About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

Predicting cognition from diffusion weighted MR images


In this master thesis, the student will use diffusion tensor imaging to build a model to assess an important cognitive score (the Symbol Digit Modalities Test) in a subset of healthy controls and people affected by multiple sclerosis. Multiple sclerosis is an inflammatory, neurodegenerative and demyelinating disease of the central nervous system. One of the disease’s components (demyelination) causes a reduction of the intracerebral conduction velocity, which we expect to highly correlate with a behavioural measure like the SDMT as this test is design to assess information processing speed.

Demyelination causes more random diffusion as opposed to diffusion along the white matter tracts and can therefore be assessed using DTI.

Kind of work

- Processing of diffusion weighted MR images using in-house scripts
- Building of an deep learning model to predict cognitive scores
- Validate the results

Framework of the Thesis

This project fits within the development of a biomarker of cognitive impairment in multiple sclerosis.

Number of Students


Expected Student Profile

- A strong interest in neuroimaging
- A strong interest in machine learning
- Confident in Linux


Dr. Ir. Jef Vandemeulebroucke

+32 (0)2 629 1033

more info

- Contact person




- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press


ETRO Department

Tel: +32 2 629 29 30

©2019 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer