Portrait de Lune Bellec

Lune Bellec

Membre affilié
Professeure titulaire, Université de Montréal, Département de psychologie
Sujets de recherche
Apprentissage automatique médical
NeuroIA
Neuroimagerie (IRMf)
Neurosciences computationnelles
Site web
Google Scholar
LinkedIn
X

Biographie

Je suis professeure au département de psychologie de l’Université de Montréal et chercheuse principale du Laboratoire de simulation et d’exploration du cerveau (SIMEXP) à l’Institut universitaire de gériatrie de Montréal (CRIUGM). J’ai récemment rejoint Mila - Institut québécois d’intelligence artificielle en tant que membre affiliée, et je supervise des étudiant·e·s en informatique (neurosciences computationnelles cognitives) au DIRO, Université de Montréal.

Mon principal intérêt de recherche est d’entraîner des réseaux de neurones artificiels afin d’imiter conjointement l’activité cérébrale humaine individuelle et le comportement. Pour atteindre cet objectif, je dirige un effort intensif de collecte de données individuelles en neuroimagerie (IRMf, MEG) dans le cadre du projet Courtois sur la modélisation neuronale (CNeuroMod).

Je suis chercheuse boursière senior du FRQS, membre de l’Alliance québécoise en neurosciences et intelligence artificielle (UNIQUE), responsable du domaine Santé numérique au CRIUGM, co-responsable de la plateforme de gestion des données au CRIUGM et directrice adjointe à l’informatique neurofonctionnelle de l’Unité de neuroimagerie fonctionnelle (UNF) du CRIUGM.

Étudiants actuels

Hugo Delhaye
Maîtrise recherche - UdeM
Co-superviseur⋅e :
Audrey Durand
Maximilien Le Clei
Doctorat - UdeM
Pravish Sainath
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Guillaume Lajoie
Github

Publications

Training neural networks from scratch in a videogame leads to brittle brain encoding
François Paugam
Basile Pinsard
Marie St-Laurent
Guillaume Lajoie
Lune Bellec
Recent brain-encoding studies using videogame tasks suggest that the training objective of an artificial neural network plays a central role… (voir plus) in how well the network’s representations align with brain activity. This study investigates the alignment of artificial neural network activations with brain activity elicited by a video game task using models trained from scratch in controlled settings. We specifically compared three model training objectives: reinforcement learning, imitation learning, and a vision task, while accounting for other potential factors which may impact performance such as training data and model architecture. We tested models on brain encoding, i.e. their ability to predict functional magnetic resonance imaging (fMRI) signals acquired while human subjects played different levels of the video game Super Mario Bros. When tested on new playthroughs from the game levels seen at training, the reinforcement learning objective had a small but significant advantage in brain encoding, followed by the imitation learning and vision models. We hypothesized that brain-aligned representations would emerge only in task-competent models, and that the specific brain regions well encoded by a model would depend on the nature of the task it was trained on. While brain encoding did improve during model training, even an untrained model with matching architecture approached the performance of the best models. Contrary to our hypotheses, no model layers or specific training objectives aligned preferentially with specific brain areas. Large performance gaps also persisted in fully trained models across game levels, both those seen during training and entirely novel ones. Overall, even though reinforcement learning presented a small advantage to train brain encoding models for videogame data, all tested brain encoding models exhibited brittle performance with limited generalization both within- and out-of-distribution. Overall, our results suggest that training small artificial models from scratch is not sufficiently reliable, and that incorporating pretrained models such as foundation vision–action models may ultimately be necessary to support robust inferences about brain representations.
2025-12-01
bioRxiv (prépublication)
doi.org
Longitudinal reproducibility of brain and spinal cord quantitative MRI biomarkers
Mathieu Boudreau
Agah Karakuzu
Arnaud Boré
Basile Pinsard
Kiril Zelenkovski
Eva Alonso‐Ortiz
Julie Boyle
Lune Bellec
Julien Cohen-Adad
Abstract Quantitative MRI (qMRI) promises better specificity, accuracy, repeatability, and reproducibility relative to its clinically-used q… (voir plus)ualitative MRI counterpart. Longitudinal reproducibility is particularly important in qMRI. The goal is to reliably quantify tissue properties that may be assessed in longitudinal clinical studies throughout disease progression or during treatment. In this work, we present the initial data release of the quantitative MRI portion of the Courtois project on neural modelling (CNeuroMod), where the brain and cervical spinal cord of six participants were scanned at regular intervals over the course of several years. This first release includes 3 years of data collection and up to 10 sessions per participant using quantitative MRI imaging protocols (T1, magnetization transfer (MTR, MTsat), and diffusion). In the brain, T1MP2RAGE, fractional anisotropy (FA), mean diffusivity (MD), and radial diffusivity (RD) all exhibited high longitudinal reproducibility (intraclass correlation coefficient – ICC ≃ 1 and within-subject coefficient of variations – wCV 1%). The spinal cord cross-sectional area (CSA) computed using T2w images and T1MTsat exhibited the best longitudinal reproducibility (ICC ≃ 1 and 0.7 respectively, and wCV 2.4% and 6.9%). Results from this work show the level of longitudinal reproducibility that can be expected from qMRI protocols in the brain and spinal cord in the absence of hardware and software upgrades, and could help in the design of future longitudinal clinical studies.
2025-01-01
Imaging Neuroscience (publié)
doi.org
Longitudinal reproducibility of brain and spinal cord quantitative MRI biomarkers
Mathieu Boudreau
Agah Karakuzu
Arnaud Boré
Basile Pinsard
Kiril Zelenkovski
Eva Alonso‐Ortiz
Julie Boyle
Lune Bellec
Julien Cohen-Adad
Abstract Quantitative MRI (qMRI) promises better specificity, accuracy, repeatability, and reproducibility relative to its clinically-used q… (voir plus)ualitative MRI counterpart. Longitudinal reproducibility is particularly important in qMRI. The goal is to reliably quantify tissue properties that may be assessed in longitudinal clinical studies throughout disease progression or during treatment. In this work, we present the initial data release of the quantitative MRI portion of the Courtois project on neural modelling (CNeuroMod), where the brain and cervical spinal cord of six participants were scanned at regular intervals over the course of several years. This first release includes 3 years of data collection and up to 10 sessions per participant using quantitative MRI imaging protocols (T1, magnetization transfer (MTR, MTsat), and diffusion). In the brain, T1MP2RAGE, fractional anisotropy (FA), mean diffusivity (MD), and radial diffusivity (RD) all exhibited high longitudinal reproducibility (intraclass correlation coefficient – ICC ≃ 1 and within-subject coefficient of variations – wCV 1%). The spinal cord cross-sectional area (CSA) computed using T2w images and T1MTsat exhibited the best longitudinal reproducibility (ICC ≃ 1 and 0.7 respectively, and wCV 2.4% and 6.9%). Results from this work show the level of longitudinal reproducibility that can be expected from qMRI protocols in the brain and spinal cord in the absence of hardware and software upgrades, and could help in the design of future longitudinal clinical studies.
2025-01-01
Imaging Neuroscience (publié)
doi.org
Longitudinal reproducibility of brain and spinal cord quantitative MRI biomarkers
Mathieu Boudreau
Agah Karakuzu
Arnaud Boré
Basile Pinsard
Kiril Zelenkovski
Eva Alonso‐Ortiz
Julie Boyle
Lune Bellec
Julien Cohen-Adad
Quantitative MRI (qMRI) promises better specificity, accuracy, repeatability, and reproducibility relative to its clinically-used qualitativ… (voir plus)e MRI counterpart. Longitudinal reproducibility is particularly important in qMRI. The goal is to reliably quantify tissue properties that may be assessed in longitudinal clinical studies throughout disease progression or during treatment. In this work, we present the initial data release of the quantitative MRI portion of the Courtois project on neural modelling (CNeuroMod), where the brain and cervical spinal cord of six participants were scanned at regular intervals over the course of several years. This first release includes three years of data collection and up to ten sessions per participant using quantitative MRI imaging protocols (T1, magnetization transfer (MTR, MTsat), and diffusion). In the brain, T1MP2RAGE, FA, MD, and RD all exhibited high longitudinal reproducibility (intraclass correlation coefficient— ICC ≃ 1 and within-subject coefficient of variations— wCV 1%). The spinal cord cross-sectional area (CSA) computed using T2w images and T1MTsat exhibited the best longitudinal reproducibility (ICC ≃ 1 and 0.7 respectively, and wCV 2.4% and 6.9%). Results from this work show the level of longitudinal reproducibility that can be expected from qMRI protocols in the brain and spinal cord in the absence of hardware and software upgrades, and could help in the design of future longitudinal clinical studies.
2024-01-01
Imaging Neuroscience (publié)
doi.org