AI for Medical Imaging

Period (from – till ): 16 November 2026 - 05 February 2027 (BMS_P2_A), Part-time. This course can be followed together with Diffusion MRI BMB4709022, the schedules do not overlap.

This course covers topics on deep learning for medical image analysis:
• Machine Learning fundamentals
• Deep Learning
• Convolutional Neural Network
• Network Architectures
• Medical Image Analysis applications

During practical sessions students will improve their understanding of the above topics. Additionally there will be a homework group assignment to be handed in at the end of the course.

Evaluation:
Students will be divided in groups to perform a homework assingment. At the end of the course, students will present their approach to the assingment. The final score is based on the evalution of:

• Multiple choice questions
• Approach to the homework. This item includes a peer-reviewcomponent (self evaluation among students in a group)
• Presentation according to the rubrics of the GSLS (a group presentation in which each student is required to present)
• Questions handling (on both the assignment and the material)

Literature/study material used:
Deep Learning with PyTorch by Eli Stevens, Luca Antiga, Thomas Viehmann. ISBN: 9781617295263; Please note that the book is available as an e-book on the website of Utrecht University Library

Registration:
You can register for this course via Osiris Student. More information about the registration procedure can be found here on the Students' site.
Students from outside the UU or TU/e MI-track can register for this course by sending an email to mix@umcutrecht.nl or via EduXchange. Please include your name, student number, Master’s programme and the course code.

Mandatory for students in Master’s programme:
no

Optional for students in other GSLS Master’s programme:
yes

After completing the course the student:
• will be familiar with the key concepts of machine learning and deep learning for medical imaging
• will be able to train and apply essential deep learning models to medical imaginga data
• will be familiar with how to evaluate deep learning methods in the context of medical imaging