PT – Saurabh Kapur
e – Introduction to Jubilant Biosys\, Scale-up and GMP manufactur
ing
\n
9:30-9:40 AM\, PT – Jay Sheth –
How Jubilant Biosys works with academic partners: examples and case-studie
s \n9:40-10:00 AM\, PT – Moderated by Jason Thanh Le
e – Discussion
\n
\n
ABOUT \nJubilant Biosys\, an integrated contract research organization i
n India with business offices in Asia and North America\, is a leading col
laborator for biotechnology and pharmaceutical companies\, with in-depth e
xpertise in discovery informatics\, medicinal chemistry\, structural biolo
gy\, and in vitro pharmacology services. Jubilant Biosys provides
comprehensive drug discovery services and contract research services\, fr
om target discovery to candidate selection and with flexible business mode
ls (FFS\, FTE and risk shared). This seminar will showcase case studies fr
om recent Stanford projects and a discussion of future opportunities.
\n
\n
Sponsored by: Molecular Imaging Program at Stanford\, D
epartment of Radiology
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2161@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:MIPS\,MIPS Seminar
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://med.stanford.edu/
mips/events.html
DESCRIPTION:MIPS Seminar Series: Image-guided focal therapy for prostate ca
ncer\nGeoffrey Sonn\, MD\nAssistant Professor of Urology and\, by courtesy
\, of Radiology (Molecular Imaging Program at Stanford)\nStanford Universi
ty Medical Center\n \nLocation: Zoom\nWebinar URL: https://stanford.zoom.u
s/s/96126703618\nDial: +1 650 724 9799 or +1 833 302 1536\nWebinar ID: 961
2670 3618\nPasscode: 186059\n12:00pm – 12:45pm Seminar & Discussion\nRSVP
Here\n \nABSTRACT\nIn recent years\, prostate cancer treatment has increa
singly focused on selecting patients who are most likely to benefit and re
ducing harms from treatment. This has been seen both in adoption of active
surveillance for men with low-risk prostate cancer and emergence of image
-guided focal ablative therapy. While focal therapy causes fewer sexual an
d urinary side effects than conventional prostate cancer treatments\, many
questions remain about proper patient selection\, treatment planning\, an
d follow up care.\n \nImprovements in prostate MRI performance and interpr
etation have paved the way for adoption of focal therapy. However\, clinic
al challenges remain in prostate cancer imaging. This talk will describe p
rostate cancer focal therapy\, discuss patient selection\, and highlight t
he research efforts of my group to improve MRI interpretation to guide bio
psy and improve focal therapy performance.\n \nABOUT\nGeoffrey Sonn\, MD i
s a urologic oncologist who specializes in treating patients with prostate
and kidney cancer. He has a particular interest in cancer imaging\, MRI-U
ltrasound fusion targeted prostate biopsy\, prostate cancer focal therapy\
, and robotic surgery for prostate and kidney cancer. He is the principal
investigator of the first clinical trial in Northern California to use MRI
-guided focused ultrasound to treat prostate cancer. The goal of this tria
l is to treat prostate cancer with fewer side effects than surgery or radi
ation.\nDr. Sonn was born in Washington State and lived there until leavin
g for college at Georgetown. After graduating magna cum laude at Georgetow
n he returned to the West Coast for medical school at UCLA. Following medi
cal school\, Dr. Sonn completed a 6-year urology residency at Stanford whe
re he developed particular interests in the clinical care of patients with
urologic cancers and research in cancer imaging. Dr. Sonn completed a 2-y
ear urologic oncology fellowship at UCLA. Since completing his fellowship\
, Dr. Sonn has been at Stanford as an assistant professor in urology. Dr.
Sonn’s research is devoted to developing new cancer imaging techniques\, a
pplying artificial intelligence to find cancers on medical images\, and ap
plying new methods to treat prostate cancer with fewer side effects.\n \nH
osted by: Katherine Ferrara\, PhD\nSponsored by: Molecular Imaging Program
at Stanford & the Department of Radiology\nTickets: https://stanford.zoom
.us/webinar/register/8116097828282/WN_mfyC-_dUTwymWGqvmmF1zA.
DTSTART;TZID=America/Los_Angeles:20210527T120000
DTEND;TZID=America/Los_Angeles:20210527T124500
LOCATION:Zoom - See Description for Zoom Link
SEQUENCE:0
SUMMARY:MIPS Seminar – Geoffrey Sonn\, MD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/mips-sem
inar-geoffrey-sonn-md/
X-COST-TYPE:external
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/geoffrey-sonn_profilephoto-150x150.jpg
\;150\;150\;1\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcal
endar/wp-content/uploads/2019/10/geoffrey-sonn_profilephoto-300x300.jpg\;3
00\;300\;1\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcalenda
r/wp-content/uploads/2019/10/geoffrey-sonn_profilephoto.jpg\;350\;350\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
MIPS Semina
r Series: Image-guided focal therapy for prostate cancer
12:00pm – 12:4
5pm Seminar & Discussion \nRSVP Here
\n
<
/p>\n
ABSTRACT
\n
In recent years\, prostate cance
r treatment has increasingly focused on selecting patients who are most li
kely to benefit and reducing harms from treatment. This has been seen both
in adoption of active surveillance for men with low-risk prostate cancer
and emergence of image-guided focal ablative therapy. While focal therapy
causes fewer sexual and urinary side effects than conventional prostate ca
ncer treatments\, many questions remain about proper patient selection\, t
reatment planning\, and follow up care.
\n
\n
Improvements in prostate MRI performance and interpretation have paved th
e way for adoption of focal therapy. However\, clinical challenges remain
in prostate cancer imaging. This talk will describe prostate cancer focal
therapy\, discuss patient selection\, and highlight the research efforts o
f my group to improve MRI interpretation to guide biopsy and improve focal
therapy performance.
\n
\n
ABOUT \nGeof
frey Sonn\, MD is a urologic oncologist who specializes in treating patien
ts with prostate and kidney cancer. He has a particular interest in cancer
imaging\, MRI-Ultrasound fusion targeted prostate biopsy\, prostate cance
r focal therapy\, and robotic surgery for prostate and kidney cancer. He i
s the principal investigator of the first clinical trial in Northern Calif
ornia to use MRI-guided focused ultrasound to treat prostate cancer. The g
oal of this trial is to treat prostate cancer with fewer side effects than
surgery or radiation.
\n
Dr. Sonn was born in Washington State and l
ived there until leaving for college at Georgetown. After graduating magna
cum laude at Georgetown he returned to the West Coast for medical school
at UCLA. Following medical school\, Dr. Sonn completed a 6-year urology re
sidency at Stanford where he developed particular interests in the clinica
l care of patients with urologic cancers and research in cancer imaging. D
r. Sonn completed a 2-year urologic oncology fellowship at UCLA. Since com
pleting his fellowship\, Dr. Sonn has been at Stanford as an assistant pro
fessor in urology. Dr. Sonn’s research is devoted to developing new cancer
imaging techniques\, applying artificial intelligence to find cancers on
medical images\, and applying new methods to treat prostate cancer with fe
wer side effects.
\n
\n
Hosted by: Katherine Ferrara\, PhD
\nSponsored by: Molecular Imaging Program at Stanford & the
Department of Radiology
X-TICKETS-URL:https://stanford.zoom.us/webinar/register/8116097828282/WN_mf
yC-_dUTwymWGqvmmF1zA
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2803@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI\,IBIIS\,Radiology\,RSL
CONTACT:
DESCRIPTION:Radiology Department-Wide Research Meeting\n• Research Announce
ments\n• Mirabela Rusu\, PhD – Learning MRI Signatures of Aggressive Prost
ate Cancer: Bridging the Gap between Digital Pathologists and Digital Radi
ologists\n• Akshay Chaudhari\, PhD – Data-Efficient Machine Learning for M
edical Imaging\nLocation: Zoom – Details can be found here: https://radres
earch.stanford.edu\nMeetings will be the 3rd Friday of each month.\n \nHos
ted by: Kawin Setsompop\, PhD\nSponsored by: the the Department of Radiolo
gy
DTSTART;TZID=America/Los_Angeles:20210716T120000
DTEND;TZID=America/Los_Angeles:20210716T130000
LOCATION:Zoom – Details can be found here: https://radresearch.stanford.edu
SEQUENCE:0
SUMMARY:Radiology-Wide Research Conference
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/radiolog
y-wide-research-conference/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2021/07/RWRC-July-150x150.jpeg\;150\;150\;1\,m
edium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content
/uploads/2021/07/RWRC-July-300x195.jpeg\;300\;195\;1\,large\;http://web.st
anford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2021/07/RWR
C-July.jpeg\;443\;288\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
\n
Radiology Department-Wide Research Meeting
\n
•
Research Announcements \n• Mirabela Rusu\, PhD – Learning MRI Signat
ures of Aggressive Prostate Cancer: Bridging the Gap between Digital Patho
logists and Digital Radiologists \n• Akshay Chaudhari\, PhD – Data-Ef
ficient Machine Learning for Medical Imaging
Hosted by: Kawin Setsompop\, PhD \nSponsore
d by: the the Department of Radiology
\n
\n\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2809@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI\,Annual Conferences
CONTACT:AIMI Center\; aimicenter@stanford.edu\; https://aimi.stanford.edu/n
ews-events/aimi-symposium/overview
DESCRIPTION:Stanford AIMI Director Curt Langlotz and Co-Directors Matt Lung
ren and Nigam Shah invite you to join us on August 3 for the 2021 Stanford
Center for Artificial Intelligence in Medicine and Imaging (AIMI) Symposi
um. The virtual symposium will focus on the latest\, best research on the
role of AI in diagnostic excellence across medicine\, current areas of imp
act\, fairness and societal impact\, and translation and clinical implemen
tation. The program includes talks\, interactive panel discussions\, and b
reakout sessions. Registration is free and open to all.\n \nAlso\, the 2nd
Annual BiOethics\, the Law\, and Data-sharing: AI in Radiology (BOLD-AIR)
Summit will be held on August 4\, in conjunction with the AIMI Symposium.
The summit will convene a broad range of speakers in bioethics\, law\, re
gulation\, industry groups\, and patient safety and data privacy\, to addr
ess the latest ethical\, regulatory\, and legal challenges regarding AI in
radiology.\n \nREGISTER HERE\nTickets: https://www.eventbrite.com/e/2021-
stanford-aimi-symposium-bold-air-summit-registration-152725816027.
DTSTART;TZID=America/Los_Angeles:20210803T080000
DTEND;TZID=America/Los_Angeles:20210804T150000
LOCATION:Virtual Livestream
SEQUENCE:0
SUMMARY:2021 AIMI Symposium + BOLD-AIR Summit
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/2021-aim
i-symposium-bold-air-summit/
X-COST-TYPE:external
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/2021-Symposium-and-BOLD-Banner_0618212
1-150x150.png\;150\;150\;1\,medium\;http://web.stanford.edu/group/radweb/c
gi-bin/radcalendar/wp-content/uploads/2019/10/2021-Symposium-and-BOLD-Bann
er_06182121-300x112.png\;300\;112\;1\,large\;http://web.stanford.edu/group
/radweb/cgi-bin/radcalendar/wp-content/uploads/2019/10/2021-Symposium-and-
BOLD-Banner_06182121-1024x382.png\;640\;239\;1\,full\;http://web.stanford.
edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2019/10/2021-Sympo
sium-and-BOLD-Banner_06182121.png\;1770\;660\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
Stanfo
rd AIMI Director Curt Langlotz and Co-Directors Matt Lungren and Nigam Sha
h invite you to join us on August 3 for
the 2021 Stanford Center for Artificial Intell
igence in Medicine and Imaging (AIMI) Symp
osium. The virtual symposium will focus on the latest\, best research
on the role of AI in diagnostic excellence across medicine\, current areas
of impact\, fairness and societal impact\, and translation and clinical i
mplementation. The program includes talks\, interactive panel discussions\
, and breakout sessions. Registration is free and open to all.
\n
p>\n
Also\, the 2nd Annual BiOethics\, the L
aw\, and Data-sharing: AI in Radiology (BOLD-AIR) Summit will be held
on August 4\, in conjunction with the AI
MI Symposium. The summit will convene a broad range of speakers in bioethi
cs\, law\, regulation\, industry groups\, and patient safety and data priv
acy\, to address the latest ethical\, regulatory\, and legal challenges re
garding AI in radiology.
X-TICKETS-URL:https://www.eventbrite.com/e/2021-stanford-aimi-symposium-bol
d-air-summit-registration-152725816027
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2989@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; http://ibiis.stan
ford.edu/events/seminars/2021seminars.html
DESCRIPTION: \n\nRegina Barzilay\, PhD\nSchool of Engineering Distinguished
Professor for AI and Health\nElectrical Engineering and Computer Science
Department\nAI Faculty Lead at Jameel Clinic for Machine Learning in Healt
h\nComputer Science and Artificial Intelligence Lab\nMassachusetts Institu
te of Technology\nAbstract:\nIn this talk\, I will present methods for fut
ure cancer risk from medical images. The discussion will explore alternati
ve ways to formulate the risk assessment task and focus on algorithmic iss
ues in developing such models. I will also discuss our experience in trans
lating these algorithms into clinical practice in hospitals around the wor
ld.
DTSTART;TZID=America/Los_Angeles:20210922T110000
DTEND;TZID=America/Los_Angeles:20210922T120000
LOCATION:Zoom: https://stanford.zoom.us/j/99474772502?pwd=NEQrQUQ0MzdtRjFiY
U42TCs2bFZsUT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Seeing the Future from Images: ML-Based Model
s for Cancer Risk Assessment
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-seeing-the-future-from-images-ml-based-models-for-cancer-risk-a
ssessment/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2021/08/regina-300x300.jpeg\;300\;300\,medium\
;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploa
ds/2021/08/regina-300x300.jpeg\;300\;300\,large\;http://web.stanford.edu/g
roup/radweb/cgi-bin/radcalendar/wp-content/uploads/2021/08/regina-300x300.
jpeg\;300\;300\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcale
ndar/wp-content/uploads/2021/08/regina-300x300.jpeg\;300\;300
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
\n
p>\n
Regina Barzilay\, PhD \nSchool of Engineering Distingui
shed Professor for AI and Health \nElectrical Engineering and Compute
r Science Department \nAI Faculty Lead at Jameel Clinic for Machine L
earning in Health \nComputer Science and Artificial Intelligence Lab<
br />\nMassachusetts Institute of Technology
\n
Abstract: \nIn this talk\, I will present methods for future cancer risk
from medical images. The discussion will explore alternative ways to formu
late the risk assessment task and focus on algorithmic issues in developin
g such models. I will also discuss our experience in translating these alg
orithms into clinical practice in hospitals around the world.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2575@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:MIPS\,MIPS Seminar
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://med.stanford.edu/
mips/events.html
DESCRIPTION:MIPS Seminar Series: Predicting and Preventing Fetal and Neonat
al Pathology: Looking Back and Looking Forward\nDavid K. Stevenson\, MD\nT
he Harold K. Faber Professor of Pediatrics\, Senior Associate Dean\, Mater
nal and Child Health and Professor\, by courtesy\, of Obstetrics and Gynec
ology\nLucile Packard Children’s Hospital\n \nZoom Webinar Details\nWebina
r URL: https://stanford.zoom.us/s/94584828060\nDial: +1 650 724 9799 or +1
833 302 1536\nWebinar ID: 945 8482 8060\nPasscode: 481874\n12:00pm – 12:4
5pm Seminar & Discussion\nRSVP Here\n \nABSTRACT\nThe importance of minima
lly invasive technologies for interrogating the fetus and newborn\, as wel
l as of knowing where a biologic system is headed\, not just where it has
been\, when trying to predict and prevent acquired diseases\, will be disc
ussed. Examples of such technologies\, such as trace gas analysis and opt
ical reporting of biologic phenomena\, and their application to model syst
ems and the human newborn will be presented. The role of advanced computa
tional approaches for the integration and interpretation of large amounts
of data derived from these new measurement tools will be emphasized.\n \nA
BOUT\nDr. David K. Stevenson is the Harold K. Faber Professor of Pediatric
s and has made many impactful contributions to the field of neonatology an
d pediatrics\, including his seminal studies on neonatal jaundice\, biliru
bin production and heme oxygenase biology. As a neonatologist\, his resea
rch has focused primarily on neonatal jaundice and more recently on the ca
uses of preterm birth and its prevention. He has held numerous leadership
roles at Stanford University School of Medicine\, including Vice Dean and
Senior Associate Dean for Academic Affairs. He is currently the Senior As
sociate Dean for Maternal & Child Health\, the Co-Director of the Stanford
Maternal & Child Health Research Institute\, and the Principal Investigat
or for the March of Dimes Prematurity Research Center at Stanford Universi
ty. Dr. Stevenson has received many awards\, including the Virginia Apgar
Award\, which is the highest award in Perinatal Pediatrics\, the Joseph W
. St. Geme\, Jr. Leadership Award from the Federation of Pediatric Organiz
ations\, the Jonas Salk Award for Leadership in Prematurity Prevention fro
m the March of Dimes Foundation\, and the John Howland Medal and Award\, t
he highest award in academic pediatrics. He has served as the President o
f the American Pediatric Society. In recognition of his achievements\, Dr.
Stevenson is a member of the National Academy of Medicine.\n \nHosted by:
Katherine Ferrara\, PhD\nSponsored by: Molecular Imaging Program at Stanf
ord & the Department of Radiology\nTickets: https://stanford.zoom.us/webin
ar/register/7116294064170/WN_H60DZOKZSlWC6UBOB3FTVw.
DTSTART;TZID=America/Los_Angeles:20210923T120000
DTEND;TZID=America/Los_Angeles:20210923T124500
LOCATION:Zoom - See Description for Zoom Link
SEQUENCE:0
SUMMARY:MIPS Seminar – David K. Stevenson\, MD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/mips-sem
inar-david-k-stevenson-md/
X-COST-TYPE:external
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/david-stevenson_profilephoto-150x150.j
pg\;150\;150\;1\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radc
alendar/wp-content/uploads/2019/10/david-stevenson_profilephoto-300x300.jp
g\;300\;300\;1\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcal
endar/wp-content/uploads/2019/10/david-stevenson_profilephoto.jpg\;350\;35
0\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
MIPS Semi
nar Series:Predicting and Preventing Fetal and Neonatal Path
ology: Looking Back and Looking Forward
\n
David K. Stevenson\, MD \nThe
Harold K. Faber Professor of Pediatrics\, Senior Associate Dean\, Maternal
and Child Health and Professor\, by courtesy\, of Obstetrics and Gynecolo
gy \nLucile Packard Children’s Hospital
12:00p
m – 12:45pm Seminar & Discussion \nRSVP Here
\n
\n
ABSTRACT \nThe importance of minimal
ly invasive technologies for interrogating the fetus and newborn\, as well
as of knowing where a biologic system is headed\, not just where it has b
een\, when trying to predict and prevent acquired diseases\, will be discu
ssed. Examples of such technologies\, such as trace gas analysis and opti
cal reporting of biologic phenomena\, and their application to model syste
ms and the human newborn will be presented. The role of advanced computat
ional approaches for the integration and interpretation of large amounts o
f data derived from these new measurement tools will be emphasized.
\n<
p>
\n
ABOUT \nDr. David K. Stevenson is the Ha
rold K. Faber Professor of Pediatrics and has made many impactful contribu
tions to the field of neonatology and pediatrics\, including his seminal s
tudies on neonatal jaundice\, bilirubin production and heme oxygenase biol
ogy. As a neonatologist\, his research has focused primarily on neonatal
jaundice and more recently on the causes of preterm birth and its preventi
on. He has held numerous leadership roles at Stanford University School o
f Medicine\, including Vice Dean and Senior Associate Dean for Academic Af
fairs. He is currently the Senior Associate Dean for Maternal & Child Heal
th\, the Co-Director of the Stanford Maternal & Child Health Research Inst
itute\, and the Principal Investigator for the March of Dimes Prematurity
Research Center at Stanford University. Dr. Stevenson has received many a
wards\, including the Virginia Apgar Award\, which is the highest award in
Perinatal Pediatrics\, the Joseph W. St. Geme\, Jr. Leadership Award from
the Federation of Pediatric Organizations\, the Jonas Salk Award for Lead
ership in Prematurity Prevention from the March of Dimes Foundation\, and
the John Howland Medal and Award\, the highest award in academic pediatric
s. He has served as the President of the American Pediatric Society. In r
ecognition of his achievements\, Dr. Stevenson is a member of the National
Academy of Medicine.
\n
\n
Hosted by: Katherine Ferrara\,
PhD \nSponsored by: Molecular Imaging Program at Stanford &
the Department of Radiology
X-TICKETS-URL:https://stanford.zoom.us/webinar/register/7116294064170/WN_H6
0DZOKZSlWC6UBOB3FTVw
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2993@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/retreat/2021Hybrid.html
DESCRIPTION:Keynote:\nSelf-Supervision for Learning from the Bottom Up\nWhy
do self-supervised learning? A common answer is: “because data labeling i
s expensive.” In this talk\, I will argue that there are other\, perhaps m
ore fundamental reasons for working on self-supervision. First\, it should
allow us to get away from the tyranny of top-down semantic categorization
and force meaningful associations to emerge naturally from the raw sensor
data in a bottom-up fashion. Second\, it should allow us to ditch fixed d
atasets and enable continuous\, online learning\, which is a much more nat
ural setting for real-world agents. Third\, and most intriguingly\, there
is hope that it might be possible to force a self-supervised task curricul
um to emerge from first principles\, even in the absence of a pre-defined
downstream task or goal\, similar to evolution. In this talk\, I will touc
h upon these themes to argue that\, far from running its course\, research
in self-supervised learning is only just beginning.
DTSTART;TZID=America/Los_Angeles:20210927T130000
DTEND;TZID=America/Los_Angeles:20210927T163000
LOCATION:https://ibiis.stanford.edu/events/retreat/2021Hybrid.html
SEQUENCE:0
SUMMARY:2021 IBIIS & AIMI Virtual Retreat
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/2021-ibi
is-aimi-virtual-retreat/
X-COST-TYPE:free
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
Keynote:
\n
Self-Supervision for Learning from the Bottom Up
\n
Why do sel
f-supervised learning? A common answer is: “because data labeling is expen
sive.” In this talk\, I will argue that there are other\, perhaps more fun
damental reasons for working on self-supervision. First\, it should allow
us to get away from the tyranny of top-down semantic categorization and fo
rce meaningful associations to emerge naturally from the raw sensor data i
n a bottom-up fashion. Second\, it should allow us to ditch fixed datasets
and enable continuous\, online learning\, which is a much more natural se
tting for real-world agents. Third\, and most intriguingly\, there is hope
that it might be possible to force a self-supervised task curriculum to e
merge from first principles\, even in the absence of a pre-defined downstr
eam task or goal\, similar to evolution. In this talk\, I will touch upon
these themes to argue that\, far from running its course\, research in sel
f-supervised learning is only just beginning.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2295@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:Canary Center\,Early Cancer Detection Seminar Ser
ies
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://canarycenter.stan
ford.edu/seminars.html
DESCRIPTION:CEDSS: The First Cell: A new model for cancer research and trea
tment\nAzra Raza\, M.D.\nChan Soon-Shiong Professor of Medicine\nDirector\
, Myelodysplastic Syndrome Center\nColumbia University Medical Center\n \n
Location: Zoom\nMeeting URL: https://stanford.zoom.us/s/99340345860\nDial:
US: +1 650 724 9799 or +1 833 302 1536 (Toll Free)\nMeeting ID: 993 4034
5860\nPasscode: 711508\nRSVP Here\n \nABSTRACT\nCancer research continues
to be predicated on a 1970’s model of research and treatment. Despite hal
f a century of intense research\, we are failing spectacularly to improve
the outcome for patients with advanced disease. Those who are cured contin
ue to be treated mostly with the older strategies (surgery-chemo-radiation
). Our contention is that the real solution to the cancer problem is to di
agnose cancer early\, at the stage of The First Cell. The rapidly evolving
technologies are doing much in this area but need to be expanded. We stud
y a pre-leukemic condition called myelodysplastic syndrome (MDS) with the
hope that we can detect the first leukemia cells as the disease transforms
to acute myeloid leukemia (AML). Towards this end\, we have collected blo
od and bone marrow samples on MDS and AML patients since 1984. Today\, our
Tissue Repository has more than 60\,000 samples. We propose novel methods
to identify surrogate markers that can identify the First Cell through st
udying the serial samples of patients who evolve from MDS to AML.\n \nABOU
T\nDr. Raza is a Professor of Medicine and Director of the MDS Center at C
olumbia University in New York\, NY.She started her research in Myelodispl
astic Syndromes (MDS) in 1982 and moved to Rush University\, Chicago\, Ill
inois in 1992\, where she was the Charles Arthur Weaver Professor in Oncol
ogy and Director\, Division of Myeloid Diseases. The MDS Program\, along w
ith a Tissue Repository containing more than 50\,000 samples from MDS and
acute leukemia patients was successfully relocated to the University of Ma
ssachusetts in 2004 and to Columbia University in 2010.\nBefore moving to
New York\, Dr. Raza was the Chief of Hematology Oncology and the Gladys Sm
ith Martin Professor of Oncology at the University of Massachussetts in Wo
rcester. She has published the results of her laboratory research and clin
ical trials in prestigious\, peer reviewed journals such as The New Englan
d Journal of Medicine\, Nature\, Blood\, Cancer\, Cancer Research\, Britis
h Journal of Hematology\, Leukemia\, and Leukemia Research. Dr. Raza serve
s on numerous national and international panels as a reviewer\, consultant
and advisor and is the recipient of a number of awards.\n \nHosted by: Ut
kan Demirci\, Ph.D.\nSponsored by: The Canary Center & the Department of R
adiology \nStanford University – School of Medicine
DTSTART;TZID=America/Los_Angeles:20211012T110000
DTEND;TZID=America/Los_Angeles:20211012T120000
LOCATION:Venue coming soon!
SEQUENCE:0
SUMMARY:Cancer Early Detection Seminar Series – Azra Raza\, MD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/cancer-e
arly-detection-seminar-series-azra-raza-md/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/A_Raza-150x150.png\;150\;150\;1\,mediu
m\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upl
oads/2019/10/A_Raza-300x200.png\;300\;200\;1\,large\;http://web.stanford.e
du/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2019/10/A_Raza.png\
;640\;426\;\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalenda
r/wp-content/uploads/2019/10/A_Raza.png\;700\;466\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
CEDSS: The First Cell: A new model
for cancer research and treatment
\n
Azra Raza\, M.D. \nChan
Soon-Shiong Professor of Medicine \nDirector\, Myelodysplastic Syndro
me Center \nColumbia University Medical Center
\n
\n
L
ocation: Zoom \nMeeting URL: https:
//stanford.zoom.us/s/99340345860 \nDial: US: +1 650 724 9799 or
+1 833 302 1536 (Toll Free) \nMeeting ID: 993 4034 5860 \nPassco
de: 711508
Cancer research continues to
be predicated on a 1970’s model of research and treatment. Despite half a
century of intense research\, we are failing spectacularly to improve the
outcome for patients with advanced disease. Those who are cured continue
to be treated mostly with the older strategies (surgery-chemo-radiation).
Our contention is that the real solution to the cancer problem is to diagn
ose cancer early\, at the stage of The First Cell. The rapidly evolving te
chnologies are doing much in this area but need to be expanded. We study a
pre-leukemic condition called myelodysplastic syndrome (MDS) with the hop
e that we can detect the first leukemia cells as the disease transforms to
acute myeloid leukemia (AML). Towards this end\, we have collected blood
and bone marrow samples on MDS and AML patients since 1984. Today\, our Ti
ssue Repository has more than 60\,000 samples. We propose novel methods to
identify surrogate markers that can identify the First Cell through study
ing the serial samples of patients who evolve from MDS to AML.
\n
p>\n
ABOUT
\n
Dr. Raza is a Professor of Medicine
and Director of the MDS Center at Columbia University in New York\, NY.She
started her research in Myelodisplastic Syndromes (MDS) in 1982 and moved
to Rush University\, Chicago\, Illinois in 1992\, where she was the Charl
es Arthur Weaver Professor in Oncology and Director\, Division of Myeloid
Diseases. The MDS Program\, along with a Tissue Repository containing more
than 50\,000 samples from MDS and acute leukemia patients was successfull
y relocated to the University of Massachusetts in 2004 and to Columbia Uni
versity in 2010.
\n
Before moving to New York\, Dr. Raza was the Chie
f of Hematology Oncology and the Gladys Smith Martin Professor of Oncology
at the University of Massachussetts in Worcester. She has published the r
esults of her laboratory research and clinical trials in prestigious\, pee
r reviewed journals such as The New England Journal of Medicine\, Nature\,
Blood\, Cancer\, Cancer Research\, British Journal of Hematology\, Leukem
ia\, and Leukemia Research. Dr. Raza serves on numerous national and inter
national panels as a reviewer\, consultant and advisor and is the recipien
t of a number of awards.
\n
\n
Hosted by: Utkan Demirci\,
Ph.D. \nSponsored by: Th
e Canary Center & the Department of Radiology \nStanford Un
iversity – School of Medicine
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2521@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:MIPS\,MIPS Seminar
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://med.stanford.edu/
mips/events.html
DESCRIPTION:MIPS Seminar Series: Title TBA\nSteven Paul Poplack\, MD\nProfe
ssor of Radiology (Breast Imaging)\nStanford University Medical Center\n
\nLocation: Coming soon!\n12:00pm – 12:45pm Seminar & Discussion\nRSVP: Co
ming soon!\n \nABSTRACT\nComing soon!\n \nABOUT\nComing soon!\n \nHosted b
y: Katherine Ferrara\, PhD\nSponsored by: Molecular Imaging Program at Sta
nford & the Department of Radiology
DTSTART;TZID=America/Los_Angeles:20211028T120000
DTEND;TZID=America/Los_Angeles:20211028T124500
LOCATION:Venue coming soon!
SEQUENCE:0
SUMMARY:MIPS Seminar – Steven Paul Poplack\, MD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/mips-sem
inar-steven-paul-poplack-md/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/steven-poplack-150x150.jpg\;150\;150\;
1\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-con
tent/uploads/2019/10/steven-poplack-300x300.jpg\;300\;300\;1\,large\;http:
//web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/201
9/10/steven-poplack.jpg\;320\;320\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
MIPS Seminar Series: Title TBA
\n
Steven Paul Poplack\, MD \nProfessor of Radiology
(Breast Imaging) \nStanford University Medical Center
Hosted by: Katherine Ferrara\, PhD \nSponsored by: Molecular Imaging Program at Stanford & the Department of
Radiology
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3033@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; http://ibiis.stan
ford.edu/events/seminars/2021seminars.html
DESCRIPTION:Saeed Hassanpour\, PhD\nAssociate Professor of Biomedical Data
Science\nAssociate Professor of Epidemiology\nAssociate Professor of Compu
ter Science\nDartmouth Geisel School of Medicine\nDeep Learning for Histol
ogy Images Analysis\nAbstract:\nWith the recent expansions of whole-slide
digital scanning\, archiving\, and high-throughput tissue banks\, the fiel
d of digital pathology is primed to benefit significantly from deep learni
ng technology. This talk will cover several applications of deep learning
for characterizing histopathological patterns on high-resolution microscop
y images for cancerous and precancerous lesions. Furthermore\, the current
challenges for building deep learning models for pathology image analysis
will be discussed and new methodological advances to address these bottle
necks will be presented.\nAbout:\nDr. Saeed Hassanpour is an Associate Pro
fessor in the Departments of Biomedical Data Science\, Computer Science\,
and Epidemiology at Dartmouth College. His research is focused on machine
learning and multimodal data analysis for precision health. Dr. Hassanpour
has led multiple NIH-funded research projects\, which resulted in novel m
achine learning and deep learning models for medical image analysis and cl
inical text mining to improve diagnosis\, prognosis\, and personalized the
rapies. Before joining Dartmouth\, he worked as a Research Engineer at Mic
rosoft. Dr. Hassanpour received his Ph.D. in Electrical Engineering with a
minor in Biomedical Informatics from Stanford University and completed hi
s postdoctoral training at Stanford Center for Artificial Intelligence in
Medicine & Imaging.
DTSTART;TZID=America/Los_Angeles:20211117T120000
DTEND;TZID=America/Los_Angeles:20211117T130000
LOCATION:Zoom: https://stanford.zoom.us/j/91788140120?pwd=K2NvMHZ2SUFVWjc1d
2xJUndjTG9lQT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Deep Learning for Histology Images Analysis
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-deep-learning-for-histology-images-analysis/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2021/11/Saeed.jpg\;300\;300\,medium\;http://we
b.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2021/11
/Saeed.jpg\;300\;300\,large\;http://web.stanford.edu/group/radweb/cgi-bin/
radcalendar/wp-content/uploads/2021/11/Saeed.jpg\;300\;300\,full\;http://w
eb.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2021/1
1/Saeed.jpg\;300\;300
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
S
aeed Hassanpour\, PhD \nAssociate Professor of Biomedical Da
ta Science \nAssociate Professor of Epidemiology \nAssociate Pro
fessor of Computer Science \nDartmouth Geisel School of Medicine
\n
Deep Learning for Histology Images Analysis
\n
Abstract: \nWith the recent expansions of whole-slid
e digital scanning\, archiving\, and high-throughput tissue banks\, the fi
eld of digital pathology is primed to benefit significantly from deep lear
ning technology. This talk will cover several applications of deep learnin
g for characterizing histopathological patterns on high-resolution microsc
opy images for cancerous and precancerous lesions. Furthermore\, the curre
nt challenges for building deep learning models for pathology image analys
is will be discussed and new methodological advances to address these bott
lenecks will be presented.
\n
About:
\n
Dr. Sae
ed Hassanpour is an Associate Professor in the Departments of Biomedical D
ata Science\, Computer Science\, and Epidemiology at Dartmouth College. Hi
s research is focused on machine learning and multimodal data analysis for
precision health. Dr. Hassanpour has led multiple NIH-funded research pro
jects\, which resulted in novel machine learning and deep learning models
for medical image analysis and clinical text mining to improve diagnosis\,
prognosis\, and personalized therapies. Before joining Dartmouth\, he wor
ked as a Research Engineer at Microsoft. Dr. Hassanpour received his Ph.D.
in Electrical Engineering with a minor in Biomedical Informatics from Sta
nford University and completed his postdoctoral training at Stanford Cente
r for Artificial Intelligence in Medicine & Imaging.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-2547@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:MIPS\,MIPS Seminar
CONTACT:Ashley Williams\; ashleylw@stanford.edu\; https://med.stanford.edu/
mips/events.html
DESCRIPTION:MIPS Seminar Series: Title TBA\nMatthew Bogyo\, PhD\nProfessor
of Pathology and of Microbiology and Immunology and\, by courtesy\, of Che
mical and Systems Biology\nStanford University\n \nLocation: Coming soon!
\n12:00pm – 12:45pm Seminar & Discussion\nRSVP: Coming soon!\n \nABSTRACT
\nComing soon!\n \nABOUT\nDr. Bogyo received a B.Sc. degree in Chemistry f
rom Bates College in 1993 and a Ph.D. in Biochemistry from the Massachuset
ts Institute of Technology in 1997. After completion of his degree he was
appointed as a Faculty Fellow in the Department of Biochemistry and Biophy
sics at the University of California\, San Francisco. Dr. Bogyo served as
the Head of Chemical Proteomics at Celera Genomics from 2001 to 2003 while
maintaining an Adjunct Faculty appointment at UCSF. In the Summer of 2003
Dr. Bogyo joined the Department of Pathology at Stanford Medical School a
nd was appointed as a faculty member in the Department of Microbiology and
Immunology in 2004. His interests are focused on the use of chemistry to
study the role of proteases in human disease. In particular his laboratory
is currently working on understanding the role of cysteine proteases in t
umorgenesis and also in the life cycle of human parasites and bacterial pa
thogens. Dr. Bogyo currently serves on the Editorial Board of Biochemical
Journal\, Cell Chemical Biology\, Molecular and Cellular Proteomics and is
an Academic Editor at PLoS One. Dr. Bogyo is a consultant for several bio
technology and pharmaceutical companies in the Bay Area and is a founder a
nd board member of Akrotome Imaging and Facile Therapeutics.\n \nHosted by
: Katherine Ferrara\, PhD\nSponsored by: Molecular Imaging Program at Stan
ford & the Department of Radiology
DTSTART;TZID=America/Los_Angeles:20211118T120000
DTEND;TZID=America/Los_Angeles:20211118T124500
LOCATION:Venue coming soon!
SEQUENCE:0
SUMMARY:MIPS Seminar – Matthew Bogyo\, PhD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/mips-sem
inar-matthew-bogyo-phd/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2019/10/BogyoHeadshotJuly2017-150x150.jpg\;150
\;150\;1\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar
/wp-content/uploads/2019/10/BogyoHeadshotJuly2017-244x300.jpg\;244\;300\;1
\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-conte
nt/uploads/2019/10/BogyoHeadshotJuly2017.jpg\;320\;393\;
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
MIPS Seminar Ser
ies: Title TBA
\n
Matthew Bogyo\, PhD \nProfessor of Pathology and of M
icrobiology and Immunology and\, by courtesy\, of Chemical and Systems Bio
logy \nStanford University
ABOUT \nDr. Bogyo received a B.Sc. degree in
Chemistry from Bates College in 1993 and a Ph.D. in Biochemistry from the
Massachusetts Institute of Technology in 1997. After completion of his deg
ree he was appointed as a Faculty Fellow in the Department of Biochemistry
and Biophysics at the University of California\, San Francisco. Dr. Bogyo
served as the Head of Chemical Proteomics at Celera Genomics from 2001 to
2003 while maintaining an Adjunct Faculty appointment at UCSF. In the Sum
mer of 2003 Dr. Bogyo joined the Department of Pathology at Stanford Medic
al School and was appointed as a faculty member in the Department of Micro
biology and Immunology in 2004. His interests are focused on the use of ch
emistry to study the role of proteases in human disease. In particular his
laboratory is currently working on understanding the role of cysteine pro
teases in tumorgenesis and also in the life cycle of human parasites and b
acterial pathogens. Dr. Bogyo currently serves on the Editorial Board of B
iochemical Journal\, Cell Chemical Biology\, Molecular and Cellular Proteo
mics and is an Academic Editor at PLoS One. Dr. Bogyo is a consultant for
several biotechnology and pharmaceutical companies in the Bay Area and is
a founder and board member of Akrotome Imaging and Facile Therapeutics.
\n
\n
Hosted by: Katherine Ferrara\, PhD \nSpo
nsored by: Molecular Imaging Program at Stanford & the Department of Radio
logy
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3039@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; http://ibiis.stan
ford.edu/events/seminars/2021seminars.html
DESCRIPTION:Indrani Bhattacharya\, PhD\nPostdoctoral Research Fellow\nDepar
tment of Radiology\nStanford University\nTitle: Multimodal Data Fusion for
Selective Identification of Aggressive and Indolent Prostate Cancer on Ma
gnetic Resonance Imaging\nAbstract: Automated methods for detecting prosta
te cancer and distinguishing indolent from aggressive disease on Magnetic
Resonance Imaging (MRI) could assist in early diagnosis and treatment plan
ning. Existing automated methods of prostate cancer detection mostly rely
on ground truth labels with limited accuracy\, ignore disease pathology ch
aracteristics observed on resected tissue\, and cannot selectively identif
y aggressive (Gleason Pattern≥4) and indolent (Gleason Pattern=3) cancers
when they co-exist in mixed lesions. This talk will cover multimodal and m
ulti-scale fusion approaches to integrate radiology images\, pathology ima
ges\, and clinical domain knowledge about prostate cancer distribution to
selectively identify and localize aggressive and indolent cancers on prost
ate MRI.\n\nRogier van der Sluijs\, PhD\nPostdoctoral Research Fellow\nDep
artment of Radiology\nStanford University\nTitle: Pretraining Neural Netwo
rks for Medical AI\nAbstract: Transfer learning has quickly become standar
d practice for deep learning on medical images. Typically\, practitioners
repurpose existing neural networks and their corresponding weights to boot
strap model development. This talk will cover several methods to pretrain
neural networks for medical tasks. The current challenges for pretraining
neural networks in Radiology will be discussed and recent advancements tha
t address these bottlenecks will be highlighted.
DTSTART;TZID=America/Los_Angeles:20211215T120000
DTEND;TZID=America/Los_Angeles:20211215T130000
LOCATION:Zoom: https://stanford.zoom.us/j/95371438521?pwd=Y3BheHpUanpESnh6V
UkycVhlUWtodz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Indrani Bhattacharya\, PhD & Rogier van der S
luijs\, PhD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-indrani-bhattacharya-phd-rogier-van-der-sluijs-phd/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2021/12/Indrani.jpg\;200\;200\,medium\;http://
web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2021/
12/Indrani.jpg\;200\;200\,large\;http://web.stanford.edu/group/radweb/cgi-
bin/radcalendar/wp-content/uploads/2021/12/Indrani.jpg\;200\;200\,full\;ht
tp://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/
2021/12/Indrani.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Indrani Bhattacharya\, PhD \nPostdoctoral Research Fell
ow \nDepartment of Radiology \nStanford University
\n
Title: Multimodal Data Fusion for Selective Identification of
Aggressive and Indolent Prostate Cancer on Magnetic Resonance Imaging
\n
Abstract: Automated methods for detecting prostate c
ancer and distinguishing indolent from aggressive disease on Magnetic Reso
nance Imaging (MRI) could assist in early diagnosis and treatment planning
. Existing automated methods of prostate cancer detection mostly rely on g
round truth labels with limited accuracy\, ignore disease pathology charac
teristics observed on resected tissue\, and cannot selectively identify ag
gressive (Gleason Pattern≥4) and indolent (Gleason Pattern=3) cancers when
they co-exist in mixed lesions. This talk will cover multimodal and multi
-scale fusion approaches to integrate radiology images\, pathology images\
, and clinical domain knowledge about prostate cancer distribution to sele
ctively identify and localize aggressive and indolent cancers on prostate
MRI.
\n\n
R
ogier van der Sluijs\, PhD \nPostdoctoral Research Fellow \nDepartment of Radiology \nStanford University
\n
Ti
tle: Pretraining Neural Networks for Medical AI
\n
A
bstract: Transfer learning has quickly become standard practice f
or deep learning on medical images. Typically\, practitioners repurpose ex
isting neural networks and their corresponding weights to bootstrap model
development. This talk will cover several methods to pretrain neural netwo
rks for medical tasks. The current challenges for pretraining neural netwo
rks in Radiology will be discussed and recent advancements that address th
ese bottlenecks will be highlighted.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3047@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:Nina Kottler\, MD\, MS\nAssociate Chief Medical Officer\, Clini
cal AI\nVP Clinical Operations\nRadiology Partners\nAbstract:\nWe have a c
all to action in healthcare – we need to drive value. Artificial intellig
ence (AI)\, if deployed correctly\, can help accomplish this lofty mission
. In this discussion we will review the following lessons learned in depl
oying radiology AI at scale: 4 unexpected benefits of implementing AI eme
rgent finding triage\; the importance of investing in AI radiologist educa
tion\; how “most” AI needs to be incorporated into the radiologist workflo
w\; why a platform is required to deploy AI at scale and what a modern pla
tform looks like\; how to use AI to add value to your data\; and\, as Dr.
Curt Langlotz famously said\, why rads (practices) who use AI will replace
those who don’t (a depiction of what the role of the radiologist might lo
ok like in a tech enabled future).\nBio:\nDr. Kottler has been a practicin
g radiologist specializing in emergency imaging for over 16 years. Combin
ing her clinical experience with a graduate degree in applied mathematics\
, she has been using technological innovation to drive value in radiology.
As the first radiologist to join Radiology Partners\, Dr. Kottler has he
ld multiple leadership positions within her practice and is currently the
associate Chief Medical Officer for Clinical AI. Externally Dr. Kottler s
erves on multiple committees for the ACR\, RSNA\, and SIIM. Dr. Kottler i
s also passionate about promoting diversity and creating a culture of belo
nging. As such she is a member of the AAWR\, is a member of the diversity
and inclusion committee at SIIM\, serves on the steering committee for RA
D=\, and leads the education and development division of the Belonging Com
mittee within Radiology Partners.
DTSTART;TZID=America/Los_Angeles:20220119T120000
DTEND;TZID=America/Los_Angeles:20220119T130000
LOCATION:Zoom: https://stanford.zoom.us/j/92632628279?pwd=S3RFdXdEUmEweTNKe
lhrcmVxQUExdz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: AI In Clinical Use – Lessons Learned
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-ai-in-clinical-use-lessons-learned/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/01/Nina-Kottler-2021.jpg\;200\;200\,mediu
m\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upl
oads/2022/01/Nina-Kottler-2021.jpg\;200\;200\,large\;http://web.stanford.e
du/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/01/Nina-Kottle
r-2021.jpg\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/r
adcalendar/wp-content/uploads/2022/01/Nina-Kottler-2021.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Nina Kottler\, MD\, MS \nAssociate
Chief Medical Officer\, Clinical AI \nVP Clinical Operations \nR
adiology Partners
\n
Abstract: \nWe have a call
to action in healthcare – we need to drive value. Artificial intelligenc
e (AI)\, if deployed correctly\, can help accomplish this lofty mission.
In this discussion we will review the following lessons learned in deployi
ng radiology AI at scale: 4 unexpected benefits of implementing AI emerge
nt finding triage\; the importance of investing in AI radiologist educatio
n\; how “most” AI needs to be incorporated into the radiologist workflow\;
why a platform is required to deploy AI at scale and what a modern platfo
rm looks like\; how to use AI to add value to your data\; and\, as Dr. Cur
t Langlotz famously said\, why rads (practices) who use AI will replace th
ose who don’t (a depiction of what the role of the radiologist might look
like in a tech enabled future).
\n
Bio: \nDr. K
ottler has been a practicing radiologist specializing in emergency imaging
for over 16 years. Combining her clinical experience with a graduate deg
ree in applied mathematics\, she has been using technological innovation t
o drive value in radiology. As the first radiologist to join Radiology Pa
rtners\, Dr. Kottler has held multiple leadership positions within her pra
ctice and is currently the associate Chief Medical Officer for Clinical AI
. Externally Dr. Kottler serves on multiple committees for the ACR\, RSNA
\, and SIIM. Dr. Kottler is also passionate about promoting diversity and
creating a culture of belonging. As such she is a member of the AAWR\, i
s a member of the diversity and inclusion committee at SIIM\, serves on th
e steering committee for RAD=\, and leads the education and development di
vision of the Belonging Committee within Radiology Partners.
\n<
/HTML>
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3053@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:Spyridon (Spyros) Bakas\, PhD\nAssistant Professor in the Depar
tment of Pathology\,\nLaboratory Medicine\, and of Radiology\nCenter for B
iomedical Image Computing and Analytics (CBICA)\nPerelman School of Medici
ne\nUniversity of Pennsylvania\nTitle: Imaging Analytics for Neuro-Oncolog
y:\nTowards Computational Diagnostics\nAbstract: Central nervous system (C
NS) tumors come with vastly heterogeneous histologic\, molecular\, and rad
iographic landscapes\, rendering their precise characterization challengin
g. The rapidly growing fields of biophysical modeling and radiomics have s
hown promise in better characterizing the molecular\, spatial\, and tempor
al heterogeneity of tumors. Integrative analysis of CNS tumors\, including
clinically acquired multi-parametric magnetic resonance imaging (mpMRI)\,
assists in identifying macroscopic quantifiable tumor patterns of invasio
n and proliferation\, potentially leading to improved (a) detection/segmen
tation of tumor subregions and (b) computer-aided diagnostic/prognostic/pr
edictive modeling. This talk will touch upon example studies on this space
\, as well as an overview of the largest to-date real-world federated lear
ning study to detect brain tumor boundaries.
DTSTART;TZID=America/Los_Angeles:20220216T120000
DTEND;TZID=America/Los_Angeles:20220216T130000
LOCATION:ZOOM: https://stanford.zoom.us/j/98789338790?pwd=OXRORjhYUUdaRGJpU
HJZdzZ5NGw5dz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Imaging Analytics for Neuro-Oncology: Towards
Computational Diagnostics
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-imaging-analytics-for-neuro-oncology-towards-computational-diag
nostics/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-A
M.jpg\;200\;200\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radc
alendar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-AM
.jpg\;200\;200\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcal
endar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-AM.j
pg\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalend
ar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-AM.jpg\
;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Spyridon (Spyros) Bakas\, PhD \nAssistant P
rofessor in the Department of Pathology\, \nLaboratory Medicine\, and
of Radiology \nCenter for Biomedical Image Computing and Analytics (
CBICA) \nPerelman School of Medicine \nUniversity of Pennsylvani
a
\n
Title: Imaging Analytics for Neuro-Oncology: \nTowar
ds Computational Diagnostics
\n
Abstract: Central ne
rvous system (CNS) tumors come with vastly heterogeneous histologic\, mole
cular\, and radiographic landscapes\, rendering their precise characteriza
tion challenging. The rapidly growing fields of biophysical modeling and r
adiomics have shown promise in better characterizing the molecular\, spati
al\, and temporal heterogeneity of tumors. Integrative analysis of CNS tum
ors\, including clinically acquired multi-parametric magnetic resonance im
aging (mpMRI)\, assists in identifying macroscopic quantifiable tumor patt
erns of invasion and proliferation\, potentially leading to improved (a) d
etection/segmentation of tumor subregions and (b) computer-aided diagnosti
c/prognostic/predictive modeling. This talk will touch upon example studie
s on this space\, as well as an overview of the largest to-date real-world
federated learning study to detect brain tumor boundaries.
\n
HTML>
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3061@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:Harini Veeraraghavan\, PhD\nAssociate Attending Computer Scient
ist\nDepartment of Medical Physics\nMemorial Sloan-Kettering Cancer Center
\nUsing AI for Longitudinal Tumor Response Monitoring and AI Guided Cancer
Treatments: From Lab to Clinic\nAbstract:\nCancer patients are imaged wit
h multiple imaging modalities as part of routine cancer care. However\, th
e rich information available from the images are not fully exploited to be
tter manage patient care through earlier intervention as well as more prec
ise targeted treatments. In this talk\, I will present some of the new AI
methodologies we have been developing to track tumor response as well as f
rom routinely acquired imaging applied to image-guided radiation treatment
s using CT/cone-beam CT as well as MRI-guided precision treatments. I will
also present some demonstration studies of how AI based automated segment
ation and tumor as well as healthy tissue change assessment can be used to
early detect treatment toxicities to enable clinicians to better manage c
ancer care. Finally\, I will show how these developed methods have been pu
t to routine clinical care for automating radiotherapy treatment planning
at MSK.
DTSTART;TZID=America/Los_Angeles:20220316T120000
DTEND;TZID=America/Los_Angeles:20220316T130000
LOCATION:ZOOM: https://stanford.zoom.us/j/99319571697?pwd=c2lhRkN4cXEzTzFzM
UhKaTVJMHZLQT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Using AI for Longitudinal Tumor Response Moni
toring and AI Guided Cancer Treatments: From Lab to Clinic
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-using-ai-for-longitudinal-tumor-response-monitoring-and-ai-guid
ed-cancer-treatments-from-lab-to-clinic/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/03/harini-veeraraghavan_15_1200x800.jpg\;
200\;200\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar
/wp-content/uploads/2022/03/harini-veeraraghavan_15_1200x800.jpg\;200\;200
\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-conte
nt/uploads/2022/03/harini-veeraraghavan_15_1200x800.jpg\;200\;200\,full\;h
ttp://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads
/2022/03/harini-veeraraghavan_15_1200x800.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Harini Veeraraghavan\, PhD \nAssociate Attending Computer Scient
ist \nDepartment of Medical Physics \nMemorial Sloan-Kettering C
ancer Center
\n
Using AI for Longitudinal Tumor Response Moni
toring and AI Guided Cancer Treatments: From Lab to Clinic
\n<
p>Abstract: \nCancer patients are imaged with multip
le imaging modalities as part of routine cancer care. However\, the rich i
nformation available from the images are not fully exploited to better man
age patient care through earlier intervention as well as more precise targ
eted treatments. In this talk\, I will present some of the new AI methodol
ogies we have been developing to track tumor response as well as from rout
inely acquired imaging applied to image-guided radiation treatments using
CT/cone-beam CT as well as MRI-guided precision treatments. I will also pr
esent some demonstration studies of how AI based automated segmentation an
d tumor as well as healthy tissue change assessment can be used to early d
etect treatment toxicities to enable clinicians to better manage cancer ca
re. Finally\, I will show how these developed methods have been put to rou
tine clinical care for automating radiotherapy treatment planning at MSK.<
/p>\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3071@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; rtotah@stanford.edu\; https://ibiis.stanford.edu/even
ts/seminars/2022seminars.html
DESCRIPTION:Spyridon (Spyros) Bakas\, PhD\nAssistant Professor in the Depar
tment of Pathology\,\nLaboratory Medicine\, and of Radiology\nCenter for B
iomedical Image Computing and Analytics (CBICA)\nPerelman School of Medici
ne\nUniversity of Pennsylvania\nTitle: Imaging Analytics for Neuro-Oncolog
y: Towards Computational Diagnostics\nCentral nervous system (CNS) tumors
come with vastly heterogeneous histologic\, molecular\, and radiographic l
andscapes\, rendering their precise characterization challenging. The rapi
dly growing fields of biophysical modeling and radiomics have shown promis
e in better characterizing the molecular\, spatial\, and temporal heteroge
neity of tumors. Integrative analysis of CNS tumors\, including clinically
acquired multi-parametric magnetic resonance imaging (mpMRI)\, assists in
identifying macroscopic quantifiable tumor patterns of invasion and proli
feration\, potentially leading to improved (a) detection/segmentation of t
umor subregions and (b) computer-aided diagnostic/prognostic/predictive mo
deling. This talk will touch upon example studies on this space\, as well
as an overview of the largest to-date real-world federated learning study
to detect brain tumor boundaries.
DTSTART;TZID=America/Los_Angeles:20220414T110000
DTEND;TZID=America/Los_Angeles:20220414T120000
LOCATION:Zoom: https://stanford.zoom.us/j/98789338790?pwd=OXRORjhYUUdaRGJpU
HJZdzZ5NGw5dz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Imaging Analytics for Neuro-Oncology: Towards
Computational Diagnostics
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-imaging-analytics-for-neuro-oncology-towards-computational-diag
nostics-2/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-A
M.jpg\;200\;200\,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radc
alendar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-AM
.jpg\;200\;200\,large\;http://web.stanford.edu/group/radweb/cgi-bin/radcal
endar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-AM.j
pg\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalend
ar/wp-content/uploads/2022/02/bakas-aibil-headshot-160-215-8.37.55-AM.jpg\
;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Spyridon (Spyros) Bakas\, PhD \nAssistant P
rofessor in the Department of Pathology\, \nLaboratory Medicine\, and
of Radiology \nCenter for Biomedical Image Computing and Analytics (
CBICA) \nPerelman School of Medicine \nUniversity of Pennsylvani
a
\n
Title: Imaging Analytics for Neuro-Oncology: Towards Comp
utational Diagnostics
\n
Central nervous system (CNS) tumors come wit
h vastly heterogeneous histologic\, molecular\, and radiographic landscape
s\, rendering their precise characterization challenging. The rapidly grow
ing fields of biophysical modeling and radiomics have shown promise in bet
ter characterizing the molecular\, spatial\, and temporal heterogeneity of
tumors. Integrative analysis of CNS tumors\, including clinically acquire
d multi-parametric magnetic resonance imaging (mpMRI)\, assists in identif
ying macroscopic quantifiable tumor patterns of invasion and proliferation
\, potentially leading to improved (a) detection/segmentation of tumor sub
regions and (b) computer-aided diagnostic/prognostic/predictive modeling.
This talk will touch upon example studies on this space\, as well as an ov
erview of the largest to-date real-world federated learning study to detec
t brain tumor boundaries.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3069@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:
DESCRIPTION:Daniel Marcus\, PhD\nProfessor of Radiology\nDirector of the Ne
uroinformatics Research Group\nDirector of the Neuroimaging Informatics an
d Analysis Center\nWashington University\nAbstract:\nDeveloping and deploy
ing computational tools for neuro-oncology applications includes a sequenc
e of complex steps to identify appropriate images\, assess image quality\,
annotate\, process and other prepare and manipulate data for analysis. We
have implemented services and tools on the open source XNAT informatics p
latform to automate much of this workflow to improve both its efficiency a
nd effectiveness. Dr. Marcus will discuss this automated workflow and its
implementation in a number of data sets and applications at Washington Uni
versity.
DTSTART;TZID=America/Los_Angeles:20220420T120000
DTEND;TZID=America/Los_Angeles:20220420T130000
LOCATION:Zoom: https://stanford.zoom.us/j/94439662481?pwd=N1BUc2FqWUt4QVlQM
nNSS21rcEV4UT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Automated Workflows for Neuro-Oncology Image
Analysis
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-automated-workflows-for-neuro-oncology-image-analysis/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/04/Daniel-Marcus.jpg\;200\;200\,medium\;h
ttp://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads
/2022/04/Daniel-Marcus.jpg\;200\;200\,large\;http://web.stanford.edu/group
/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/04/Daniel-Marcus.jpg\;
200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/w
p-content/uploads/2022/04/Daniel-Marcus.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Daniel Marcus\, PhD \nProfessor of Radiology \nDirector of the Neuroinformatics Research Group \nDirector of th
e Neuroimaging Informatics and Analysis Center \nWashington Universit
y
\n
Abstract: \nDeveloping and deploying computational tools fo
r neuro-oncology applications includes a sequence of complex steps to iden
tify appropriate images\, assess image quality\, annotate\, process and ot
her prepare and manipulate data for analysis. We have implemented services
and tools on the open source XNAT informatics platform to automate much o
f this workflow to improve both its efficiency and effectiveness. Dr. Marc
us will discuss this automated workflow and its implementation in a number
of data sets and applications at Washington University.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3077@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; rtotah@stanford.edu\; https://ibiis.stanford.edu/even
ts/seminars/2022seminars.html
DESCRIPTION:Lena Maier-Hein\, PhD\nHead of Department\, Computer Assisted M
edical Interventions\nManaging Director\, Data Science and Digital Oncolog
y\nManaging Director\, National Center for Tumor Diseases\nGerman Cancer R
esearch Center\nTitle: Missing the (Bench)mark?\n\n\n\n\n\n\n\n\n\nAbstrac
t\n\n\n\n\n\n\n\nMachine learning has begun to revolutionize almost all ar
eas of health research. Success stories cover a wide variety of applicatio
n fields ranging from radiology and gastroenterology all the way to mental
health. Strikingly\, however\, solutions that perform favorably in resear
ch generally do not translate well to clinical practice\, and little atten
tion is being given to learning from failures. Focusing on biomedical imag
e analysis as a key area of health-related machine learning\, this talk wi
ll present pitfalls\, caveats and recommendations related to machine learn
ing-based biomedical image analysis. As a particular highlight\, it will c
over yet unpublished work on two key research questions related to biomedi
cal image analysis competitions: 1) How can we best select performance met
rics according to the characteristics of the driving biomedical question?
And 2) Why is the winner the best? The results have been compiled based on
the input of hundreds of image analysis researchers worldwide.
DTSTART;TZID=America/Los_Angeles:20220518T093000
DTEND;TZID=America/Los_Angeles:20220518T103000
LOCATION:Zoom: https://stanford.zoom.us/j/95872488712?pwd=dDhmT1JPdWtTSlBOQ
1BENmtGOUxjUT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Missing the (Bench)mark?
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-missing-the-benchmark/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/05/Meier-Hein.jpg\;200\;200\,medium\;http
://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/20
22/05/Meier-Hein.jpg\;200\;200\,large\;http://web.stanford.edu/group/radwe
b/cgi-bin/radcalendar/wp-content/uploads/2022/05/Meier-Hein.jpg\;200\;200\
,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content
/uploads/2022/05/Meier-Hein.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
\n
\n
\n
Lena Maier-Hein\,
PhD \nHead of Department\, Computer Assisted Medical Intervention
s \nManaging Director\, Data Science and Digital Oncology \nMana
ging Director\, National Center for Tumor Diseases \nGerman Cancer Re
search Center
\n
Title: Missing the (Bench)mark?
\n
\n
\n
\n
\n
\n
\n\n
\n
\n
Abstract
\n
\n
\n
\n
\n
\n
\n
\n
Machine learning has begun to revol
utionize almost all areas of health research. Success stories cover a wide
variety of application fields ranging from radiology and gastroenterology
all the way to mental health. Strikingly\, however\, solutions that perfo
rm favorably in research generally do not translate well to clinical pract
ice\, and little attention is being given to learning from failures. Focus
ing on biomedical image analysis as a key area of health-related machine l
earning\, this talk will present pitfalls\, caveats and recommendations re
lated to machine learning-based biomedical image analysis. As a particular
highlight\, it will cover yet unpublished work on two key research questi
ons related to biomedical image analysis competitions: 1) How can we best
select performance metrics according to the characteristics of the driving
biomedical question? And 2) Why is the winner the best? The results have
been compiled based on the input of hundreds of image analysis researchers
worldwide.
\n
\n
\n
\n
\n
\n
\n
\n<
/div>\n
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3083@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:Lauren Oakden-Rayner\, PhD\nDirector of Research in Medical Ima
ging\nRoyal Adelaide Hospital\nSenior Research Fellow\nAustralian Institut
e for Machine Learning\nTitle: Medical AI Safety – A Clinical Perspective
\nAbstract:\nMedical artificial intelligence is rapidly moving into clinic
s\, particularly in imaging-based specialties such as radiology. This tran
sition is producing many new challenges\, as the regulatory environment ha
s struggled to keep up and AI training for healthcare workers is virtually
non-existent. Dr. Oakden-Rayner will provide a clinical safety perspectiv
e on medical AI\, discuss a range of identified risks and potential harms\
, and discuss possible solutions to mitigate these risks as this exciting
field continues to develop.\nBio:\nDr. Lauren Oakden-Rayner (FRANZCR\, PhD
) is the Director of Research in Medical Imaging at the Royal Adelaide Hos
pital and is a senior research fellow at the Australian Institute for Mach
ine Learning. Her research explores the safe translation of artificial int
elligence technologies into clinical practice\, both from a technical and
clinical perspective.
DTSTART;TZID=America/Los_Angeles:20220616T160000
DTEND;TZID=America/Los_Angeles:20220616T170000
LOCATION:Zoom: https://stanford.zoom.us/j/93524639045?pwd=NUV1MFE2clBCYVp3K
0FJNlJFTGswdz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Medical AI Safety – A Clinical Perspective
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-medical-ai-safety-a-clinical-perspective/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/06/lauren-oakden-rayner.jpg\;200\;200\,me
dium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/
uploads/2022/06/lauren-oakden-rayner.jpg\;200\;200\,large\;http://web.stan
ford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/06/laure
n-oakden-rayner.jpg\;200\;200\,full\;http://web.stanford.edu/group/radweb/
cgi-bin/radcalendar/wp-content/uploads/2022/06/lauren-oakden-rayner.jpg\;2
00\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
\nLauren Oakden-Rayner\, PhD
\nDirector of Research in Medical Imaging \nRoyal Adelaide Hospital\nSenior Research Fellow \nAustralian Institute for Machine Learn
ing
\n
Title: Medical AI Safety – A Clinical Perspec
tive
\n
Abstract: \nMedical artificial intelligence is ra
pidly moving into clinics\, particularly in imaging-based specialties such
as radiology. This transition is producing many new challenges\, as the r
egulatory environment has struggled to keep up and AI training for healthc
are workers is virtually non-existent. Dr. Oakden-Rayner will provide a cl
inical safety perspective on medical AI\, discuss a range of identified ri
sks and potential harms\, and discuss possible solutions to mitigate these
risks as this exciting field continues to develop.
\n
Bio:\nDr. Lauren Oakden-Rayner (FRANZCR\, PhD) is the Director of
Research in Medical Imaging at the Royal Adelaide Hospital and is a senio
r research fellow at the Australian Institute for Machine Learning. Her re
search explores the safe translation of artificial intelligence technologi
es into clinical practice\, both from a technical and clinical perspective
. \n
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3089@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:David Magnus\, PhD\nThomas A Raffin Professor of Medicine and B
iomedical Ethics and Professor of Pediatrics\, Medicine\, and by courtesy
of Bioengineering\nDirector\, Stanford Center for Biomedical Ethics\nAssoc
iate Dean for Research\nStanford University\nTitle: Ethical Challenges in
the Application of AI to Healthcare\nAbstract:\nThis presentation will foc
us on three issues. First\, applying AI to healthcare requires access to l
arge data sets. Data acquisition and data sharing raises a number of chall
enging ethical issues\, including challenges to traditional understandings
of informed consent\, and importance of diversity and inclusion in data s
ources. Second\, I will briefly discuss the widely discussed issues around
justice and equity raised by AI in healthcare. Finally\, I will discuss c
hallenges with ethical oversight and governance\, particularly in relation
to research development of AI. IRB’s are prohibited from considering down
stream social consequences and harms to individuals other than research pa
rticipants when evaluating the harms and risks of research. This gap needs
to be filled\, particularly as dual uses of AI models are now recognized
as a problem.\nBio: \nDavid Magnus\, PhD is Thomas A. Raffin Professor of
Medicine and Biomedical Ethics and Professor of Pediatrics and Medicine an
d by Courtesy of Bioengineering at Stanford University\, where he is Direc
tor of the Stanford Center for Biomedical Ethics and an Associate Dean of
Research. Magnus is member of the Ethics Committee for the Stanford Hospit
al. He is currently the Vice-Chair of the IRB for the NIH Precision Medici
ne Initiative (“All of Us”). He is the former President of the Association
of Bioethics Program Directors\, and is the Editor in Chief of the Americ
an Journal of Bioethics. He has published articles on a wide range of topi
cs in bioethics\, including research ethics\, genetics\, stem cell researc
h\, organ transplantation\, end of life\, and patient communication. He wa
s a member of the Secretary of Agriculture’s Advisory Committee on Biotech
nology in the 21st Century and currently serves on the California Human St
em Cell Research Advisory Committee. He is the principal editor of a colle
ction of essays entitled “Who Owns Life?” (2002) and his publications have
appeared in New England Journal of Medicine\, Science\, Nature Biotechnol
ogy\, and the British Medical Journal. He has appeared on many radio and t
elevision shows including 60 Minutes\, Good Morning America\, The Today Sh
ow\, CBS This Morning\, FOX news Sunday\, and ABC World News and NPR. In a
ddition to his scholarly work\, he has published Opinion pieces in the Phi
ladelphia Inquirer\, the Chicago Tribune\, the San Jose Mercury News\, and
the New Jersey Star Ledger.
DTSTART;TZID=America/Los_Angeles:20220921T133000
DTEND;TZID=America/Los_Angeles:20220921T143000
LOCATION:ZOOM: https://stanford.zoom.us/j/99191454207?pwd=N0ZYWnh1Mks0UEluO
VRUZjdWNHZPUT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Ethical Challenges in the Application of AI t
o Healthcare
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-ethical-challenges-in-the-application-of-ai-to-healthcare/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/09/david_magnus_ep_44_good.jpg\;200\;200\
,medium\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-conte
nt/uploads/2022/09/david_magnus_ep_44_good.jpg\;200\;200\,large\;http://we
b.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/09
/david_magnus_ep_44_good.jpg\;200\;200\,full\;http://web.stanford.edu/grou
p/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/09/david_magnus_ep_44
_good.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
David Magnus\, PhD \nThomas A Raffin Professor of Medicine and Biomedical Ethics and Profes
sor of Pediatrics\, Medicine\, and by courtesy of Bioengineering \nDi
rector\, Stanford Center for Biomedical Ethics \nAssociate Dean for R
esearch \nStanford University
\n
Title: Ethical Challenge
s in the Application of AI to Healthcare
\n
Abstract: \nT
his presentation will focus on three issues. First\, applying AI to health
care requires access to large data sets. Data acquisition and data sharing
raises a number of challenging ethical issues\, including challenges to t
raditional understandings of informed consent\, and importance of diversit
y and inclusion in data sources. Second\, I will briefly discuss the widel
y discussed issues around justice and equity raised by AI in healthcare. F
inally\, I will discuss challenges with ethical oversight and governance\,
particularly in relation to research development of AI. IRB’s are prohibi
ted from considering downstream social consequences and harms to individua
ls other than research participants when evaluating the harms and risks of
research. This gap needs to be filled\, particularly as dual uses of AI m
odels are now recognized as a problem.
\n
Bio: \nDavid Magnus\, PhD is Thomas A. Raffin Profe
ssor of Medicine and Biomedical Ethics and Professor of Pediatrics and Med
icine and by Courtesy of Bioengineering at Stanford University\, where he
is Director of the Stanford Center for Biomedical Ethics and an Associate
Dean of Research. Magnus is member of the Ethics Committee for the Stanfor
d Hospital. He is currently the Vice-Chair of the IRB for the NIH Precisio
n Medicine Initiative (“All of Us”). He is the former President of the Ass
ociation of Bioethics Program Directors\, and is the Editor in Chief of th
e American Journal of Bioethics. He has published articles on a wide range
of topics in bioethics\, including research ethics\, genetics\, stem cell
research\, organ transplantation\, end of life\, and patient communicatio
n. He was a member of the Secretary of Agriculture’s Advisory Committee on
Biotechnology in the 21st Century and currently serves on the California
Human Stem Cell Research Advisory Committee. He is the principal editor of
a collection of essays entitled “Who Owns Life?” (2002) and his publicati
ons have appeared in New England Journal of Medicine\, Science\, Nature Bi
otechnology\, and the British Medical Journal. He has appeared on many rad
io and television shows including 60 Minutes\, Good Morning America\, The
Today Show\, CBS This Morning\, FOX news Sunday\, and ABC World News and N
PR. In addition to his scholarly work\, he has published Opinion pieces in
the Philadelphia Inquirer\, the Chicago Tribune\, the San Jose Mercury Ne
ws\, and the New Jersey Star Ledger.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3093@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:Polina Golland\, PhD\nProfessor of Electrical Engineering and C
omputer Science\nPI in the Computer Science and Artificial Intelligence La
boratory\nMassachusetts Institute of Technology\nTitle: Learning to Read X
-Ray: Applications to Heart Failure Monitoring\nAbstract: We propose and d
emonstrate a novel approach to training image classification models based
on large collections of images with limited labels. We take advantage of a
vailability of radiology reports to construct joint multimodal embedding t
hat serves as a basis for classification. We demonstrate the advantages of
this approach in application to assessment of pulmonary edema severity in
congestive heart failure that motivated the development of the method.
DTSTART;TZID=America/Los_Angeles:20221019T120000
DTEND;TZID=America/Los_Angeles:20221019T130000
LOCATION:ZOOM: https://stanford.zoom.us/j/93555578704?pwd=eTdhRHM4K0w5WGVmS
ElSWGkzN3VqQT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Learning to Read X-Ray: Applications to Heart
Failure Monitoring
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-learning-to-read-x-ray-applications-to-heart-failure-monitoring
/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/09/Polina-Golland.jpg\;200\;200\,medium\;
http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upload
s/2022/09/Polina-Golland.jpg\;200\;200\,large\;http://web.stanford.edu/gro
up/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/09/Polina-Golland.jp
g\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalenda
r/wp-content/uploads/2022/09/Polina-Golland.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Polina Golland\, PhD \nProfessor of Electric
al Engineering and Computer Science \nPI in the Computer Science and
Artificial Intelligence Laboratory \nMassachusetts Institute of Techn
ology
\n
Title: Learning to Read X-Ray: Applications to Heart
Failure Monitoring
\n
Abstract: We propose and demonstrate a n
ovel approach to training image classification models based on large colle
ctions of images with limited labels. We take advantage of availability of
radiology reports to construct joint multimodal embedding that serves as
a basis for classification. We demonstrate the advantages of this approach
in application to assessment of pulmonary edema severity in congestive he
art failure that motivated the development of the method.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3100@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:Baris Turkbey\, MD\, FSAR\nSenior Clinician\nSection Chief of M
RI\nSection Chief of Artificial Intelligence\nMolecular Imaging Branch\nNa
tional Cancer Institute\, NIH\nTitle: Advanced Prostate Cancer Imaging\nTa
lk Objectives: \n\nTo discuss current status and limitations of localized
prostate cancer diagnosis.\nTo discuss use of artificial intelligence in d
iagnosis of localized prostate cancer.\nTo discuss use of molecular imagin
g in clinical prostate cancer management.\n\nBio:\nDr. Turkbey obtained hi
s medical degree from Hacettepe University in Ankara\, Turkey in 2003. He
completed his residency in Diagnostic and Interventional Radiology at Hace
ttepe University. He joined Molecular Imaging Branch (MIB)\, National Canc
er Institute\, NIH in 2007. His main research areas are imaging of prostat
e cancer (multiparametric MRI\, PET CT)\, image guided biopsy and treatmen
t techniques (focal therapy\, surgery and radiation therapy) for prostate
cancer and artificial intelligence. Dr. Turkbey is a member of Prostate Im
aging Reporting & Data System (PI-RADS) Steering Committee. He is the Dire
ctor Magnetic Resonance Imaging section in MIB and the Artificial Intellig
ence Resource in MIB.
DTSTART;TZID=America/Los_Angeles:20221116T120000
DTEND;TZID=America/Los_Angeles:20221116T130000
LOCATION:Zoom: https://stanford.zoom.us/j/99807942044?pwd=TmJkclNkbVBZOG04K
zJaSFRWVXlxZz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Advanced Prostate Cancer Imaging
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-advanced-prostate-cancer-imaging/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/11/Turkbey.jpg\;200\;200\,medium\;http://
web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/
11/Turkbey.jpg\;200\;200\,large\;http://web.stanford.edu/group/radweb/cgi-
bin/radcalendar/wp-content/uploads/2022/11/Turkbey.jpg\;200\;200\,full\;ht
tp://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/
2022/11/Turkbey.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Baris Turkbey\, MD\, FSAR \nSenior Clinician \nSection Chief
of MRI \nSection Chief of Artificial Intelligence \nMolecular I
maging Branch \nNational Cancer Institute\, NIH
\n
Title
: Advanced Prostate Cancer Imaging
\n
Talk Objectives:
b>
\n
\n
To discuss current status and limitations of localized p
rostate cancer diagnosis.
\n
To discuss use of artificial intellige
nce in diagnosis of localized prostate cancer.
\n
To discuss use of
molecular imaging in clinical prostate cancer management.
\n
\n
Bio: \nDr. Turkbey obtained his medical degree from
Hacettepe University in Ankara\, Turkey in 2003. He completed his residen
cy in Diagnostic and Interventional Radiology at Hacettepe University. He
joined Molecular Imaging Branch (MIB)\, National Cancer Institute\, NIH in
2007. His main research areas are imaging of prostate cancer (multiparame
tric MRI\, PET CT)\, image guided biopsy and treatment techniques (focal t
herapy\, surgery and radiation therapy) for prostate cancer and artificial
intelligence. Dr. Turkbey is a member of Prostate Imaging Reporting & Dat
a System (PI-RADS) Steering Committee. He is the Director Magnetic Resonan
ce Imaging section in MIB and the Artificial Intelligence Resource in MIB.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3106@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2022seminars.html
DESCRIPTION:In Person at the Clark Center S360 – Lunch will be provided!\nZ
oom: https://stanford.zoom.us/j/99496515255?pwd=MHlXbXM2WXJULzZwemk1WjJHNF
ZOdz09\n\nAnthony Gatti\, PhD\nPostdoctoral Research Fellow\nDepartment of
Radiology\nWu Tsai Human Performance Alliance\nStanford University\n\n\n
\nTitle: Towards Understanding Knee Health Using Automated MRI-Based Stati
stical Shape Models\n\n\n\n\n\n\n\n\n\nAbstract: Knee injuries and pain ar
e prevalent across all ages\, with varying causes from “anterior knee pain
” in runners to osteoarthritis-related pain. Osteoarthritis pain is a part
icular problem because structural outcomes assessed on medical images ofte
n disagree with symptoms. Most studies trying to understand knee health an
d pain use simple biomarkers such as mean cartilage thickness. My talk wil
l present an automated pipeline for quantifying the whole knee using stati
stical shape modeling. I will present a conventional statistical shape mod
el as well as a novel approach that uses generative neural implicit repres
entations. Both modeling approaches allow unsupervised identification of s
alient anatomic features. I will demonstrate how these features can be use
d to predict existing radiographic outcomes\, patient demographics\, and k
nee pain.\n\n\n\n\nLiangqiong Qu\, PhD\nPostdoctoral Research Fellow\nDepa
rtment of Biomedical Data Sciences\nStanford University\nTitle: Distribute
d Deep Learning in Medical Imaging\n\n\n\n\n\n\n\n\n\nAbstract: Distribute
d deep learning is an emerging research paradigm for enabling collaborativ
ely training deep learning models without sharing patient data.\nIn this t
alk\, we will first investigate the use distributed deep learning to build
medical imaging classification models in a real-world collaborative setti
ng.\nWe then present several strategies to tackle the data heterogeneity c
hallenge and the lack of quality labeled data challenge in distributed dee
p learning.
DTSTART;TZID=America/Los_Angeles:20221214T130000
DTEND;TZID=America/Los_Angeles:20221214T140000
LOCATION:Clark Center S360 @ 318 Campus Drive\, Stanford\, CA
SEQUENCE:0
SUMMARY:IBIIS & AIMI Hybrid Seminar: Anthony Gatti\, PhD & Liangqiong Qu\,
PhD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-hybrid-seminar-anthony-gatti-phd-liangqiong-qu-phd/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2022/12/Anthony-Gatti.jpg\;200\;200\,medium\;h
ttp://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads
/2022/12/Anthony-Gatti.jpg\;200\;200\,large\;http://web.stanford.edu/group
/radweb/cgi-bin/radcalendar/wp-content/uploads/2022/12/Anthony-Gatti.jpg\;
200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/w
p-content/uploads/2022/12/Anthony-Gatti.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
In Pe
rson at the Clark Center S360 – Lunch will be provided! \nZoom: https://stanford.zoom.us/j/99496515255?pwd=MHlXbXM2WX
JULzZwemk1WjJHNFZOdz09
\n\n
Anthony Gatt
i\, PhD \nPostdoctoral Research Fellow \nDepartment of Radio
logy \nWu Tsai Human Performance Alliance \nStanford University<
/p>\n
\n
\n
\n
Title: Towar
ds Understanding Knee Health Using Automated MRI-Based Statistical Shape M
odels
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Abstract: Knee
injuries and pain are prevalent across all ages\, with varying causes fro
m “anterior knee pain” in runners to osteoarthritis-related pain. Osteoart
hritis pain is a particular problem because structural outcomes assessed o
n medical images often disagree with symptoms. Most studies trying to unde
rstand knee health and pain use simple biomarkers such as mean cartilage t
hickness. My talk will present an automated pipeline for quantifying the w
hole knee using statistical shape modeling. I will present a conventional
statistical shape model as well as a novel approach that uses generative n
eural implicit representations. Both modeling approaches allow unsupervise
d identification of salient anatomic features. I will demonstrate how thes
e features can be used to predict existing radiographic outcomes\, patient
demographics\, and knee pain.
\n\n<
div class='text-image section'>\n
\n
\n
Liangqiong Qu\, PhD \nPostdoctoral Research Fellow \nDepartment of Biomedical Data
Sciences \nStanford University
\n
Title: Distributed Dee
p Learning in Medical Imaging
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Abstract: Distributed deep learning is an emerging res
earch paradigm for enabling collaboratively training deep learning models
without sharing patient data. \nIn this talk\, we will first investig
ate the use distributed deep learning to build medical imaging classificat
ion models in a real-world collaborative setting. \nWe then present s
everal strategies to tackle the data heterogeneity challenge and the lack
of quality labeled data challenge in distributed deep learning.
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3114@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 4088131312\; ramzitotah@gmail.com\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Archana Venkataraman\, PhD\nAssociate Professor of Electrical a
nd Computer Engineering\nBoston University\nTitle: Biologically Inspired D
eep Learning as a New Window into Brain Dysfunction\nAbstract: Deep learni
ng has disrupted nearly every major field of study from computer vision to
genomics. The unparalleled success of these models has\, in many cases\,
been fueled by an explosion of data. Millions of labeled images\, thousand
s of annotated ICU admissions\, and hundreds of hours of transcribed speec
h are common standards in the literature. Clinical neuroscience is a notab
le holdout to this trend. It is a field of unavoidably small datasets\, ma
ssive patient variability\, and complex (largely unknown) phenomena. My la
b tackles these challenges across a spectrum of projects\, from answering
foundational neuroscientific questions to translational applications of ne
uroimaging data to exploratory directions for probing neural circuitry. On
e of our key strategies is to integrate a priori information about the bra
in and biology into the model design.\nThis talk will highlight two ongoin
g projects that epitomize this strategy. First\, I will showcase an end-to
-end deep learning framework that fuses neuroimaging\, genetic\, and pheno
typic data\, while maintaining interpretability of the extracted biomarker
s. We use a learnable dropout layer to extract a sparse subset of predicti
ve imaging features and a biologically informed deep network architecture
for whole-genome analysis. Specifically\, the network uses hierarchical gr
aph convolution that mimic the organization of a well-established gene ont
ology to track the convergence of genetic risk across biological pathways.
Second\, I will present a deep-generative hybrid model for epileptic seiz
ure detection from scalp EEG. The latent variables in this model capture t
he spatiotemporal spread of a seizure\; they are complemented by a nonpara
metric likelihood based on convolutional neural networks. I will also high
light our current end-to-end extensions of this work focused on seizure on
set localization. Finally\, I will conclude with exciting future direction
s for our work across the foundational\, translational\, and exploratory a
xes.
DTSTART;TZID=America/Los_Angeles:20230118T120000
DTEND;TZID=America/Los_Angeles:20230118T130000
LOCATION:Zoom: https://stanford.zoom.us/j/96155849129?pwd=MTVtenF6RWdHMEwwd
EZoV3NhM0svUT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Zoom Seminar: Biologically Inspired Deep Learning as a
New Window into Brain Dysfunction
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-biologically-inspired-deep-learning-as-a-new-window-into-brain-
dysfunction/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/01/Picture1-298x300.jpg\;298\;300\,medium
\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uplo
ads/2023/01/Picture1-298x300.jpg\;298\;300\,large\;http://web.stanford.edu
/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2023/01/Picture1-298x
300.jpg\;298\;300\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radc
alendar/wp-content/uploads/2023/01/Picture1-298x300.jpg\;298\;300
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Archana
Venkataraman\, PhD \nAssociate Professor of Electrical and Compu
ter Engineering \nBoston University
\n
Title: Biologicall
y Inspired Deep Learning as a New Window into Brain Dysfunction
\n
Abstract: Deep learning has disrupted nearly every major fi
eld of study from computer vision to genomics. The unparalleled success of
these models has\, in many cases\, been fueled by an explosion of data. M
illions of labeled images\, thousands of annotated ICU admissions\, and hu
ndreds of hours of transcribed speech are common standards in the literatu
re. Clinical neuroscience is a notable holdout to this trend. It is a fiel
d of unavoidably small datasets\, massive patient variability\, and comple
x (largely unknown) phenomena. My lab tackles these challenges across a sp
ectrum of projects\, from answering foundational neuroscientific questions
to translational applications of neuroimaging data to exploratory directi
ons for probing neural circuitry. One of our key strategies is to integrat
e a priori information about the brain and biology into the model d
esign.
\n
This talk will highlight two ongoing projects that epitomiz
e this strategy. First\, I will showcase an end-to-end deep learning frame
work that fuses neuroimaging\, genetic\, and phenotypic data\, while maint
aining interpretability of the extracted biomarkers. We use a learnable dr
opout layer to extract a sparse subset of predictive imaging features and
a biologically informed deep network architecture for whole-genome analysi
s. Specifically\, the network uses hierarchical graph convolution that mim
ic the organization of a well-established gene ontology to track the conve
rgence of genetic risk across biological pathways. Second\, I will present
a deep-generative hybrid model for epileptic seizure detection from scalp
EEG. The latent variables in this model capture the spatiotemporal spread
of a seizure\; they are complemented by a nonparametric likelihood based
on convolutional neural networks. I will also highlight our current end-to
-end extensions of this work focused on seizure onset localization. Finall
y\, I will conclude with exciting future directions for our work across th
e foundational\, translational\, and exploratory axes.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3120@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Andrew Janowczyk\, PhD\nAssistant Professor\nDepartment of Biom
edical Engineering\nEmory University\nTitle: Computational Pathology: Towa
rds Precision Medicine\nAbstract:\nRoughly 40% of the population will be d
iagnosed with some form of cancer in their lifetime. In a large majority o
f these cases\, a definitive cancer diagnosis is only possible via histopa
thologic confirmation on a tissue slide. With the increasing popularity of
the digitization of pathology slides\, a wealth of new untapped data is n
ow regularly being created.\nComputational analysis of these routinely cap
tured H&E slides is facilitating the creation of diagnostic tools for task
s such as disease identification and grading. Further\, by identifying pat
terns of disease presentation across large cohorts of retrospectively anal
yzed patients\, new insights for predicting prognosis and therapy response
are possible [1\,2]. Such biomarkers\, derived from inexpensive histology
slides\, stand to improve the standard of care for all patient population
s\, especially where expensive genomic testing may not be readily availabl
e. Moreover\, since numerous other diseases and disorders\, such as oncomi
ng clinical heart failure [3]\, are similarly diagnosed via pathology slid
es\, those patients also stand to benefit from these same technological ad
vances in the digital pathology space.\nThis talk will discuss our researc
h aimed towards reaching the goal of precision medicine\, wherein patients
receive optimized treatment based on historical evidence. The talk discus
ses how the applications of deep learning in this domain are significantly
improving the efficiency and robustness of these models [4]. Numerous cha
llenges remain\, though\, especially in the context of quality control and
annotation gathering. This talk further introduces the audience to open-s
ource tools being developed and deployed to meet these pressing needs\, in
cluding quality control (histoqc.com [5])\, annotation (quickannotator.com
)\, labeling (patchsorter.com)\, validation (cohortfinder.com).
DTSTART;TZID=America/Los_Angeles:20230215T093000
DTEND;TZID=America/Los_Angeles:20230215T103000
LOCATION:Zoom: https://stanford.zoom.us/j/91585038349?pwd=L1ZuRkZibG1iSmdtR
0RtakhVdi9HZz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Computational Pathology – Towards Precision M
edicine
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-computational-pathology-towards-precision-medicine/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/02/janowczyk-andrew.jpg\;200\;200\,medium
\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uplo
ads/2023/02/janowczyk-andrew.jpg\;200\;200\,large\;http://web.stanford.edu
/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2023/02/janowczyk-and
rew.jpg\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radc
alendar/wp-content/uploads/2023/02/janowczyk-andrew.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Andrew Janowczyk\, PhD \nAssistant Pro
fessor \nDepartment of Biomedical Engineering \nEmory University
\n
Title: Computational Pathology: Towards Precision Medicine
\n
Abstract: \nRoughly 40% of the population will be dia
gnosed with some form of cancer in their lifetime. In a large majority of
these cases\, a definitive cancer diagnosis is only possible via histopath
ologic confirmation on a tissue slide. With the increasing popularity of t
he digitization of pathology slides\, a wealth of new untapped data is now
regularly being created.
\n
Computational analysis of these routinel
y captured H&E slides is facilitating the creation of diagnostic tools for
tasks such as disease identification and grading. Further\, by identifyin
g patterns of disease presentation across large cohorts of retrospectively
analyzed patients\, new insights for predicting prognosis and therapy res
ponse are possible [1\,2]. Such biomarkers\, derived from inexpensive hist
ology slides\, stand to improve the standard of care for all patient popul
ations\, especially where expensive genomic testing may not be readily ava
ilable. Moreover\, since numerous other diseases and disorders\, such as o
ncoming clinical heart failure [3]\, are similarly diagnosed via pathology
slides\, those patients also stand to benefit from these same technologic
al advances in the digital pathology space.
\n
This talk will discuss
our research aimed towards reaching the goal of precision medicine\, wher
ein patients receive optimized treatment based on historical evidence. The
talk discusses how the applications of deep learning in this domain are s
ignificantly improving the efficiency and robustness of these models [4].
Numerous challenges remain\, though\, especially in the context of quality
control and annotation gathering. This talk further introduces the audien
ce to open-source tools being developed and deployed to meet these pressin
g needs\, including quality control (histoqc.com [5])\, annotation (quicka
nnotator.com)\, labeling (patchsorter.com)\, validation (cohortfinder.com)
.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3128@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Melissa McCradden\, PhD\nJohn and Melinda Thompson Director of
Artificial Intelligence in Medicine\nIntegration Lead\, AI in Medicine Ini
tiative\nBioethicist\, The Hospital for Sick Children (SickKids)\nAssociat
e Scientist\, Genetics & Genome Biology\nAssistant Professor\, Dalla Lana
School of Public Health\nTitle: What Makes a ‘Good’ Decision? An Empirical
Bioethics Study of Using AI at the Bedside\nAbstract: This presentation w
ill identify the gap between AI accuracy and making good clinical decision
s. I will present a study where we develop an ethical framework for clinic
al decision-making that can help clinicians meet medicolegal and ethical s
tandards when using AI that does not rely on explainability\, nor perfect
accuracy of the model.
DTSTART;TZID=America/Los_Angeles:20230315T120000
DTEND;TZID=America/Los_Angeles:20230315T130000
LOCATION:https://stanford.zoom.us/j/96612401401?pwd=WFNJb2Q4dStoVDE5a25BYTB
kMjN4QT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: What Makes a ‘Good’ Decision? An Empirical Bi
oethics Study of Using AI at the Bedside
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-what-makes-a-good-decision-an-empirical-bioethics-study-of-usin
g-ai-at-the-bedside/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/03/Screen-Shot-2023-03-06-at-10.12.28-AM-
247x300.png\;247\;300\,medium\;http://web.stanford.edu/group/radweb/cgi-bi
n/radcalendar/wp-content/uploads/2023/03/Screen-Shot-2023-03-06-at-10.12.2
8-AM-247x300.png\;247\;300\,large\;http://web.stanford.edu/group/radweb/cg
i-bin/radcalendar/wp-content/uploads/2023/03/Screen-Shot-2023-03-06-at-10.
12.28-AM-247x300.png\;247\;300\,full\;http://web.stanford.edu/group/radweb
/cgi-bin/radcalendar/wp-content/uploads/2023/03/Screen-Shot-2023-03-06-at-
10.12.28-AM-247x300.png\;247\;300
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
\n
Melissa McCradden\, PhD \nJohn and Melinda Thompson Director of Artificial Intelligence in Medic
ine \nIntegration Lead\, AI in Medicine Initiative \nBioethicist
\, The Hospital for Sick Children (SickKids) \nAssociate Scientist\,
Genetics & Genome Biology \nAssistant Professor\, Dalla Lana School o
f Public Health
\n
Title: What Makes a ‘Good’ Decision? An Emp
irical Bioethics Study of Using AI at the Bedside
\n
Abstract:
This presentation will identify the gap between AI accuracy and making go
od clinical decisions. I will present a study where we develop an ethical
framework for clinical decision-making that can help clinicians meet medic
olegal and ethical standards when using AI that does not rely on explainab
ility\, nor perfect accuracy of the model.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3134@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Marzyeh Ghassemi\, PhD\nAssistant Professor\, Department of Ele
ctrical Engineering and Computer Science\nInstitute for Medical Engineerin
g & Science\nMassachusetts Institute of Technology (MIT)\nCanadian CIFAR A
I Chair at Vector Institute\nTitle: Designing Machine Learning Processes F
or Equitable Health Systems\nAbstract\nDr. Marzyeh Ghassemi focuses on cre
ating and applying machine learning to understand and improve health in wa
ys that are robust\, private and fair. Dr. Ghassemi will talk about her wo
rk trying to train models that do not learn biased rules or recommendation
s that harm minorities or minoritized populations. The Healthy ML group ta
ckles the many novel technical opportunities for machine learning in healt
h\, and works to make important progress with careful application to this
domain.
DTSTART;TZID=America/Los_Angeles:20230419T120000
DTEND;TZID=America/Los_Angeles:20230419T130000
LOCATION:ZOOM: https://stanford.zoom.us/j/97119304595?pwd=clBRVW45NXdWZE9ZU
k8ySzQ0OEtYQT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Hybrid Seminar: Designing Machine Learning Processes F
or Equitable Health Systems
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-hybrid-seminar-designing-machine-learning-processes-for-equitable-healt
h-systems/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/03/marzyeh-768x768.jpg\;200\;200\,medium\
;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploa
ds/2023/03/marzyeh-768x768.jpg\;200\;200\,large\;http://web.stanford.edu/g
roup/radweb/cgi-bin/radcalendar/wp-content/uploads/2023/03/marzyeh-768x768
.jpg\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcale
ndar/wp-content/uploads/2023/03/marzyeh-768x768.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Marzyeh Ghassemi\, PhD \nAssistant Profes
sor\, Department of Electrical Engineering and Computer Science \nIns
titute for Medical Engineering & Science \nMassachusetts Institute of
Technology (MIT) \nCanadian CIFAR AI Chair at Vector Institute
\n
Title: Designing Machine Learning Processes For Equitable Health
Systems
\n
Abstract \nDr. Marzyeh Ghassemi fo
cuses on creating and applying machine learning to understand and improve
health in ways that are robust\, private and fair. Dr. Ghassemi will talk
about her work trying to train models that do not learn biased rules or re
commendations that harm minorities or minoritized populations. The Healthy
ML group tackles the many novel technical opportunities for machine learn
ing in health\, and works to make important progress with careful applicat
ion to this domain.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3138@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Hoifung Poon\nHoifung Poon\, PhD\nGeneral Manager at Health Fut
ures of Microsoft Research\nAffiliated Professor at the University of Wash
ington Medical School.\nTitle: Advancing Health at the Speed of AI\n\n\n\n
\n\n\n\n\n\nAbstract: The dream of precision health is to develop a data-d
riven\, continuous learning system where new health information is instant
ly incorporated to optimize care delivery and accelerate biomedical discov
ery. In reality\, however\, the health ecosystem is plagued by overwhelmin
g unstructured data and unscalable manual processing. Self-supervised AI s
uch as large language models (LLMs) can supercharge structuring of biomedi
cal data and accelerate transformation towards precision health. In this t
alk\, I’ll present our research progress on biomedical AI for precision he
alth\, spanning biomedical LLMs\, multi-modal learning\, and causal discov
ery. This enables us to extract knowledge from tens of millions of publica
tions\, structure real-world data for millions of cancer patients\, and ap
ply the extracted knowledge and real-world evidence to advancing precision
oncology in deep partnerships with real-world stakeholders.
DTSTART;TZID=America/Los_Angeles:20230426T143000
DTEND;TZID=America/Los_Angeles:20230426T153000
LOCATION:LKSC 120 and remote via Zoom @ https://stanford.zoom.us/j/92666973
395?pwd=SHpzVmVPMEFYRXQ5Skp5eG1vcXBrdz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Advancing Health at the Speed of AI
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-advancing-health-at-the-speed-of-ai/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/04/Hoifung-Poon-PhD.jpg\;200\;198\,medium
\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uplo
ads/2023/04/Hoifung-Poon-PhD.jpg\;200\;198\,large\;http://web.stanford.edu
/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2023/04/Hoifung-Poon-
PhD.jpg\;200\;198\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radc
alendar/wp-content/uploads/2023/04/Hoifung-Poon-PhD.jpg\;200\;198
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n
\n
\n
\n\n
Hoifung Poon\, PhD
\nGeneral Manager at Health Futures of Microsoft Research
\nAffiliated Professor at the University of Washington Medical School.
\n
Title: Advancing Health at the Speed of AI
\n
\n
\n
\n
\n
\n
\n<
div class='panel panel-default'>\n
\n
\n
Abstract: The dream of precision
health is to develop a data-driven\, continuous learning system where new
health information is instantly incorporated to optimize care delivery an
d accelerate biomedical discovery. In reality\, however\, the health ecosy
stem is plagued by overwhelming unstructured data and unscalable manual pr
ocessing. Self-supervised AI such as large language models (LLMs) can supe
rcharge structuring of biomedical data and accelerate transformation towar
ds precision health. In this talk\, I’ll present our research progress on
biomedical AI for precision health\, spanning biomedical LLMs\, multi-moda
l learning\, and causal discovery. This enables us to extract knowledge fr
om tens of millions of publications\, structure real-world data for millio
ns of cancer patients\, and apply the extracted knowledge and real-world e
vidence to advancing precision oncology in deep partnerships with real-wor
ld stakeholders.
\n
\n
\n
\n
\n
\n\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3144@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Despina Kontos\, PhD\nMatthew J. Wilson Professor of Research R
adiology II\nAssociate Vice-Chair for Research\, Department of Radiology\n
Perelman School of Medicine\nUniversity of Pennsylvania\nTitle: Radiomics
and Radiogenomics: The Role of Imaging\, Machine Learning\, and AI\, as a
Biomarker for Cancer Prognostication and Therapy Response Evaluation\nAbst
ract: Cancer is a heterogeneous disease\, with known inter-tumor and intra
-tumor heterogeneity in solid tumors. Established histopathologic prognost
ic biomarkers generally acquired from a tumor biopsy may be limited by sam
pling variation. Radiomics is an emerging field with the potential to leve
rage the whole tumor via non-invasive sampling afforded by medical imaging
to extract high throughput\, quantitative features for personalized tumor
characterization. Identifying imaging phenotypes via radiomics analysis a
nd understanding their relationship with prognostic markers and patient ou
tcomes can allow for a non-invasive assessment of tumor heterogeneity. Rec
ent studies have shown that intrinsic radiomic phenotypes of tumor heterog
eneity for cancer may have independent prognostic value when predicting di
sease aggressiveness and recurrence. The independent prognostic value of i
maging heterogeneity phenotypes suggests that radiogenomic phenotypes can
provide a non-invasive characterization of tumor heterogeneity to augment
genomic assays in precision prognosis and treatment.
DTSTART;TZID=America/Los_Angeles:20230517T120000
DTEND;TZID=America/Los_Angeles:20230517T130000
LOCATION:Clark Center S360 - Zoom Details on IBIIS website @ 318 Campus Dri
ve
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Radiomics and Radiogenomics: The Role of Imag
ing\, Machine Learning\, and AI\, as a Biomarker for Cancer Prognosticatio
n and Therapy Response Evaluation
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-radiomics-and-radiogenomics-the-role-of-imaging-machine-learnin
g-and-ai-as-a-biomarker-for-cancer-prognostication-and-therapy-response-ev
aluation/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/05/kont4311.jpg\;200\;200\,medium\;http:/
/web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2023
/05/kont4311.jpg\;200\;200\,large\;http://web.stanford.edu/group/radweb/cg
i-bin/radcalendar/wp-content/uploads/2023/05/kont4311.jpg\;200\;200\,full\
;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/uploa
ds/2023/05/kont4311.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Despina Kontos\, PhD \nMatthew J. Wilson Professor of Research
Radiology II \nAssociate Vice-Chair for Research\, Department of Rad
iology \nPerelman School of Medicine \nUniversity of Pennsylvani
a
\n
Title: Radiomics and Radiogenomics: The Role of Imaging\,
Machine Learning\, and AI\, as a Biomarker for Cancer Prognostication and
Therapy Response Evaluation
\n
Abstract: Cancer is a heteroge
neous disease\, with known inter-tumor and intra-tumor heterogeneity in so
lid tumors. Established histopathologic prognostic biomarkers generally ac
quired from a tumor biopsy may be limited by sampling variation. Radiomics
is an emerging field with the potential to leverage the whole tumor via n
on-invasive sampling afforded by medical imaging to extract high throughpu
t\, quantitative features for personalized tumor characterization. Identif
ying imaging phenotypes via radiomics analysis and understanding their rel
ationship with prognostic markers and patient outcomes can allow for a non
-invasive assessment of tumor heterogeneity. Recent studies have shown tha
t intrinsic radiomic phenotypes of tumor heterogeneity for cancer may have
independent prognostic value when predicting disease aggressiveness and r
ecurrence. The independent prognostic value of imaging heterogeneity pheno
types suggests that radiogenomic phenotypes can provide a non-invasive cha
racterization of tumor heterogeneity to augment genomic assays in precisio
n prognosis and treatment.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3150@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Daguang Xu\, PhD\nSenior Research Manager\nNVIDIA Healthcare\nT
itle: Industrial Applied Research in Healthcare and Federated Learning at
NVIDIA\nAbstract: As the market leader in deep learning and parallel compu
ting\, NVIDIA is fully committed to advancing applied research in medical
imaging. Our goal is to revolutionize the capabilities of medical doctors
and radiologists by equipping them with powerful tools and applications ba
sed on deep learning. We firmly believe that the integration of deep learn
ing and accelerated AI will have a profound impact on the life sciences\,
medicine\, and the healthcare industry as a whole. To drive this transform
ative process\, NVIDIA is actively democratizing deep learning through the
provision of a comprehensive AI computing platform specifically designed
for the healthcare community. These GPU-accelerated solutions not only pro
mote collaboration but also prioritize the security of each institution’s
information. By doing so\, we are fostering a collective effort in harness
ing the potential of deep learning to benefit healthcare.\nDuring this tal
k\, I will showcase remarkable research achievements accomplished by NVIDI
A’s deep learning in medical imaging team. This includes breakthroughs in
segmentation\, self-supervised learning\, federated learning\, and other r
elated areas. Additionally\, I will provide insights into the exciting ave
nues of research that our team is currently exploring.
DTSTART;TZID=America/Los_Angeles:20230621T120000
DTEND;TZID=America/Los_Angeles:20230621T130000
LOCATION:ZOOM: https://stanford.zoom.us/j/92801875181?pwd=TzAyOXd2UDJwYjJkc
2xQZ1doaXA3QT09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Industrial Applied Research in Healthcare and
Federated Learning at NVIDIA
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-industrial-applied-research-in-healthcare-and-federated-learnin
g-at-nvidia/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/06/DaguangXu-225x300.jpg\;225\;300\,mediu
m\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upl
oads/2023/06/DaguangXu-225x300.jpg\;225\;300\,large\;http://web.stanford.e
du/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2023/06/DaguangXu-2
25x300.jpg\;225\;300\,full\;http://web.stanford.edu/group/radweb/cgi-bin/r
adcalendar/wp-content/uploads/2023/06/DaguangXu-225x300.jpg\;225\;300
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Daguang
Xu\, PhD \nSenior Research Manager \nNVIDIA Healthcare
\n
Title: Industrial Applied Research in Healthcare and Federated
Learning at NVIDIA
\n
Abstract: As the market leader in deep
learning and parallel computing\, NVIDIA is fully committed to advancing a
pplied research in medical imaging. Our goal is to revolutionize the capab
ilities of medical doctors and radiologists by equipping them with powerfu
l tools and applications based on deep learning. We firmly believe that th
e integration of deep learning and accelerated AI will have a profound imp
act on the life sciences\, medicine\, and the healthcare industry as a who
le. To drive this transformative process\, NVIDIA is actively democratizin
g deep learning through the provision of a comprehensive AI computing plat
form specifically designed for the healthcare community. These GPU-acceler
ated solutions not only promote collaboration but also prioritize the secu
rity of each institution’s information. By doing so\, we are fostering a c
ollective effort in harnessing the potential of deep learning to benefit h
ealthcare.
\n
During this talk\, I will showcase remarkable research
achievements accomplished by NVIDIA’s deep learning in medical imaging tea
m. This includes breakthroughs in segmentation\, self-supervised learning\
, federated learning\, and other related areas. Additionally\, I will prov
ide insights into the exciting avenues of research that our team is curren
tly exploring.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3156@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Negar Golestani\, PhD\nPostdoctoral Research Fellow\nDepartment
of Radiology\nStanford University\n\nTitle: AI in Radiology-Pathology Fus
ion Towards Precise Breast Cancer Detection\nAbstract: Breast cancer is a
global public health concern with various treatment options based on tumor
characteristics. Pathological examination of excised tissue after surgery
provides important information for treatment decisions. This pathology pr
ocessing involving the manual selection of representative sections for his
tological examination is time-consuming and subjective\, which can lead to
potential sampling errors. Accurately identifying residual tumors is a ch
allenging task\, which highlights the need for systematic or assisted meth
ods. Radiology-pathology registration is essential for developing deep-lea
rning algorithms to automate cancer detection on radiology images. However
\, aligning faxitron and histopathology images is difficult due to content
and resolution differences\, tissue deformation\, artifacts\, and impreci
se correspondence. We propose a novel deep learning-based pipeline for aff
ine registration of faxitron images (x-ray representations of macrosection
s of ex-vivo breast tissue) with their corresponding histopathology images
. Our model combines convolutional neural networks (CNN) and vision transf
ormers (ViT)\, capturing local and global information from the entire tiss
ue macrosection and its segments. This integrated approach enables simulta
neous registration and stitching of image segments\, facilitating segment-
to-macrosection registration through a puzzling-based mechanism. To overco
me the limitations of multi-modal ground truth data\, we train the model u
sing synthetic mono-modal data in a weakly supervised manner. The trained
model successfully performs multi-modal registration\, outperforms existin
g baselines\, including deep learning-based and iterative models\, and is
approximately 200 times faster than the iterative approach. The applicatio
n of proposed registration method allows for the precise mapping of pathol
ogy labels onto radiology images\, thereby establishing ground truth label
s for training classification and detection models on radiological data. T
his work bridges the gap in current research and clinical workflow\, offer
ing potential improvements in efficiency and accuracy for breast cancer ev
aluation and streamlining pathology workflow.\n \nJean Benoit Delbrouck\,
PhD\nResearch Scientist\nDepartment of Radiology\nStanford University\n\nT
itle: Generating Accurate and Factually Correct Medical Text\nAbstract: Ge
nerating factually correct medical text is of utmost importance due to sev
eral reasons. Firstly\, patient safety is heavily dependent on accurate in
formation as medical decisions are often made based on the information pro
vided. Secondly\, trust in AI as a reliable tool in the medical field is e
ssential\, and this trust can only be established by generating accurate a
nd reliable medical text. Lastly\, medical research also relies heavily on
accurate information for meaningful results.\nRecent studies have explore
d new approaches for generating medical text from images or findings\, ran
ging from pretraining to Reinforcement Learning\, and leveraging expert an
notations. However\, a potential game changer in the field is the integrat
ion of GPT models in pipelines for generating factually correct medical te
xt for research or production purposes.
DTSTART;TZID=America/Los_Angeles:20230927T140000
DTEND;TZID=America/Los_Angeles:20230927T150000
LOCATION:Li Ka Shing\, LK120 - Zoom Details on IBIIS website
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Negar Golestani\, PhD & Jean Benoit Delbrouck
\, PhD
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-negar-golestani-phd-jean-benoit-delbrouck-phd/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/09/NegarGolestani.png\;200\;200\,medium\;
http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upload
s/2023/09/NegarGolestani.png\;200\;200\,large\;http://web.stanford.edu/gro
up/radweb/cgi-bin/radcalendar/wp-content/uploads/2023/09/NegarGolestani.pn
g\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalenda
r/wp-content/uploads/2023/09/NegarGolestani.png\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Negar Golestani\, PhD
\nPostdoctoral Research Fellow \nDepartment of Radiolo
gy \nStanford University \n
\n
Title: AI in Radiology-Pathology F
usion Towards Precise Breast Cancer Detection
\n
Abstract: Breast cancer is a glob
al public health concern with various treatment options based on tumor cha
racteristics. Pathological examination of excised tissue after surgery pro
vides important information for treatment decisions. This pathology proces
sing involving the manual selection of representative sections for histolo
gical examination is time-consuming and subjective\, which can lead to pot
ential sampling errors. Accurately identifying residual tumors is a challe
nging task\, which highlights the need for systematic or assisted methods.
Radiology-pathology registration is essential for developing deep-learnin
g algorithms to automate cancer detection on radiology images. However\, a
ligning faxitron and histopathology images is difficult due to content and
resolution differences\, tissue deformation\, artifacts\, and imprecise c
orrespondence. We propose a novel deep learning-based pipeline for affine
registration of faxitron images (x-ray representations of macrosections of
ex-vivo breast tissue) with their corresponding histopathology images. Ou
r model combines convolutional neural networks (CNN) and vision transforme
rs (ViT)\, capturing local and global information from the entire tissue m
acrosection and its segments. This integrated approach enables simultaneou
s registration and stitching of image segments\, facilitating segment-to-m
acrosection registration through a puzzling-based mechanism. To overcome t
he limitations of multi-modal ground truth data\, we train the model using
synthetic mono-modal data in a weakly supervised manner. The trained mode
l successfully performs multi-modal registration\, outperforms existing ba
selines\, including deep learning-based and iterative models\, and is appr
oximately 200 times faster than the iterative approach. The application of
proposed registration method allows for the precise mapping of pathology
labels onto radiology images\, thereby establishing ground truth labels fo
r training classification and detection models on radiological data. This
work bridges the gap in current research and clinical workflow\, offering
potential improvements in efficiency and accuracy for breast cancer evalua
tion and streamlining pathology workflow.
\n
\n
Jean Benoit Delbrouck\, PhD \nResearch Scientist \n
Department of Radiology \nStanford University \n<
/strong>
\n
Title: Genera
ting Accurate and Factually Correct Medical Text \nAbstract:<
/strong> Generating factually correct medical text is of utmost importance
due to several reasons. Firstly\, patient safety is heavily dependent on
accurate information as medical decisions are often made based on the info
rmation provided. Secondly\, trust in AI as a reliable tool in the medical
field is essential\, and this trust can only be established by generating
accurate and reliable medical text. Lastly\, medical research also relies
heavily on accurate information for meaningful results.
\n
Recent studies have explored new approaches for generati
ng medical text from images or findings\, ranging from pretraining to Rein
forcement Learning\, and leveraging expert annotations. However\, a potent
ial game changer in the field is the integration of GPT models in pipeline
s for generating factually correct medical text for research or production
purposes.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3166@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 16507214161\; rtotah@stanford.edu\; https://ibiis.sta
nford.edu/events/seminars/2023seminars.html
DESCRIPTION:Bram van Ginneken\, PhD\nProfessor of Medical Image Analysis\nC
hair of the Diagnostic Image Analysis Group\nRadboud University Medical Ce
nter\nTitle: Why AI Should Replace Radiologists\nAbstract:\nIn this talk\,
I will provide arguments for the thesis that nearly all diagnostic radiol
ogy could be performed by computers and that the notion that AI will not r
eplace radiologists is only temporarily true. Some well-known and lesser-k
nown examples of AI systems analyzing medical images with a stand-alone pe
rformance on par or beyond human experts will be presented. I will show th
at systems built by academia\, in collaborative efforts\, may even outperf
orm commercially available systems. Next\, I will sketch a way forward to
implement automated diagnostic radiology and argue that this is needed to
keep healthcare affordable in societies wrestling with aging populations.
Some pitfalls\, like excessive demands for trials\, will be discussed. Th
e key to success is to convince radiologists to take the lead in this proc
ess. They need to collaborate with AI developers\, but AI developers and t
he medical device industry should not lead this process. Radiologists shou
ld\, in fact\, stop training radiologists\, and instead\, start training m
achines.
DTSTART;TZID=America/Los_Angeles:20231115T090000
DTEND;TZID=America/Los_Angeles:20231115T100000
LOCATION:ZOOM: https://stanford.zoom.us/j/97076943141?pwd=Z2E5eGtaUDdNVklEY
VNpcDJzcy9sdz09
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar: Why AI Should Replace Radiologists
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-why-ai-should-replace-radiologists/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2023/11/Bram_van_Ginneken.jpg\;200\;200\,mediu
m\;http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upl
oads/2023/11/Bram_van_Ginneken.jpg\;200\;200\,large\;http://web.stanford.e
du/group/radweb/cgi-bin/radcalendar/wp-content/uploads/2023/11/Bram_van_Gi
nneken.jpg\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/r
adcalendar/wp-content/uploads/2023/11/Bram_van_Ginneken.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Bram van Ginneken\, PhD \nPr
ofessor of Medical Image Analysis \nChair of the Diagnostic Image Ana
lysis Group \nRadboud University Medical Center
\n
Title:
Why AI Should Replace Radiologists
\n
Abstract: \nIn thi
s talk\, I will provide arguments for the thesis that nearly all diagnosti
c radiology could be performed by computers and that the notion that AI wi
ll not replace radiologists is only temporarily true. Some well-known and
lesser-known examples of AI systems analyzing medical images with a stand-
alone performance on par or beyond human experts will be presented. I will
show that systems built by academia\, in collaborative efforts\, may even
outperform commercially available systems. Next\, I will sketch a way for
ward to implement automated diagnostic radiology and argue that this is n
eeded to keep healthcare affordable in societies wrestling with aging popu
lations. Some pitfalls\, like excessive demands for trials\, will be discu
ssed. The key to success is to convince radiologists to take the lead in t
his process. They need to collaborate with AI developers\, but AI develope
rs and the medical device industry should not lead this process. Radiologi
sts should\, in fact\, stop training radiologists\, and instead\, start tr
aining machines.
\n
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-3170@web.stanford.edu/group/radweb/cgi-bin/radcalendar
DTSTAMP:20240330T072556Z
CATEGORIES;LANGUAGE=en-US:AIMI
CONTACT:Ramzi Totah\; 6507214161\; rtotah@stanford.edu\; https://ibiis.stan
ford.edu/events/seminars/2023seminars.html
DESCRIPTION:Andrey Fedorov\, PhD \nAssociate Professor\, Harvard Medical Sc
hool\nLead Investigator\, Brigham and Women’s Hospital\n\n\n\nTitle: NCI I
maging Data Commons:Towards Transparency\, Reproducibility\, and Scalabili
ty in Imaging AI\n\n\n\n\n\n\n\n\n\nAbstract\nThe remarkable advances of a
rtificial intelligence (AI) technology are revolutionizing established app
roaches to the acquisition\, interpretation\, and analysis of biomedical i
maging data. Development\, validation\, and continuous refinement of AI to
ols requires easy access to large high-quality annotated datasets\, which
are both representative and diverse. The National Cancer Institute (NCI)
Imaging Data Commons (IDC) hosts over 50 TB of diverse publicly available
cancer image data spanning radiology and microscopy domains. By harmonizin
g all data based on industry standards and colocalizing it with analysis
and exploration resources\, IDC aims to facilitate the development\, valid
ation\, and clinical translation of AI tools and address the well-document
ed challenges of establishing reproducible and transparent AI processing
pipelines. Balanced use of established commercial products with open-sourc
e solutions\, interconnected by standard interfaces\, provides value and
performance\, while preserving sufficient agility to address the evolving
needs of the research community. Emphasis on the development of tools\, us
e cases to demonstrate the utility of uniform data representation\, and c
loud-based analysis aim to ease adoption and help define best practices. I
ntegration with other data in the broader NCI Cancer Research Data Commons
infrastructure opens opportunities for multiomics studies incorporating i
maging data to further empower the research community to accelerate breakt
hroughs in cancer detection\, diagnosis\, and treatment. The presentation
will discuss the recent developments in IDC\, highlighting resources\, dem
onstrations and examples that we hope can help you improve your everyday i
maging research practices – both those that use public and internal datase
ts.
DTSTART;TZID=America/Los_Angeles:20240320T120000
DTEND;TZID=America/Los_Angeles:20240320T130000
LOCATION:Clark Center S360 - Zoom Details on IBIIS website @ 318 Campus Dri
ve
SEQUENCE:0
SUMMARY:IBIIS & AIMI Seminar – NCI Imaging Data Commons: Towards Transparen
cy\, Reproducibility\, and Scalability in Imaging AI
URL:http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/event/ibiis-ai
mi-seminar-nci-imaging-data-commons-towards-transparency-reproducibility-a
nd-scalability-in-imaging-ai/
X-COST-TYPE:free
X-WP-IMAGES-URL:thumbnail\;http://web.stanford.edu/group/radweb/cgi-bin/rad
calendar/wp-content/uploads/2024/03/Andrey-Fedorov.jpg\;200\;200\,medium\;
http://web.stanford.edu/group/radweb/cgi-bin/radcalendar/wp-content/upload
s/2024/03/Andrey-Fedorov.jpg\;200\;200\,large\;http://web.stanford.edu/gro
up/radweb/cgi-bin/radcalendar/wp-content/uploads/2024/03/Andrey-Fedorov.jp
g\;200\;200\,full\;http://web.stanford.edu/group/radweb/cgi-bin/radcalenda
r/wp-content/uploads/2024/03/Andrey-Fedorov.jpg\;200\;200
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\n\n
Andrey Fedorov\, PhD \nAssociate Professor\
, Harvard Medical School \nLead Investigator\, Brigham and Women’s Ho
spital
\n
\n
\n
\n
Titl
e: NCI Imaging Data Commons:Towards Transparency\, Reproducibility\, and S
calability in Imaging AI
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Abstract \nThe remarkable advances of artifi
cial intelligence (AI) technology are revolutionizing established approach
es to the acquisition\, interpretation\, and analysis of biomedical imagin
g data. Development\, validation\, and continuous refinement of AI tools r
equires easy access to large high-quality annotated datasets\, which are
both representative and diverse. The National Cancer Institute (NCI) Imagi
ng Data Commons (IDC) hosts over 50 TB of diverse publicly available cance
r image data spanning radiology and microscopy domains. By harmonizing all
data based on industry standards and colocalizing it with analysis and e
xploration resources\, IDC aims to facilitate the development\, validation
\, and clinical translation of AI tools and address the well-documented ch
allenges of establishing reproducible and transparent AI processing pipel
ines. Balanced use of established commercial products with open-source sol
utions\, interconnected by standard interfaces\, provides value and perfo
rmance\, while preserving sufficient agility to address the evolving needs
of the research community. Emphasis on the development of tools\, use cas
es to demonstrate the utility of uniform data representation\, and cloud-
based analysis aim to ease adoption and help define best practices. Integr
ation with other data in the broader NCI Cancer Research Data Commons infr
astructure opens opportunities for multiomics studies incorporating imagin
g data to further empower the research community to accelerate breakthroug
hs in cancer detection\, diagnosis\, and treatment. The presentation will
discuss the recent developments in IDC\, highlighting resources\, demonstr
ations and examples that we hope can help you improve your everyday imagin
g research practices – both those that use public and internal datasets.
p>\n