Calendar

Location & Timing

August 5, 2020
8:30am-4:30pm
Livestream: details to come

This event is free and open to all!
Registration and Event details

Overview
Advancements of machine learning and artificial intelligence into all areas of medicine are now a reality and they hold the potential to transform healthcare and open up a world of incredible promise for everyone. Sponsored by the Stanford Center for Artificial Intelligence in Medicine and Imaging, the 2020 AIMI Symposium is a virtual conference convening experts from Stanford and beyond to advance the field of AI in medicine and imaging. This conference will cover everything from a survey of the latest machine learning approaches, many use cases in depth, unique metrics to healthcare, important challenges and pitfalls, and best practices for designing building and evaluating machine learning in healthcare applications.

Our goal is to make the best science accessible to a broad audience of academic, clinical, and industry attendees. Through the AIMI Symposium we hope to address gaps and barriers in the field and catalyze more evidence-based solutions to improve health for all.

PHIND Seminar Series: Identifying Fibroblasts Subtypes Contributing to the Progression of Preinvasive to Invasive Lung Adenocarcinoma

Sylvia Plevritis, Ph.D.
Professor of Biomedical Data Science and of Radiology
Integrative Biomedical Imaging Informatics at Stanford
Stanford University

Location
Webinar URL: https://stanford.zoom.us/s/93945120934?pwd=a29GNjFCUzBtWjRsbFdnUnVUOTMzUT09
Dial: +1 650 724 9799  or +1 833 302 1536
Webinar ID: 939 4512 0934
Password: 767148

11:00am – 12:00pm Seminar & Discussion
RSVP: https://www.onlineregistrationcenter.com/SPlevritis

ABOUT

Dr. Sylvia K. Plevritis is Professor and Chair of Biomedical Data Science, Professor of Radiology at Stanford University and Program Director of the Stanford Biomedical Informatics Graduate Training Program. Dr. Plevritis leads a computational biology cancer research program that bridges genomics, imaging and population sciences to decipher properties of cancer progression and treatment response. Dr. Plevritis received her Ph.D. in Electrical Engineering and M.S. in Health Services Research, both from Stanford University, with a focus on cancer imaging physics and modeling cancer outcomes, respectively. She has had a primary authorship role on over 100 scientific cancer-related articles. She is a fellow of the American Institute for Medical and Biological Engineering (AIMBE) and Distinguished Investigator in the Academy of Radiology Research. She serves on the NCI Board of Scientific Advisors,  the Program Leadership Committee of the Stanford Cancer Institute and the Leadership Council of the Stanford Bio-X Program. Dr. Plevritis has served on numerous NIH study sections,  chaired scientific programs for the several professional societies including the American Association for Cancer Research (AACR) and presented keynote lectures across multiple scales of computational cancer biology.   Currently, she is the Program Director of the Stanford Center in Cancer Systems Biology (CCSB) and has been a Principal Investigator with the NCI Cancer Intervention Surveillance Network (CISNET) for over fifteen years.  She has served as Program Director of the Stanford Cancer Systems Biology Scholars Program (CSBS), and co-Division Chief of Integrative Biomedical Imaging Informatics at Stanford (IBIIS).

Sponsored by the PHIND Center and the Department of Radiology

PHIND Seminar Series: Maintaining Competitive Advantage through Intellectual Capital

Soody Tronson, M.S., J.D.
Founder
Presque

Location & Timing
11:00am – 12:00pm Seminar & Discussion
Webinar URL: https://stanford.zoom.us/s/98817009379?pwd=U21pYnpCTUlxY3U2TEh4RmhvMXpvQT09
Dial: +1 650 724 9799  or +1 833 302 1536
Webinar ID: 988 1700 9379
Password: 767148

RSVP: https://www.onlineregistrationcenter.com/STronson

ABSTRACT
Digital health has provided a range of solutions, including health and wellness-related management, machine learning algorithms for pattern recognition, AI for genetic analysis, AI-enhanced clinical decision making, and virtual doctors that use AI for patient intake triage. Intellectual property can play an important role in providing a competitive advantage in the digital health industry. We will explore opportunities and challenges for protecting digital health technologies during the program, including patent eligibility challenges and the use of trade secrets.

ABOUT SOODY TRONSON
Soody Tronson is Founding Managing Counsel at STLG Law Firm, counseling domestic and international clients in IP and technology transactions in a wide range of technologies. In 2016 she formed, Presque, a company developing a line of medical devices for mothers and infants.

Soody has over 25 years of operational experience in technology, business, management, and law in start-up and fortune 100 companies, including Schering Plough Pharmaceuticals, Hewlett-Packard Co., Avantec Vascular, and the law firms of HellerEhrman and Townsend and Townsend.

Soody serves in board and leadership capacities with several organizations including the Association of Women in Science STEM to Market national accelerator; Licensing Executives Society USA/Canada, California Lawyers Association, and the Palo Alto Area Bar Association. Soody is a Commissioner with the city of Menlo Park; and an active hands-on volunteer with several civic organizations including Defy Ventures, an entrepreneurship training program for currently and formerly incarcerated. Soody has instructed courses in IP, licensing, and entrepreneurship at the University of California, Stanford University and European institutions. She is the co-author of the book “Women Securing the Future with TIPPSS for IoT: Trust, Identity, Privacy, Protection, Safety, Security for the Internet of Things.”

Hosted by: Garry Gold, MD
Sponsored by the PHIND Center and the Department of Radiology

Judy Gichoya, MD
Assistant Professor
Emory University School of Medicine

Measuring Learning Gains in Man-Machine Assemblage When Augmenting Radiology Work with Artificial Intelligence

Abstract
The work setting of the future presents an opportunity for human-technology partnerships, where a harmonious connection between human-technology produces unprecedented productivity gains. A conundrum at this human-technology frontier remains – will humans be augmented by technology or will technology be augmented by humans? We present our work on overcoming the conundrum of human and machine as separate entities and instead, treats them as an assemblage. As groundwork for the harmonious human-technology connection, this assemblage needs to learn to fit synergistically. This learning is called assemblage learning and it will be important for Artificial Intelligence (AI) applications in health care, where diagnostic and treatment decisions augmented by AI will have a direct and significant impact on patient care and outcomes. We describe how learning can be shared between assemblages, such that collective swarms of connected assemblages can be created. Our work is to demonstrate a symbiotic learning assemblage, such that envisioned productivity gains from AI can be achieved without loss of human jobs.

Specifically, we are evaluating the following research questions: Q1: How to develop assemblages, such that human-technology partnerships produce a “good fit” for visually based cognition-oriented tasks in radiology? Q2: What level of training should pre-exist in the individual human (radiologist) and independent machine learning model for human-technology partnerships to thrive? Q3: Which aspects and to what extent does an assemblage learning approach lead to reduced errors, improved accuracy, faster turn-around times, reduced fatigue, improved self-efficacy, and resilience?

Zoom: https://stanford.zoom.us/j/93580829522?pwd=ZVAxTCtEdkEzMWxjSEQwdlp0eThlUT09

Join us for the 3rd Annual Diversity and Inclusion Forum on Friday, October 9, 2020 on Zoom! This virtual event will highlight innovative workshops developed by our residents and fellows with their educational mentors who have participated in the 2019-2020 cohort of the Leadership Education in Advancing Diversity Program.

The event will be an enriching opportunity for all faculty, residents, fellows, postdocs, students, staff, and community members to learn tools and strategies to enable them to become effective change agents for diversity, equity, and inclusion in medical education.

All are welcome to participate and we look forward to seeing you on Friday, October 9!

Register here:

https://mailchi.mp/046c21726371/diversityforum2020-1632872?e=4a913cab2d

In honor of the 30th anniversary of the Americans with Disabilities Act and October as National Disability Employment Awareness Month, join the Stanford Medicine Abilities Coalition (SMAC) for a first of its kind StanfordMed LIVE event focused on disability. Now more than ever during the COVID-19 pandemic, disabilities, health conditions, and illness impact not only our patients but also all of us, both personally and as members of the Stanford Medicine community. Stanford Medicine leadership will share information, answer questions, and engage in a roundtable discussion about the state of disability at Stanford and how best to support faculty, staff, and students living with disability and chronic illness. We encourage our community to submit questions and comments here to be shared broadly with the Stanford Medicine community. The same link can be used to request any accommodations needed for the livestream. Additional information for the webcast itself will be sent out closer to the event.

Livestream link: https://livestream.com/accounts/1973198/events/9288854

PHIND Seminar Series: Serum Modulation of Mitochondrial Function as a Scalable Sensor of Insulin Resistance

Andrew Lipchik, Ph.D.
Postdoctoral Fellow – Michael Snyder Lab
Stanford University

11:00am – 12:00pm Seminar & Discussion
12:00pm – 12:15pm Reception & Light Refreshments
RSVP: https://stanford.zoom.us/webinar/register/7716009863360/WN_dbeuo7csS8q_AhR88XET0g

Location: Zoom
Webinar URL: . https://stanford.zoom.us/s/96358568342
Webinar ID: 963 5856 8342
Dial: +1 650 724 9799  or +1 833 302 1536 (Toll Free)
Password: 767148

ABSTRACT
The global epidemic of obesity is associated with the dramatic increase in the prevalence of type 2 diabetes mellitus (T2D) with an estimated 400 million people worldwide will have T2D by 2030.  T2D is proceeded by insulin resistance (IR) for up to decades prior to onset of T2D. Current estimates suggest approximately one in three individuals are sufficiently insulin resistant to be at risk for IR complications including T2D, coronary heart disease and nonalcoholic fatty liver disease. IR often goes undiagnosed due to the complex, invasive and laborious nature of clamp assays preventing their universal application in the clinic. Surrogate measurements using fasting plasma glucose and insulin levels can estimate IR but are imprecise. There is a need for the identification of new biomarkers and assays for the detection and monitoring of IR. Here, we demonstrate the utility of cellular mitochondrial respiration in response to individuals’ serum as a sensor for personalized monitoring of insulin sensitivity. The modulation of insulin-dependent mitochondrial function by patient serum was highly correlated with insulin sensitivity as determined by the gold-standard modified insulin suppression test (IST). We further applied this methodology to monitor insulin sensitivity over time in response to illness as well as treatment with the insulin sensitizing medication, pioglitazone. Our results demonstrate the development and application of a novel surrogate measurement for the determination and monitoring of insulin sensitivity. This assay offers the advantages of minimal invasiveness and complexity compared to IST as well as superior correlation with IST compared to existing surrogate measurements.

ABOUT ANDREW LIPCHIK
Andrew Lipchik majored in Chemistry at Xavier University where he preformed research on the development of oxygen activation Ni(II) complexes with Dr. Craig Davis and Dr. Michael Baldwin at the University of Cincinnati. He went on to obtain his PhD from Purdue University under mentorship of Dr. Laurie Parker. His thesis work focused on identifying determinants of kinase substrate specificity. This understanding was applied to the development of novel kinase-specific peptide biosensors to monitor intracellular kinase activity. Following his graduate work, he joined the laboratory of Michael Snyder at Stanford University where he has focused on understanding the impact of the immune system on insulin resistance and glucose metabolism.

Hosted by: Garry Gold, M.D.
Sponsored by the PHIND Center and the Department of Radiology

ZOOM LINK HERE

“High Resolution Breast Diffusion Weighted Imaging”
Jessica McKay, PhD

ABSTRACT: Diffusion-weighted imaging (DWI) is a quantitative MRI method that measures the apparent diffusion coefficient (ADC) of water molecules, which reflects cell density and serves as an indication of malignancy. Unfortunately, however, the clinical value of DWI is severely limited by the undesirable features in images that common clinical methods produce, including large geometric distortions, ghosting and chemical shift artifacts, and insufficient spatial resolution. Thus, in order to exploit information encoded in diffusion characteristics and fully assess the clinical value of ADC measurements, it is first imperative to achieve technical advancements of DWI.

In this talk, I will largely focus on the background of breast DWI, providing the clinical motivation for this work and explaining the current standard in breast DWI and alternatives proposed throughout the literature. I will also present my PhD dissertation work in which a novel strategy for high resolution breast DWI was developed. The purpose of this work is to improve DWI methods for breast imaging at 3 Tesla to robustly provide diffusion-weighted images and ADC maps with anatomical quality and resolution. This project has two major parts: Nyquist ghost correction and the use of simultaneous multislice imaging (SMS) to achieve high resolution. Exploratory work was completed to characterize the Nyquist ghost in breast DWI, showing that, although the ghost is mostly linear, the three-line navigator is unreliable, especially in the presence of fat. A novel referenceless ghost correction, Ghost/Object minimization was developed that reduced the ghost in standard SE-EPI and advanced SMS. An advanced SMS method with axial reformatting (AR) is presented for high resolution breast DWI. In a reader study, AR-SMS was preferred by three breast radiologists compared to the standard SE-EPI and readout-segmented-EPI.

“Machine-learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study”
Michael Zhang, MD

ABSTRACT: Clinicoradiologic differentiation between benign and malignant peripheral nerve sheath tumors (PNSTs) is a diagnostic challenge with important management implications. We sought to develop a radiomics classifier based on 900 features extracted from gadolinium-enhanced, T1-weighted MRI, using the Quantitative Imaging Feature Pipeline and the PyRadiomics package. Additional patient-specific clinical variables were recorded. A radiomic signature was derived from least absolute shrinkage and selection operator, followed by gradient boost machine learning. A training and test set were selected randomly in a 70:30 ratio. We further evaluated the performance of radiomics-based classifier models against human readers of varying medical-training backgrounds. Following image pre-processing, 95 malignant and 171 benign PNSTs were available. The final classifier included 21 features and achieved a sensitivity 0.676, specificity 0.882, and area under the curve (AUC) 0.845. Collectively, human readers achieved sensitivity 0.684, specificity 0.742, and AUC 0.704. We concluded that radiomics using routine gadolinium enhanced, T1-weighted MRI sequences and clinical features can aid in the evaluation of PNSTs, particularly by increasing specificity for diagnosing malignancy. Further improvement may be achieved with incorporation of additional imaging sequences.