CSE 320/420 Biomedical Image Computing and Modeling (3)


Lifang He (Fall 2021)

Course 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.



Student will have

1. Understand the principles of biomedical imaging modalities such as X-ray, CT, MRI, Ultrasound, Nuclear Medicine, and Microscopy

2. Understand the definition and usage of standard biomedical image formats such as DICOM and TIFF

3. Have working knowledge and ability to write computer programs to implement algorithms for processing, enhancing and analyzing images, including image noise reduction, morphology, binary image analysis, image segmentation, image registration, image recognition, learning and statistical inference methods, functional and time series data analysis

4. Write graphics applications with graphical user interfaces (GUI) to implement image analysis, shape analysis and modeling, volume rendering, 3D surface reconstruction

5. Have a grasp of computer systems techniques for the storage, distribution, and retrieval of biomedical images

6. Understand guideline for the usage of display devices in medical diagnosis, electronic health records, and computer-aided diagnosis

7. Propose a course project integrating multiple techniques learned in class, develop a software demo for the courses project, perform system evaluation, present results in both technical report and oral presentation


CSE 320 substantially supports the following student enabled characteristics

A. An ability to apply knowledge of computing and mathematics appropriate to the discipline

B. An ability to analyze a problem and identify and define the computing requirements appropriate to its solution

I. An ability to use current techniques, skills, and tools necessary for computing practices

J. An ability to apply mathematical foundations, algorithmic principles, and computer science theory in the modeling and design of computer-based systems in a way that demonstrates comprehension of the tradeoffs involved in design choices

K. An ability to apply design and development principles in the construction of software systems of varying complexity

Prerequisites by Topic

  • Linear algebra: matrices, vectors, vector spaces, basic matrix transformations, eigenvalues and linear differential equations
  • Programming: algorithm and implementation in a high level language such as Matlab, Python, C/C++

Major Topics Covered in the Course

  • Subspace (manifold) learning Theory: PCA, kernel PCA; Applications: Eigen faces, Active shape models
  • Regularization Theory: Calculus of variations, total variation; Applications: image denoising, ROF model
  • Shape descriptors: Shape context, landmarks, medial axis, skeletons
  • Transformations and their manipulation Theory: diffeomorphisms; Applications: shape representation, image registration
  • Graphical Models Theory: Expectation maximization (EM) algorithm, inference; Applications: segmentation, tracking
  • Clustering Theory: K-means; Applications: grouping in images
  • Convolutional Neural Network: Network design; image classification/segmentation