Medical Imaging 

Credits and Contact Hours

4 credits, 4 contact hours

Instructor and Coordinator

Ge Wang

Textbook(s)

1. Fundamentals of Medical Imaging, Second Edition

Paul Suetens

Cambridge University Press, 2009

2. Machine Learning for Tomographic Imaging

Ge Wang, Yi Zhang, Xiaojing Ye, and Xuanqin Mou

IOP Publishing, 2019

Supplemental Materials

Additional journal articles, lecture notes, research papers, and educational resources will be provided throughout the course and made available through the course learning management system.

Catalog Description

This course provides an in-depth introduction to modern medical imaging, covering the physical, mathematical, computational, and engineering principles underlying major imaging modalities. Emphasis is placed on image formation, tomographic data acquisition, image reconstruction, and clinical applications. The course also introduces state-of-the-art artificial intelligence (AI) and deep learning (DL) methods for medical imaging, with particular attention to learning-based and data-driven tomographic reconstruction techniques. Students will gain both theoretical understanding and exposure to current research developments in medical imaging.

Prerequisites

BMED 2300 Bio-Instrumentation and Bio-Imaging, or equivalent background in biomedical imaging and instrumentation.

Course Classification

Elective undergraduate course and graduate course in Biomedical Engineering and related disciplines.

Course Outcomes

Students who successfully complete the course should be able to:

Student Outcomes

BME Program Criteria

Topics

Neural networks and deep learning; x-ray physics and imaging components; filtered backprojection; computed tomography (CT); cone-beam CT; spiral CT; interior CT; spectral CT; iterative reconstruction; learning-based image reconstruction; Maxwell equations; Bloch equations; magnetic resonance imaging (MRI); pulse sequences; image formation and reconstruction; advanced medical imaging modalities; artificial intelligence applications in medical imaging; and current research trends in medical imaging.

Software Requirements

Programming assignments and computational exercises may require the use of Python, TensorFlow, or equivalent machine learning and scientific computing software.

Grading Policy

Optional project-based credit may be awarded at the instructor's discretion.

Academic Integrity

Students are expected to uphold the highest standards of academic honesty and professional conduct. All submitted work must represent the student's own effort unless collaboration is explicitly authorized. Any form of academic dishonesty, including plagiarism, cheating, fabrication, or unauthorized collaboration, may result in disciplinary action according to university policies.

Course Format

This course consists of lectures, demonstrations, programming exercises, homework assignments, examinations, and discussions of current research topics. Students are expected to actively engage with course materials and complete all required assignments to reinforce their understanding of medical imaging principles and applications.