MR Image Processing

Short Description: This course offers a comprehensive overview of MR image processing techniques, focusing on both key concepts and practical applications. It consists of five modules: an introduction, segmentation and registration, radiomics, fMRI data processing, and hands-on practical exercises. Through a combination of lectures and interactive notebooks, students will develop both theoretical knowledge and practical skills for processing and analyzing MR images in research and clinical settings.

Target Audience: Researchers, clinicians, radiologists, medical physicists, and students in biomedical engineering or related fields interested in learning MR image processing techniques for research and clinical applications.

Prerequisites: Basic understanding of MR imaging principles, fundamental programming skills (preferably in Python or MATLAB), and familiarity with medical imaging concepts.

Course Objectives:

1. Provide a comprehensive understanding of MR image processing techniques, including segmentation, registration, radiomics, and fMRI data processing.
2. Equip students with the ability to utilize theoretical knowledge to solve practical challenges in MR image analysis using interactive tools.
3. Enable students to apply advanced image processing methods in both research and clinical settings.
4. Develop hands-on expertise through interactive notebooks and practical exercises.
5. Foster an understanding of how MR image analysis contributes to clinical decision-making and research outcomes.

Course Materials:

Textbook: McAndrew, A. Introduction to Digital Image Processing with MATLAB®. (ISBN 0-534-40011-6).

Software: MATLAB/Python

Module	Topic	Lecture
Module 1A	Householding; Why image processing?	Recording in Progress
Module 1B	Practical module 1A	Jupyter Notbook
Module 2A	Bits; Pixel reduction; Dithering; Contrast; Histograms	Recording in Progress
Module 2B	Practical module 2A	Jupyter Notbook
Module 3A	Linear registration; Interpolation; Motion correction	Recording in Progress
Module 3B	Practical module 3A	Jupyter Notbook
Module 4	Edges; Neighborhood processing; Filtering; Masking; Kernels	Recording in Progress
Module 5A	Fourier Transform (FT); Convolution	Recording in Progress
Module 5B	Practical module 4 and 5A	Jupyter Notbook
Module 6	Dilation; Erosion	Recording in Progress
Module 7A	Segmentation; Connected components	Recording in Progress
Module 7B	Practical module 6 and 7A	Jupyter Notbook
Module 8	Distance transform; Hough transform for straight lines
Module 9	Machine learning technical	Recording in Progress
Module 10	Machine learning applied	Recording in Progress
Module 11	MRI Segmentation: Basic Concepts and Modern Methods
Module 12	Radiomics
Module 13	FMRI data processing