Machine Learning for Neuroimaging

PSYC 121 / PSYC 221 / BIODS 227 | 2024 Fall

Course Information

  • Location : Lathrop 282, Lathrop Library
  • Zoom : Available in Canvas
  • Time : 10:30am - 11:50am, Tu/Th (3&4 Credits) ; 12:00 - 1:00 PM Fri via Zoom (4 Credit only)
  • Contact : psyc221-aut2425-staff@lists.stanford.edu
  • Text Book: Data Science for Neuroimaging: An Introduction (Online Version)
  • Description: Machine learning has driven remarkable advances in many fields and, recently, it has been pivotal in enhancing the diagnosis and treatment of complex brain disorders. Biomedical and neuroscience studies frequently rely on neuroimaging as it provides non-invasive quantitative measurement of the structure and function of the nervous system. Machine and deep learning methods can, for example, refine findings for specific diseases or cohorts enabling the detection of imaging markers at an individual level. This, in turn, paves the way for personalized treatment plans. In this course, we explore the methodological gaps in analyzing high-dimensional, longitudinal, and heterogeneous neuroimaging data and study novel, robust, scalable, and interpretable machine learning models for this purpose.
    Students have the option to enroll in the class for either 3 or 4 units. All students, regardless of their unit choice, are expected to attend every class session. The primary class content will cover the fundamentals of machine learning, offer some limited hands-on training, and explore the application of ML to neuroimaging. Those opting for 4 units will benefit from an extra hour of instruction weekly, diving deeper into core ML concepts and receiving extended hands-on training. Undergraduate students and those who do not have strong ML backgrounds are advised to take the course for 4 units.
  • Prerequisites (Suggested):
    • Proficiency in Python or other programming languages. The class will primarily use Python for assignments, but students are welcome to use other languages (such as R) if they prefer.
    • College Calculus, Linear Algebra (e.g., MATH 19, MATH 51)
    • Basic Probability and Statistics (e.g., CS 109, EE 178, or other stats course)
    • Familiarity with basics of machine learning (e.g., CS 229)
  • Grading : assigments (30%), attendence (5%), project proposal presentation (10%), project (25%), in-class exam (30%)

    • Instructors

     
     
     

    Course Assistants

     
     
           

    Course Admin


    Syllabus

    Week Date Topics Comments
    Week 1 9/24 Tue Course outline, Intros
    9/26 Thu Brain Anatomy and Neuroimaging basics
    Week 2 10/1 Tue Intro to Multivariate Analysis (ML)
    10/3 Thu Traditional MRI Preprocessing Chapter link
    10/4 Fri Tutorial: THE DATA SCIENCE TOOLBOX & PROGRAMMING Chapter link
    4 Credit only
    Week 3 10/8 Tue Image Registration & Parcellation Chapter link
    Homework 1 released
    10/10 Thu Image Segmentation Chapter link
    10/11 Fri Tutorial: SCIENTIFIC COMPUTING Chapter link
    4 Credit only
    Week 4 10/15 Tue Brain Structural Mapping (Feature Extraction)
    10/17 Thu Feature Selection & Dim reduction
    10/18 Fri Tutorial: NEUROIMAGING IN PYTHON Chapter link
    4 Credit only
    Week 5 10/22 Tue Statistical Parametric Mapping Homework 2 released
    10/24 Thu Brain Predictive Modeling I (DTI)
    10/25 Fri Tutorial: ML NEUROIMAGING Chapter link
    4 Credit only
    Week 6 10/29 Tue Brain Predictive Modeling II (fMRI) Homework 3 released
    10/31 Thu Brain Predictive Modeling III (Graph)
    11/1 Fri Tutorial: GRAPH & CONNECTOMES 4 Credit only
    Week 7 11/5 Tue Democracy Day, No classes
    11/7 Thu In Class Exam
    Week 8 11/12 Tue Project Milestone Presnetations
    11/14 Thu Other Modalities (PET, EEG, MEG, etc.)
    Week 9 11/19 Tue Longitudinal Analysis
    11/21 Thu Explainability in ML for Medical Imaging
    Week 10 11/26 Tue Thanksgiving Break
    11/28 Thu Thanksgiving Break
    Week 11 12/3 Tue Final Projects Presentations
    12/5 Thu Final Projects Presentations
    Week 12 12/10 Tue Project Report Due

    Resources

    Reading List (Not Required)

    Textbooks
  • Introduction to Neuroimaging Analysis
  • Pattern Recognition and Machine Learning
  • Deep Learning from Scratch (Python)
  • Machine Learning and Medical Imaging
    • ML for Neuroimaging
  • ML for neuroimaging with scikit-learn

    • Public Datasets

  • Human Connectome Project (HCP)
  • Alzheimer's Disease Neuroimaging Initiative: ADNI
  • Parkinson's Progression Markers Initiative (PPMI)
  • ABIDE - International Neuroimaging Data-sharing Initiative
  • OASIS Brains - Open Access Series of Imaging Studies
  • Multimodal Brain Tumor Segmentation Challenge 2020 (BraTS)
  • Adolescent Brain Cognitive Development (ABCD)