Dr Maëliss Jallais

(she/her)

Publication

• Date
• Type

Research

My research focuses on improving the reliability and interpretability of MRI-derived biomarkers for neuroscience and clinical applications. I specialise in Bayesian inference, combined with machine learning (ML) and diffusion MRI. My work addresses a central challenge in neuroimaging: how to obtain reliable, interpretable, and clinically useful tissue properties from indirect, noisy measurements, enabling robust scientific conclusions and clinically trustworthy biomarkers. 

Key scientific contributions:

• Introduction of simulation-based inference (SBI) for dMRI:
  • I introduced, as first author, the use of SBI, a Bayesian inference technique, to estimate probability distributions of tissue parameters in dMRI.
  • Personal contribution: Led the methodological development and implementation.
  • Why it matters: This approach moves beyond traditional point estimates, enabling more robust and informative characterisation of brain microstructure.
• Development of µGUIDE: a fast Bayesian framework for uncertainty quantification:
  • I developed µGUIDE, a novel Bayesian AI framework for estimating voxel-wise posterior distributions in qMRI and released it as open-source software.
  • Personal contribution: Designed the method, led validation, and implemented the software.
  • Why it matters: µGUIDE addresses a long-standing gap in the field by providing interpretable uncertainty estimates and detecting model degeneracies, improving reproducibility and enabling more trustworthy use of imaging biomarkers in research and clinical settings. It achieves ~1500-fold speed-up over traditional methods (e.g. MCMC), without acquisition constraints or expensive hardware, overcoming a major barrier to the practical use of Bayesian inference in MRI.
• Advances in uncertainty-aware modelling of brain microstructure:
  • I applied µGUIDE to recently proposed biophysical models incorporating cell permeability.
  • Personal contribution: Led the methodological application and analysis using µGUIDE.
  • Why it matters: This work shows that uncertainty can be used to identify and filter unreliable estimates and guide experimental design, highlighting the importance of uncertainty-aware analysis in neuroscience imaging.
• Improved dendritic spine density estimation using diffusion-weighted MR spectroscopy:
  • I demonstrated that combining single and double diffusion encoding MR spectroscopy acquisitions enhances sensitivity to dendritic spine density, using advanced computational modelling of metabolite diffusion.
  • Personal contribution: Led the study design and integrated Monte Carlo simulations in realistic neuronal digital twins, sequence optimization, and probabilistic modelling for signal analysis.
  • Why it matters: This work demonstrates that integrating computational modelling with acquisition design can reveal measurable signatures of complex cellular features, providing a general framework for developing more informative neuroimaging protocols.   
• Hierarchical Bayesian modelling for improved biomarker reliability:
  • I co-developed hierarchical-µGUIDE, a framework that leverages shared information across voxels to reduce voxel-wise uncertainty and degeneracy, while jointly learning a probabilistic brain parcellation.
  • Personal contribution: Co-developed the methodology, supervised the first-author PhD student, and contributed to implementation and evaluation.
  • Why it matters: This approach reduces uncertainty by up to 80%, enabling more stable parameter estimation while learning a microstructure-based probabilistic parcellation, without requiring registration.
• Addressing noise mismatch in supervised ML for dMRI:
  • I demonstrated that supervised ML models trained on simulated dMRI data can produce biased and misleading microstructure estimates due to mismatches between simulated and real noise distributions (covariate shift) and proposed a realistic noise synthesis strategy to correct this issue.
  • Personal contribution: Co-designed the study, identified the source of bias, and developed the methodological solution and validation framework.
  • Why it matters: This work identifies a fundamental flaw in how supervised ML is currently applied to dMRI and provides a principled solution to restore reliability.

Grants:

• UKRI STFC’s Africa-UK physics partnership collaborative projects 2025. Physics-Led Development of Brain Digital Twin Technology Using Low-Cost MRI and EEG in Sub-Saharan Africa. Role: Collaborator on the project led by Prof. Wheeler-Kingshott. April 2026 – April 2028.
• NMHII Future Leaders in Research Conference Funding. Conference funding for attending the annual ISMRM conference in Cape Town (South Africa) (£1000). 2026.
• Guarantors of Brain. Travel Award for attending the ISMRM Workshop on 40 Years of Diffusion: Past, Present & Future Perspectives in Kyoto (Japan) (£1200). 2025.
• Taith Research Mobility Award. Axonal signal fraction estimation and uncertainty quantification using µGUIDE in preclinical and clinical diffusion MRI data. £1800 for a research visit of a PhD student from the Technical University of Denmark (Thina Lundsgaard Thogersen, co-supervised by Dr Pizzolato and Prof Dyrby) for 3 weeks in CUBRIC. 2025.
• SFRMBM and FLI. Travel grant for attending the annual scientific ESMRMB conference in Barcelona (Spain) (500€). 2024.
• SFRMBM and FLI. Travel grant for attending the annual ISMRM conference in Singapore (500€). 2024.
• Guarantors of Brain. Travel Award for attending the annual ISMRM conference in Toronto (Canada) (£1000). 2023.
• SFRMBM and FLI. Travel grant for attending the annual ISMRM conference in Toronto (Canada) (500€). 2023.

Teaching

• Practical session assistant for the Machine Learning class (9h, 2021); ENSAE (France), Master level.
• Practical session assistant for a software engineering project (40h, 2021); Paris-Sud University (France), 3rd year Licence students.

Biography

Education

• 2022: PhD. Inria Saclay, CEA Neurospin, Université Paris Saclay (Saclay, France), under the supervision of Dr Demian Wassermann. Thesis title: Enabling cortical cell-specific sensitivity on diffusion MRI microstructure measurements using likelihood-free inference.
• 2018: Engineering Diploma . CPE Lyon (Lyon, France). Major: Image Analysis, Modelling and Computer Science.
• 2018: Research MSc. Université Lyon 1 (double degree with CPE Lyon). Image, Development and 3D Technologies.

Employment

• July 2025 - present: Postdoctoral position at the Cardiff University Brain Research Imaging Centre
  (CUBRIC), Cardiff, UK
  • Research subject: Green AI for Accelerated medical imaging (GAIA)
  • Supervisor: Dr Marco Palombo.
• June 2022 - June 2025: Postdoctoral position at the Cardiff University Brain Research Imaging Centre
  (CUBRIC), Cardiff, UK
  • Research subject: Microstructure imaging through diffusion MRI, computational modelling and
    machine learning
  • Supervisor: Dr Marco Palombo
  • In collaboration with the Molecular Research Imaging Center (MIRCen) at the CEA Fontenay-
    aux-Roses, France.
• Feb 2019 - Feb 2022: PhD program at Inria and CEA Neurospin, Parietal Team, Paris, France
  • Research subject: Enabling cortical cell-specific sensitivity on diffusion MRI microstructure
    measurements using likelihood-free inference
  • Supervisor: Dr Demian Wassermann
  • University: Université Paris-Saclay
  • Date of defense: 16/02/2022
  • PhD thesis
• Feb 2018 - July 2018: End-of-study internship, GE Healthcare, Buc, France
  • Research subject: Image flow analysis and segmentation in an interventional procedure
  • Supervisor: Dr Régis Vaillant
• July 2016 - June 2017: One-year internship, Medical image analysis and visualization team, Kitware, Carrboro, North Carolina, USA
  • Main developer of 3D scene reconstruction and object tracking system in C++
  • Supervisor: Dr Stephen Aylward
  • AnatomicAugmentedRealityProjector: Ultrasound Augmentation: Rapid 3D scanning for tracking and on-body display in C++ using CMake.

National and International Engagement

• Co-organizer of the ESMRMB precongress workshop on Microstructure Imaging in Girona (Spain) taking place in October 2026.
• Co-organizer of the Transferable Skills sessions at the ISMRM 2026 Annual Meeting in Cape Town (South Africa) taking place in May 2026: Designed and coordinated (4-person team) a six-session program featuring invited leading experts across academia and industry.
• Co-organizer (with three junior fellows) of the “From Method to Medicine: Bridging Impact Factor and Real-World Impact” session at the ISMRM 2026 Annual Meeting in Cape Town (South Africa) taking place in May 2026: Led the development and delivery of a focused session with invited experts.
• Chair and organizer of the MicroPhysics Meetings at CUBRIC (2024 -now): Weekly meetings including a team of 40 people working on microstructure imaging at CUBRIC.
• Organizer of the Visual Computing Hackathon at Cardiff University in June 2024 (three-day event).
• Chair and organizer of the Skill Session Meetings at CUBRIC (2022-2023) with invited speakers.
• Planner and organizer of CUBRIC MicroTeam Retreat in May 2023 (three days event).
• Chair and organizer of CUBRIC Centre Conference in January 2023, involving 100 researchers.

Honours and awards

Awards:

• ISMRM Junior Fellow, 2025: Program established to recognize outstanding researchers and clinicians at an early stage in their careers, with an established and long-term commitment to ISMRM.
• John Griffiths Award for Preclinical MR, 2025: Second prize at the British and Irish Chapter of ISMRM.
• Winner of the ISMRM Shark Tank competition, 2024: International entrepreneurial competition including mock interviews for convincing investors to invest in a hypothetical new company based on innovative ideas, with an expert judge panel.
• ISMRM Magna Cum Laude Merit Award, 2024: Trainee member award for an abstract ranked in the top 15% within the Diffusion MRI category.
• Mansfield Research Innovation Award, 2024: Awarded £1500 from the British & Irish Chapter of ISMRM and Siemens to attend the annual ISMRM conference in Singapore.
• ISMRM Summa Cum Laude Merit Award, 2023: Trainee member award for an abstract ranked in the top 5% within the Diffusion MRI category.
• ISMRM Magna Cum Laude Merit Award, 2021: Trainee member award for an abstract ranked in the top 15% within the Diffusion MRI category.

Invited talks: 

• Invited talk at the British & Irish Chapter of ISMRM MR Education Series, March 2026, online. Title: High Performance Neuro MRI: Insights into Grey Matter Microstructure.
• Invited talk at the ESMRMB Precongress workshop on Microstructural Imaging, Oct. 2025, Marseille (France). Title: Emerging AI Methods for Microstructure Parameter Estimation in Diffusion MRI.
• Keynote presentation at the DIPY (Diffusion Imaging in PYthon) workshop, March 2025 (Online edition). Title: Fast and Robust Simulation-Based Bayesian Inference with AI.
• Invited talk at the Microstructure Imaging meets Machine Learning (MIML) workshop, Sept. 2023, Cardiff (UK). Title: Fast and Robust Likelihood-Free Bayesian Inference with Machine Learning.

Speaking engagements

• Volunteer at the Rendez-vous des Jeunes Mathématiciennes et Informaticiennes, organised by Inria Saclay and Animaths in 2020 and 2021: Two-day’s events that aim to encourage female high school students to pursue scientific studies.

Committees and reviewing

• Regular reviewer for research-focused journals:
  • Advanced Science
  • Medical Image Analysis (MEDIA)
  • Magnetic Resonance in Medicine
  • Imaging Neuroscience
  • Human Brain Mapping
  • NeuroImage
• Reviewer for the ISMRM annual conference since 2023
• Reviewer for a final year MSc student in 2024 at Rennes University (France).

Supervisions

PhD students:

• Gerasimos Katsagannis - with Dr Palombo, Dr. Kopanoglu and Prof Cercignani; October 2025-present.

Visiting students:

• Visiting MSc student from Utrecht University (Paula Del Popolo); February-July 2025.
• Visiting PhD student from the Technical University of Denmark (Thina Lundsgaard Thøgersen, supervised by Dr Marco Pizzolato and Prof Tim Dyrby); January 2025.

MSc group project:

• Computer Science MSc project (5 students); 2026.

Current supervision

Gerasimos Katsagannis