MRS - AI PhD fellowship

We are offering a three-year PhD scholarship in Magnetic Resonance Spectroscopy and Artificial Intelligence in Lille, funded by the University of Lille's Excellence Initiative. The project will involved two laboratories: Lille Neuroscience & Cognition (U1172 LilNCog) and Unité de Catalyse et Chimie du Solide (UCCS). The PhD student will work at Lille University Hospital (France) and will be co-supervised by Dr R. Lopes and Pr. O. Lafon.

Thesis topic: 
Foundation Models for Magnetic Resonance Spectroscopy

Project

This PhD position is part of the IMMENSE interdisciplinary project, which aims to develop new magnetic resonance methods combining spectroscopy, imaging and artificial intelligence to improve diagnostics in medicine and characterization tools in chemistry and materials science. 
Magnetic resonance spectroscopy (NMR/MRS) provides unique information about molecular composition in fields ranging from brain metabolism to structural biology and materials science. However, spectral resolution strongly depends on the magnetic field strength. High-field instruments (e.g., 7 T MRI or ultra-high-field NMR) provide much higher spectral resolution than widely available lower-field systems. 

This PhD project aims to explore a new paradigm:

Can AI reconstruct high-field spectral information from low-field measurements?

The goal is to develop foundation models for spectroscopy, capable of learning general representations of NMR signals and enhancing spectral resolution across different instruments and applications.

Research Objectives

The PhD will develop AI models for spectral representation learning and super-resolution applied to magnetic resonance spectroscopy.

Main objectives include:

1.    Foundation models for spectroscopy: Develop deep learning models capable of learning general representations of NMR spectra across different magnetic fields and experimental conditions. 
2.    Spectral super-resolution: Train models to reconstruct high-resolution spectra from low-field acquisitions (e.g., 3 T → 7 T brain MR spectroscopy). 
3.    Cross-domain generalization: Investigate whether learned representations generalize across: brain metabolite spectroscopy, protein NMR, small-molecule spectroscopy, solid-state NMR for materials. 
4.    Spectroscopy datasets and benchmarks: Contribute to building standardized datasets of paired low-field and high-field spectra for training and evaluation.

Candidate Profile

We are looking for a highly motivated candidate with a background in:

Required:

•    Artificial Intelligence / Machine Learning 
•    Computer Science or Signal Processing 
•    Python and deep learning frameworks (PyTorch preferred) 
 

Preferred:

•    generative models or representation learning 
•    medical imaging or spectroscopy 

Education

Master’s degree or engineering degree in AI, computer science, applied mathematics, signal processing, physics or biomedical engineering.

Research Environment

The PhD will be conducted within an interdisciplinary environment combining:
•    expertise in AI, spectroscopy, neuroscience, and chemistry
•    clinical 3 T and 7 T MRI scanners 
•    ultra-high-field NMR spectrometers 

Contact: Applicants should send to Renaud LOPES and Olivier LAFON: CV + motivation letter + academic transcripts + contact details of two referees.

Expected start date: October 2026