Capita Selecta Medical Imaging (UU)

Coursecode: bmb502517
Coursecoordinator: dr. Alexander Leemans
Credits: 5 EC
Lecturers: dr. Hugo Kuijf, dr. Matteo Maspero, dr. Bas van der Velden, dr. Alexander Leemans, Iris Vos, Maarten Terpstra

Course description:

In this course a selection of more specialized, independent topics in the field of medical imaging research will be covered by lecturers who are experts in the respective fields.

During the first half of the course topics on deep learning for medical image analysis will be introduced:

  • 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.

The second half of the course covers theory and practice of processing, analysing and visualising diffusion MRI data. Key concepts and practical considerations of data processing and analysis are explained. Topics include:

  • Quality assessment
  • Artifact correction
  • Diffusion approaches
  • Fiber tractography
  • Automated analyses
  • Visualisation methods

During computer practical sessions students will learn how to work with real diffusion MRI data.

Learning goals: upon completion of the course the student

  • will be familiar with the concepts of machine learning and deep learning
  • will be familiar with the latest developments and clinical applications of these techniques
  • has a basic understanding of neural networks for medical image analysis
  • can identify common MRI artifacts present in diffusion MRI data
  • will know the basic processing steps required for diffusion MRI
  • is able to discriminate between different diffusion MRI model strategies
  • will have basic hands-on knowledge of analysing and visualizing diffusion MRI data
  • will understand the limitations and pitfalls in the context of neuroscientific and biomedical applications

Literature/study material: Deep Learning with PyTorch” door Eli Stevens, Luca Antiga, Thomas Viehmann ISBN: 9781617295263
hand-outs provided by lecturers
suggested reading material

Examinitation: written exam at end of course

Prerequisite knowledge: none.

Date: Mondays between 9 – 16 hours, 14 November 2022 – 30 January 2023


Please check the registration procedure for the enrollment deadlines.

Other UU and TU/e partnership students can register for this course via Osiris Student.

Students from outside the UU or TU/E partnership can register for this course by sending an email to Please include your name, student number, Master’s programme and the course code.


For directions to the lecture rooms go to Route.