Portrait de Danilo Bzdok

Danilo Bzdok

Membre académique principal

bzdokdan@mila.quebec

Chaire en IA Canada-CIFAR

Professeur agrégé, McGill University, Département de génie biomédicale

Sujets de recherche

Apprentissage profond

Biologie computationnelle

Grands modèles de langage (LLM)

Traitement du langage naturel

Biographie

Danilo Bzdok est informaticien et médecin de formation. Il possède une double formation unique en neurosciences systémiques et en algorithmes d'apprentissage automatique. Après une formation à l'Université d'Aix-la-Chapelle (RWTH) (Allemagne), à l'Université de Lausanne (Suisse) et à la Harvard Medical School (États-Unis), il a obtenu un doctorat en neurosciences du Centre de recherche de Jülich (Allemagne) et un doctorat en informatique dans le domaine des statistiques d'apprentissage automatique à l'INRIA Saclay et à NeuroSpin (Paris, France). Il est actuellement professeur agrégé à la Faculté de médecine de l'Université McGill et titulaire d’une chaire en IA Canada-CIFAR à Mila – Institut québécois d'intelligence artificielle. Son activité de recherche interdisciplinaire est centrée sur la réduction des lacunes dans la connaissance des bases cérébrales des types de pensée qui définissent l'être humain, afin de découvrir les principes clés de conception computationnelle qui sous-tendent l'intelligence humaine.

Étudiants actuels

Karan Bali Bali

Doctorat - McGill

Doctorat - McGill

Yanis Bencheikh

Maîtrise recherche - HEC

Co-superviseur⋅e :

Anwesha Bhattacharya

Doctorat - McGill

Collaborateur·rice de recherche - CentraleSupélec

Pedro Carneiro Carneiro

Doctorat - McGill

Arthur Communal

Collaborateur·rice de recherche - École Polytechnique

Doctorat - McGill

Ryan McPhedrain McPhedrain

Postdoctorat - McGill

Maîtrise recherche - McGill

Sepehr Radmannia

Visiteur de recherche indépendant - McGill

Doctorat - McGill

Chloé Savignac

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Billets de blogue

A tab representation of the Pre trained CLIP Vision Transformer

8 octobre 2025

Pourquoi les modèles d'IA hallucinent et comment y remédier

par

25 mars 2025

Utiliser les LLMs pour mieux comprendre le diagnostic de l'autisme

par

Towards Precision Medicine: Understanding Inference and Prediction Divergence in Biomedicine

8 octobre 2020

Vers une médecine personnalisée : comprendre la divergence entre l’inférence et la prédiction en biomédecine

par

Publications

Estimating Unknown Population Sizes Using the Hypergeometric Distribution

The multivariate hypergeometric distribution describes sampling without replacement from a discrete population of elements divided into mult… (voir plus)iple categories. Addressing a gap in the literature, we tackle the challenge of estimating discrete distributions when both the total population size and the sizes of its constituent categories are unknown. Here, we propose a novel solution using the hypergeometric likelihood to solve this estimation challenge, even in the presence of severe under-sampling. We develop our approach to account for a data generating process where the ground-truth is a mixture of distributions conditional on a continuous latent variable, such as with collaborative filtering, using the variational autoencoder framework. Empirical data simulation demonstrates that our method outperforms other likelihood functions used to model count data, both in terms of accuracy of population size estimate and in its ability to learn an informative latent space. We demonstrate our method's versatility through applications in NLP, by inferring and estimating the complexity of latent vocabularies in text excerpts, and in biology, by accurately recovering the true number of gene transcripts from sparse single-cell genomics data.

2024-07-07

Proceedings of the 41st International Conference on Machine Learning (publié)

proceedings.mlr.press

ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images

Chen Liu

Ke Xu

Liangbo L. Shen

Guillaume Huguet

Jay Stewart

Jay C. Wang

Lucian V. Del Priore

Smita Krishnaswamy

Advances in medical imaging technologies have enabled the collection of longitudinal images, which involve repeated scanning of the same pat… (voir plus)ients over time, to monitor disease progression. However, predictive modeling of such data remains challenging due to high dimensionality, irregular sampling, and data sparsity. To address these issues, we propose ImageFlowNet, a novel model designed to forecast disease trajectories from initial images while preserving spatial details. ImageFlowNet first learns multiscale joint representation spaces across patients and time points, then optimizes deterministic or stochastic flow fields within these spaces using a position-parameterized neural ODE/SDE framework. The model leverages a UNet architecture to create robust multiscale representations and mitigates data scarcity by combining knowledge from all patients. We provide theoretical insights that support our formulation of ODEs, and motivate our regularizations involving high-level visual features, latent space organization, and trajectory smoothness. We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods. Our contributions include the development of ImageFlowNet, its theoretical underpinnings, and empirical validation on real-world datasets. The official implementation is available at https://github.com/KrishnaswamyLab/ImageFlowNet.

2024-06-19

ArXiv (prépublication)

High-effect gene-coding variants impact cognition, mental well-being, and neighborhood safety substrates in brain morphology

Guillaume Huguet

Shambhavi Aggarwal

Nicole Osayande

Kuldeep Kumar

Zohra Saci

Martineau Jean-Louis

Xiaoqian J. Chai

Tian Ge

B.T. Thomas Yeo

Paul M. Thompson

Carrie E. Bearden

Ole A. Andreassen

Sébastien Jacquemont

Our genetic makeup, together with environmental and social influences, shape our brain's development. Yet, the imaging genetics field has st… (voir plus)ruggled to integrate all these modalities to investigate the interplay between genetic blueprint, environment, human health, daily living skills and outcomes. Hence, we interrogated the Adolescent Brain Cognitive Development (ABCD) cohort to outline the effects of rare high-effect genetic variants on brain architecture and corresponding implications on cognitive, behavioral, psychosocial, and socioeconomic traits. Specifically, we designed a holistic pattern-learning algorithm that quantitatively dissects the impacts of copy number variations (CNVs) on brain structure and 962 behavioral variables spanning 20 categories in 7,657 adolescents. Our results reveal associations between genetic alterations, higher-order brain networks, and specific parameters of the family well-being (increased parental and child stress, anxiety and depression) or neighborhood dynamics (decreased safety); effects extending beyond the impairment of cognitive ability or language capacity, dominantly reported in the CNV literature. Our investigation thus spotlights a far-reaching interplay between genetic variation and subjective life quality in adolescents and their families.

2024-05-21

medRxiv (publié)

Supervised latent factor modeling isolates cell-type-specific transcriptomic modules that underlie Alzheimer’s disease progression

Yasser Iturria-Medina

Jo Anne Stratton

Smita Krishnaswamy

David A. Bennett

Late onset Alzheimer’s disease (AD) is a progressive neurodegenerative disease, with brain changes beginning years before symptoms surface… (voir plus). AD is characterized by neuronal loss, the classic feature of the disease that underlies brain atrophy. However, GWAS reports and recent single-nucleus RNA sequencing (snRNA-seq) efforts have highlighted that glial cells, particularly microglia, claim a central role in AD pathophysiology. Here, we tailor pattern-learning algorithms to explore distinct gene programs by integrating the entire transcriptome, yielding distributed AD-predictive modules within the brain’s major cell-types. We show that these learned modules are biologically meaningful through the identification of new and relevant enriched signaling cascades. The predictive nature of our modules, especially in microglia, allows us to infer each subject’s progression along a disease pseudo-trajectory, confirmed by post-mortem pathological brain tissue markers. Additionally, we quantify the interplay between pairs of cell-type modules in the AD brain, and localized known AD risk genes to enriched module gene programs. Our collective findings advocate for a transition from cell-type-specificity to gene modules specificity to unlock the potential of unique gene programs, recasting the roles of recently reported genome-wide AD risk loci. Designing a supervised latent factor framework for snRNA-seq human brain, the authors find distinct Alzheimer’s-predictive gene modules across celltypes, suggesting subcelltype disease progression trajectories.

2024-05-16

Communications Biology (publié)

Structural covariation between cerebellum and neocortex intrinsic structural covariation links cerebellum subregions to the cerebral cortex

Jörn Diedrichsen

Christopher Steele

Sheeba Rani Arnold-Anteraper

B. T. Thomas Yeo

Jeremy D. Schmahmann

Cerebellum’s association with the entire cerebral cortex has not been holistically studied in a unified way. Here, we conjointly character… (voir plus)ize the population-level cortical-cerebellar structural covariation patterns leveraging ∼40,000 UK Biobank participants whole brain structural scans and ∼1,000 phenotypes. We revitalize the previous hypothesis of an anticorrelation between the visual-attention system and advanced associative networks within the cerebellum. We also discovered a novel ipsilateral cerebral-cerebellar associations. Phenome-wide association (PheWAS) revealed real-world implications of the structural covariation patterns.

2024-02-19

bioRxiv (prépublication)

Performance reserves in brain-imaging-based phenotype prediction

Marc-Andre Schulz

Stefan Haufe

John-Dylan Haynes

Kerstin Ritter

This study examines the impact of sample size on predicting cognitive and mental health phenotypes from brain imaging via machine learning. … (voir plus)Our analysis shows a 3- to 9-fold improvement in prediction performance when sample size increases from 1,000 to 1 M participants. However, despite this increase, the data suggest that prediction accuracy remains worryingly low and far from fully exploiting the predictive potential of brain imaging data. Additionally, we find that integrating multiple imaging modalities boosts prediction accuracy, often equivalent to doubling the sample size. Interestingly, the most informative imaging modality often varied with increasing sample size, emphasizing the need to consider multiple modalities. Despite significant performance reserves for phenotype prediction, achieving substantial improvements may necessitate prohibitively large sample sizes, thus casting doubt on the practical or clinical utility of machine learning in some areas of neuroimaging.

2023-12-31

Cell Reports (publié)

Aberrant functional brain network organization is associated with relapse during 1-year follow-up in alcohol-dependent patients

Justin Böhmer

Pablo Reinhardt

Maria Garbusow

Michael Marxen

Michael N. Smolka

U. Zimmermann

Andreas Heinz

Eva Friedel

Johann Kruschwitz

Henrik Walter

Alcohol dependence (AD) is a debilitating disease associated with high relapse rates even after long periods of abstinence. Thus, elucidatin… (voir plus)g neurobiological substrates of relapse risk is fundamental for the development of novel targeted interventions that could promote long-lasting abstinence. In the present study, we analyzed resting-state functional magnetic resonance imaging (rsfMRI) data from a sample of recently detoxified AD patients (n = 93) who were followed-up for 12 months after rsfMRI assessment. Specifically, we employed graph theoretic analyses to compare functional brain network topology and functional connectivity between future relapsers (REL, n = 59), future abstainers (ABS, n = 28) and age and gender matched controls (CON, n = 83). Our results suggest increased whole-brain network segregation, decreased global network integration and overall blunted connectivity strength in REL compared to CON. Conversely, we found evidence for a comparable network architecture in ABS relative to CON. At the nodal level, REL exhibited decreased integration and decoupling between multiple brain systems compared to CON, encompassing regions associated with higher-order executive functions, sensory and reward processing. Among AD patients, increased coupling between nodes implicated in reward valuation and salience attribution constitutes a particular risk factor for future relapse. Importantly, aberrant network organization in REL was consistently associated with shorter abstinence duration during follow-up, portending to a putative neural signature of relapse risk in AD. Future research should further evaluate the potential diagnostic value of the identified changes in network topology and functional connectivity for relapse prediction at the individual subject level.

2023-10-01

Addiction Biology (publié)

Bayesian modelling disentangles language versus executive control disruption in stroke

Gesa Hartwigsen

Jae-Sung Lim

Hee-Joon Bae

Kyung-Ho Yu

Hugo J. Kuijf

Nick A. Weaver

J. Matthijs Biesbroek

Stroke is the leading cause of long-term disability worldwide. Incurred brain damage disrupts cognition, often with persisting deficits in l… (voir plus)anguage and executive capacities. Despite their clinical relevance, the commonalities, and differences of language versus executive control impairments remain under-specified. We tailored a Bayesian hierarchical modeling solution in a largest-of-its-kind cohort (1080 stroke patients) to deconvolve language and executive control in the brain substrates of stroke insults. Four cognitive factors distinguished left- and right-hemispheric contributions to ischemic tissue lesion. One factor delineated language and general cognitive performance and was mainly associated with damage to left-hemispheric brain regions in the frontal and temporal cortex. A factor for executive control summarized control and visual-constructional abilities. This factor was strongly related to right-hemispheric brain damage of posterior regions in the occipital cortex. The interplay of language and executive control was reflected in two factors: executive speech functions and verbal memory. Impairments on both were mainly linked to left-hemispheric lesions. These findings shed light onto the causal implications of hemispheric specialization for cognition; and make steps towards subgroup-specific treatment protocols after stroke.

2023-08-06

bioRxiv (prépublication)

Multivariate analytical approaches for investigating brain-behavior relationships

E. Leighton Durham

Andrew J. Stier

Carlos Cardenas-Iniguez

Gabrielle E. Reimann

Hee Jung Jeong

Randolph M. Dupont

Xiaoyu Dong

Tyler M. Moore

Marc G. Berman

Benjamin B. Lahey

Antonia N. Kaczkurkin

2023-07-30

Frontiers in Neuroscience (publié)

The default network dominates neural responses to evolving movie stories

Filip Milisav

Avram J. Holmes

Georgios D. Mitsis

Bratislav Misic

Emily S. Finn

Neuroscientific studies exploring real-world dynamic perception often overlook the influence of continuous changes in narrative content. In … (voir plus)our research, we utilize machine learning tools for natural language processing to examine the relationship between movie narratives and neural responses. By analyzing over 50,000 brain images of participants watching Forrest Gump from the studyforrest dataset, we find distinct brain states that capture unique semantic aspects of the unfolding story. The default network, associated with semantic information integration, is the most engaged during movie watching. Furthermore, we identify two mechanisms that underlie how the default network liaises with the amygdala and hippocampus. Our findings demonstrate effective approaches to understanding neural processes in everyday situations and their relation to conscious awareness.

2023-07-13

Nature Communications (publié)

Distinctive Whole-brain Cell-Types Predict Tissue Damage Patterns in Thirteen Neurodegenerative Conditions

Veronika Pak

Quadri Adewale

Mahsa Dadar

Yashar Zeighami

Yasser Iturria-Medina

Abstract For over a century, brain research narrative has mainly centered on neuron cells. Accordingly, most whole-brain neu… (voir plus)rodegenerative studies focus on neuronal dysfunction and their selective vulnerability, while we lack comprehensive analyses of other major cell-types’ contribution. By unifying spatial gene expression, structural MRI, and cell deconvolution, here we describe how the human brain distribution of canonical cell-types extensively predicts tissue damage in eleven neurodegenerative disorders, including early- and late-onset Alzheimer’s disease, Parkinson’s disease, dementia with Lewy bodies, amyotrophic lateral sclerosis, frontotemporal dementia, and tauopathies. We reconstructed comprehensive whole-brain reference maps of cellular abundance for six major cell-types and identified characteristic axes of spatial overlapping with atrophy. Our results support the strong mediating role of non-neuronal cells, primarily microglia and astrocytes, on spatial vulnerability to tissue loss in neurodegeneration, with distinct and shared across-disorders pathomechanisms. These observations provide critical insights into the multicellular pathophysiology underlying spatiotemporal advance in neurodegeneration. Notably, they also emphasize the need to exceed the current neuro-centric view of brain diseases, supporting the imperative for cell-specific therapeutic targets in neurodegeneration.

2023-06-08

bioRxiv (prépublication)

156. Modeling Eye Gaze to Videos Using Dynamic Trajectory Variability Analysis

Qianying Wu

Na Yeon Kim

Jasmin Turner

Umit Keles

Lynn Paul

Ralph Adolphs

2023-04-30

Biological Psychiatry (publié)