Machine Learning for Neuroimaging

PSYC 121 / PSYC 221 / BIODS 227 | 2023 Fall

Course Information

  • Location : Building 530 - Main Quad, Room 127
  • Zoom : Available in Canvas
  • Time : 10:30am - 11:50am, Tu/Th; extra class for 4-unit students will be determined based on the availability of the students
  • Contact : psyc221-aut2223-staff@lists.stanford.edu
  • 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. The scheduling of this additional hour will be determined based on the availability of the students enrolled for 4 units to ensure a mutually convenient time slot. Undergraduate students and those who do not have ML backgrounds are advised to take the course for 4 units.
  • Grading : assigments (10%), attendence (5%), midterm exam (20%), project proposal presentation (10%), project (25%), final exam (30%)

    • Instructors

     
     
     

    Course Assistants

     
      
         
                 
     

    Syllabus



    Week Date Lecturer Topics Materials and Assignments
    Week 1 9/26 Tue Ehsan Adeli
    Qingyu Zhao
    Kilian Pohl     		Course outline, What is the brain
    • Course outline, introduction, course project
    • What is the brain and neuroimaging
    • Compile a list of definitions and connections to ML
    9/28 Thu Ehsan Adeli Intro to Multivariate Analysis
    Week 2 10/3 Tue Kilian Pohl Traditional MRI Processing
    10/5 Thu Kyan Younes (Stanford Neurology) Brain Anatomy and Neuroimaging Basics
    		(Extra class for 4-unit students) Python Basics / Numpy / ScikitLearn [Hands on], Thursday 10/5 5-6:30pm (Zoom and Recordings Available on Canvas)
    Week 3 10/10 Tue Qingyu Zhao Intro to Statistical Analysis
    - including intro to hypothesis testing     		Homework 1 released
    10/12 Thu Ehsan Adeli
    		In-Depth Machine Learning
    - Connection with Hypothesis Testing
    - Dimensionality reduction, Feature Selection     		(Extra class for 4-unit students) ML Supervised & Unsupervised Learning Thursday 10/12 5-6:30pm (Zoom and Recordings Available on Canvas)
    Week 4 10/17 Tue Kilian Pohl ML-based MR Preprocessing
    - EM for image inhomogenety
    - PCA for noise
    - ICA network     		Homework 2 released
    10/19 Thu Camila Gonzalez Hands on Statistics & ML (Python)
    - application to MRI     		(Extra class for 4-unit students) ML Q/A Thursday 10/5 6-7pm (Zoom and Recordings Available on Canvas)
    Week 5 10/24 Tue Kilian Pohl, Ehsan Adeli Brain Structural Analysis Homework 1 due
    10/26 Thu Midterm exam
    Project proposal presentation
    Week 6 10/31 Tue Kilian Pohl Longitudinal Analysis Homework 2 due
    11/2 Thu Ehsan Adeli Confounders and Metadata (Extra class for 4-unit students) MRI Generative Models (1 hour)
    Week 7 11/7 Tue Democracy Day, No classes
    11/9 Thu Kilian Pohl Connectome Based Modeling I
    		(Extra class for 4-unit students) ML/Python Libraries for Connectome Analysis (1 hour)
    Week 8 11/14 Tue Russ Poldrack (Stanford Psychology) Largescale Neuroimage Analysis & OpenNeuro Homework 3 released
    11/16 Thu Qingyu Zhao Connectome Based Modeling II
    Week 9 Thanksgiving No Classes
    Week 10 11/28 Tue Amy Kuceyeski (Cornell Radiology) Human brain responses are modulated when exposed to optimized natural images or synthetically generated images
    11/30 Thu Ehsan Adeli Transformers and Generative AI (Applications to Neuroimaging/Neuroscience) Homework 3 due
    (Extra class) Projects Q/A (1 hour)
    Week 11 12/5 Tue Project presentation
    12/7 Thu Project presentation
    Week 12 12/12 Tue Final exam

    Resources

    Reading List

    Textbooks (Not Requied)
  • 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)