ENEE 739R: Medical Image Processing and Understanding
Course Goals:
This advanced level graduate course will cover the following topics: Brief discussion of computed tomography, nuclear magnetic resonance, and magnetic resonance imaging modalities. Detailed coverage of algorithms for processing and understanding these images, including, reconstruction, segmentation, and registration with an emphasis on non-rigid models. This course is designed to serve as an introduction to common medical acquisition modalities, the image reconstruction algorithms behind them, and postacquisition image processing techniques. The course focuses on hands-on learning and is project intensive.
Course Prerequisite(s):
Prerequisites: ENEE 620, ENEE 630, ENEE 621 and ENEE 631
Topics Prerequisite(s):
Textbook(s)
Reference(s):
Z.P. Liang and P.C. Lauterbur, Principles of Magnetic Resonance Imaging: A Signal Processing Perspective.Handbook of Medical Image Processing and Analysis, Edited by Issac Bankman, SPIE 2000.
Recommended Books:
Cho, Jones and Singh, Foundations of Medical Imaging.
Kak and Slaney, Principles of Computerized Tomographic Imaging.
Shung, Smith and Tsui, Principles of Medical Imaging.
Recent papers from the literature will also be discussed.
Core Topics:
Computed tomography: Basic physics, radon transform, central slice theorem, and tomographic reconstruction from 2D and 3D projections.
Magnetic resonance imaging: Nuclear magnetic resonance principles, signal segmentation and detection, and imaging concepts (slice selection, frequency encoding, and phase encoding).
Ultrasound: Ultrasound generation and detection, grayscale imaging, doppler imaging, linear and 2D arrays, and beamforming.
Nuclear medicine: Basic principles, filtered backprojection reconstruction, attenuation correction, and iterative reconstruction.
Image enhancement: Pixel and local operations, and adaptive image filtering.
Image segmentation: Edge- and region-based, clustering-based, and deformable models.
Image registration: Linear and nonlinear transformation models, landmark-based techniques, feature-based techniques, and image similarity–based techniques.
Optional Topics:
Course Structure:
Grading Method:
| Homework: | 15% |
| Midterm: | 30% |
| Project: | 20% |
| Final Exam: | 35% |