Miaomiao Zhang

CSE420 / 320: Biomedical Image Computing and Modeling

Description: This course focuses on an in-depth study of advanced topics and interests in image data analysis. Students will learn about hardcore imaging techniques and gain mathematical fundamentals needed to build their own models for an effective problem solving. Topics of deformable image registration, numerical analysis, probabilistic modeling, data dimensionality reduction, and convolutional neural networks for image segmentation will be covered. The main focus might change from semester to semester. Credit will not be given for both CSE 320 and CSE 420. Prerequisite: (Math 205 or Math 43) and CSE 017, or consent of instructor.

  • Class meetings: TR 1:10pm-2:25pm @ Whitaker Lab 270

  • Instructor: Miaomiao Zhang (miaomiao -at- cse.lehigh.edu)

  • Office hours: TR 3:30pm-4:30pm @ PL514A, or by appointment

Lecture materials including slides and notes will be posted on Course Site

Grading

  • Projects (4 course projects and 1 final project) (70%)

  • Presentation (20%)

  • Participation (10%)

No exams are required in this course. All programming will be in Matlab, a powerful, free programming tool for Lehigh students: https://software.lehigh.edu/install/. All reports must be written in LaTeX and submitted as a PDF.

Homeworks are due by midnight (11:59:59 PM) on the due date. Late assignments will not be accepted.

Schedule

Date Topics Projects
Week 1
Aug 29 Course Introduction
Aug 31 Introduction to Image Analysis and Basic Variational Methods
Week 2
Sep 5 Image Denoising I
Sept 7 Image Denoising II: Total Variation PS1, due on Sep 26
Week 3
Sep 12 Basics of Deformable Image Registration
Sep 14 Diffeomorphisms
Week 4
Sep 19 TBD
Sep 21 Geodesic Shooting I
Week 5
Sep 26 Geodesic Shooting II PS1 due
Sep 28 Diffeomorphic Image Registration: Adjoint Methods PS2, due on Oct 24
Week 6
Oct 3 Fréchet mean, atlas estimation
Oct 5 Data Dimensionality Reduction: Principal Component Analysis (PCA)
Week 7
Oct 10 TBD
Oct 12 TBD
Week 8
Oct 17 Pacing break
Oct 19 Nonlinear PCA methods, kernel trick
Week 9
Oct 24 Bayesian Methods PS2 due
Oct 26 Maximum a Posteriori (MAP), maximum likelihood (MLE) PS3, due on Nov 14
Week 10
Oct 31 Image Clustering: Gaussian Mixture Model
Nov 2 Expectation Maximization I
Week 11
Nov 7 Expectation Maximization II
Nov 9 Markov Chain Monte Carlo Methods
Week 12
Nov 14 Metropolis–Hastings PS3 due
Nov 16 Hamiltonian Monte Carlo PS4, due on Dec 5
Week 13
Nov 21 Image Classification / Segmentation Final project, due on Dec 14
Nov 23 Thanksgiving break
Week 14
Nov 28 Deep Learning I
Nov 30 Deep Learning II
Week 15
Dec 5 Paper presentation PS4 due
Dec 7 Paper presentation
Dec 14 Final project Report Due

Disclaimer

The instructor reserves the right to make changes to the course schedule, syllabus, and project deadlines. Changes will be announced early in advance.