Jean-Baptiste Fasquel is seeking a fellow for MSCA PF 2026 in graph neural networks - applicati[...]

euraxess.ec.europa.eu - Jobboard; France; Sur place; EUR 60 000 - 80 000; Plein temps

Résumé du poste

A leading research university in France is seeking a researcher to develop innovative graph-based methods for evaluating motor function in children with cerebral palsy. The project focuses on the relationship between brain structures and motor function, utilizing advanced graph neural networks. Applicants must hold a PhD with up to 8 years of research experience and comply with mobility rules. A support program including training and funding for mobility will be provided.

Prestations

Dedicated support programme

Online training

Potential funding for mobility

Qualifications

• PhD holder with a maximum of 8 years of research experience.
• Familiarity with graph-based methods and neural networks.
• Experience in medical imaging and analysis.

Responsabilités

• Develop new graph-based methods for evaluating motor function.
• Investigate relationships between brain structures and motor function.
• Assess patient-specific rehabilitation therapy using neural networks.

Connaissances

Graph neural networks

Artificial Intelligence

Entropy

Brain Imaging

Medical Imaging

Video processing

Formation

PhD

Description du poste

Organisation / Company Université d'Angers Department Direction de la Recherche - Cellule Europe Laboratory LARIS Is the Hosting related to staff position within a Research Infrastructure? No

The LARIS laboratory is a multidisciplinary research unit in Science and Technology belonging to the University of Angers. Our objective is to cultivate a strong disciplinary openness in the field of Information and Communication Sciences and Technologies (ICST). We encourage the development of scientific work that mainly relies on the skills of ICST, while associating, for certain themes or fields of application, those of Engineering Sciences and Life Sciences.

The unit is structured into three balanced groups focusing their research on the study of dynamic systems (Dynamic Systems and Optimisation group), signal and image processing for life sciences (Information, Signal, Image and Life Sciences group) and reliability and operational performances of complex system (Reliability Engineering and Decision-Making tools group).

In the ISISV group (Information, Signal, Image and Life Sciences group), we have experts in different fields related to cerebral palsy, motor function, computer vision and graph related approaches: Mickaël Dinomais (professor and medical doctor – cerebral palsy), Josselin Demas (assistant professor and physical therapist – motor function and rehabilitation), Lena Carcreff (researcher in biomechanics – motor function and rehabilitation), Patty Coupeau (assistant professor – computer vision and graph neural networks), Anne Heurtier (professor - computer vision and entropy) and Jean‑Baptiste Fasquel (professor - computer vision, artificial intelligence and graph neural networks).

Presentation of the project

The proposed project deals with the conception of new graph-based methods for evaluating and predicting individual’s motor function of children suffering a cerebral palsy (permanent motor disorders resulting from neonatal ischaemic stroke). Approaches to be investigated will focus on the use of graphs used to model relationships between brain structures (from structural T1 MRI and diffusion MRI (DTI)) as well as the body skeleton (video of the gait).

The purpose is to develop new measurement techniques of entropy on graphs as well as new graph neural network architectures to assess the irregularity of the brain structure and as well as of the gait, both resulting from a stroke having an impact on the motor function. Concerning the use of graph neural networks, the explanability will be of interest to better understand the link between the brain disorder and the alteration of the motor function. This research project will be based on emerging and challenging advances on graph neural networks, as well as on entropy applied to graphs, to identify patient specific rehabilitation therapy.

Keywords

Graph neural networks, Artificial Intelligence, Entropy, Cerebral Palsy, Brain Imaging, Medical Imaging, Video processing

Applicants must comply with the mobility rule: having stay in France less than 12 months in the past 3 years before the 9th of September 2026. Applicants also must have maximum 8 years of research experience after graduating their (first) PhD.

A dedicated support programme will be offered to the selected fellow with online training, webinars, proofreading as well as a potential funding of mobility in Angers during 3 days for dedicated writing sessions.