Course Title

Medical Image Analysis (Master)

Course Number

467706

Instructor Name

Anas Toma

Contact Information

[email protected]

Semester(s) and academic year(s)

Second Semester 2026

Compulsory / Elective

Compulsory

This course provides a comprehensive and practical introduction to medical image processing, covering the fundamental principles, algorithms, and real-world applications used in modern healthcare systems. Students will study image acquisition, enhancement, restoration, segmentation, feature extraction, and deep learning, with emphasis on practical implementation and clinical relevance. Through hands-on exercises and case studies, learners will develop the skills needed to design, implement, and evaluate image processing solutions for medical diagnostics, visualization, and decision support using specialized computational tools.

Topics:

• Introduction to medical image processing and clinical applications
• Medical imaging modalities (X-ray, CT, MRI, Ultrasound, PET, SPECT)
• Digital image representation and basic image processing concepts
• Image acquisition, sampling, and quantization
• Image enhancement techniques in spatial and frequency domains
• Noise filtering, and image restoration
• Morphological image processing
• Edge detection and boundary extraction
• Image segmentation techniques (thresholding, region-based, clustering, model-based)
• Feature extraction and representation
• Texture analysis and shape descriptors
• Image Data Formats and Compression.
• Visualization and 3D reconstruction
• Introduction to deep learning
• Case studies and real-world clinical applications

The course aims to provide students with a solid theoretical foundation and practical skills in medical image processing. It focuses on enabling students to understand medical imaging data, apply appropriate processing techniques, design and implement image analysis algorithms, and critically evaluate processing results in clinical contexts. By the end of the course, students should be able to develop effective solutions for real-world medical imaging problems using modern computational tools and methodologies.

By successfully completing this course, students will be able to understand the principles of medical image formation and representation, analyze medical images using appropriate preprocessing and enhancement techniques, implement segmentation and feature extraction algorithms, apply deep learning for recognition, and design complete image processing pipelines for clinical applications. Students will also be able to critically assess algorithmic performance, interpret results in medical contexts, and communicate findings clearly and professionally.

Textbooks:

• Digital Image Processing, 4th Edition. Rafael C. Gonzalez and Richard E. Woods. ISBN-10: 1-292-22304-9.
• A Practical Approach to Medical Image Processing, Elizabeth Berry. ISBN 9780367452841.
• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. Aurélien Géron. 2^nd Edition. ISBN: 1492032646, 978-1492032649.
• Computer Vision: Principles, Algorithms, Applications, Learning, 5th Edition. E. R. Davies. eBook ISBN: 9780128095751. Hardcover ISBN: 9780128092842.

Tools:

• ImageJ
• Book materials
• CVIPtools
• GIMP
• OpenCV
• Scikit-Learn
• TensorFlow
• Keras