Job purpose
Multiple sclerosis (MS) is a neurological disease that affected 2.8 million of people in 2020 worldwide. It is incurable and damages the central nervous system. Cognitive impairment affects one out of two patients and heavily impacts daily life activities. One of the important and long-standing problems in multiple sclerosis (MS) is the clinico-radiological paradox: the lack of a strong link between brain damage as seen on brain images and the physical and cognitive status of a patient. Using AI, we aim to identify imaging biomarkers for cognitive status. First, AI will compress brain images into key variables. Then, a federated learning model will predict cognitive state without sharing patient data. Lastly, causal inference modeling will refine predictions and reveal hidden relationships and improve the effectivity of the federated learning approach. Clinically, this project offers new insights into the paradox and a tool to flag patients for early neuropsychological testing, enabling timely intervention.
The project consists of 2 PhD students, one on the clinical side, and one focusing on the computer science aspects. In this PhD position, you will a) extend the existing body of research by integrating kernel fusion with causality, b) extend causality techniques for distributed representations, c) extend the state of the art by integrating both methods with federated learning.
The research will be carried out within the Artificial Intelligence Lab (https://ai.vub.ac.be) of Vrije Universiteit Brussels university, where you will join a multidisciplinary team of AI researchers, in collaboration with the AIMS (https://aims.research.vub.be/en/home) research group that leverages developments in artificial intelligence into an improved clinical practice and health.
Qualifications
- You have obtained a master’s degree in artificial intelligence, computer science, engineering or a related domain. You have a solid academic track record, preferably at the cum laude level. Students who will obtain their master’s degree in 2025 are also encouraged to apply.
- You have experience with and/or knowledge of neural networks, computer vision, reasoning, statistical machine learning and Bayesian approaches, with an understanding of both the mathematical foundations and programming.
- You are honest, strive for excellence, eager to learn and have a scientific mindset. You are a loyal team and open-minded player who likes to have fun, who can work autonomously and deliver solid scientific work.
- You have strong communication skills in English.
All qualifications must comply with provincial human rights legislation.
Salary, Advantages & other practical information
A fully funded PhD position (up to 4 years upon positive evaluation) in a team with weekly knowledge sharing sessions, opportunities to travel abroad. The opportunity to carry out research at the highest international level, aiming for excellence in research with impact on society
The opportunity to collaborate with leading research groups at different universities, including medical neuroscientists.
Hospitalization insurance, public transport reimbursement and other benefits
Transportation costs are reimbursed in total.
How to apply:
To express your interest, please send the following documents by mail with subject: “CFKL”
to Laetitia d’Ornano (laetitia.dornano@vub.be).
Please note that only complete applications will be processed.
- Cover letter of motivation with contact information (max. 2 pages), explaining why you like AI (incl. most exciting AI technique & why), how you learn, how you tackle complex software designs, your experiences working in team and solving real problems, your biggest mistake, how you have fun.
- Detailed CV
- Transcripts of your academic records
- Name and contact details of two references who would be willing to write a recommendation letter if asked (you do not need to contact them yourself)
- A writing sample (such as your master’s thesis)
The starting date will ideally be June 2025.