AMS 563,  Medical Image Analysis

This course explores the fundamental principles and algorithms used in medical image processing and analysis. Key topics include interpolation, registration, enhancement, feature extraction, classification, segmentation, quantification, shape analysis, motion estimation, and visualization, including traditional and machine learning techniques. Both anatomical and functional image analysis will be covered, using data from common medical imaging modalities. Through projects and assignments, students will gain hands-on experience working with real medical imaging data. 

Prerequisites:  None.  However, we assume students have a foundational understanding of linear systems and calculus, including differential equations.  Familiarity with elementary probability theory and Python programming skills is also recommended. Please contact the instructor if you have any questions about your preparation.

0-3 credits; ABCF grading

Course Materials:
None required.  Readings to be made available on Brightspace.

 

Topics:

Interpolation, registration, enhancement, feature extraction, classification, segmentation, quantification, shape analysis, motion estimation, and visualization

Learning Outcomes:

1. Understand the principles, strengths, and limitations of different medical imaging modalities (e.g., X-ray, CT, MRI, PET, and Ultrasound).

2. Develop proficiency in applying image preprocessing and enhancement techniques, such
as filtering, segmentation, and edge detection, to medical images.

3. Explore key algorithms used in medical image reconstruction, registration, and visualization, with a focus on their mathematical underpinnings.

4. Apply machine learning (ML) and deep learning (DL) algorithms to classify, segment, and
detect medical images.

5. Implement these methods in real-world scenarios, evaluate outcomes, and address ethical
considerations of medical imaging.Explores the fundamental principles and algorithms used in medical image processing and analysis