Portrait de Danilo Bzdok

Danilo Bzdok

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur agrégé, McGill University
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

Publications

Large language models deconstruct the clinical intuition behind diagnosing autism
Emmett Rabot
Laurent Mottron
Cell type transcriptomics reveal shared genetic mechanisms in Alzheimer’s and Parkinson’s disease
Edward A. Fon
Alain Dagher
Yasser Iturria-Medina
Jo Anne Stratton
David A Bennett
Historically, Alzheimer’s disease (AD) and Parkinson’s disease (PD) have been investigated as two distinct disorders of the brain. Howev… (voir plus)er, a few similarities in neuropathology and clinical symptoms have been documented over the years. Traditional single gene-centric genetic studies, including GWAS and differential gene expression analyses, have struggled to unravel the molecular links between AD and PD. To address this, we tailor a pattern-learning framework to analyze synchronous gene co-expression at sub-cell-type resolution. Utilizing recently published single-nucleus AD (70,634 nuclei) and PD (340,902 nuclei) datasets from postmortem human brains, we systematically extract and juxtapose disease-critical gene modules. Our findings reveal extensive molecular similarities between AD and PD gene cliques. In neurons, disrupted cytoskeletal dynamics and mitochondrial stress highlight convergence in key processes; glial modules share roles in T-cell activation, myelin synthesis, and synapse pruning. This multi-module sub-cell-type approach offers insights into the molecular basis of shared neuropathology in AD and PD.
Cell type transcriptomics reveal shared genetic mechanisms in Alzheimer’s and Parkinson’s disease
Edward A. Fon
Alain Dagher
Yasser Iturria-Medina
Jo Anne Stratton
David A Bennett
Historically, Alzheimer’s disease (AD) and Parkinson’s disease (PD) have been investigated as two distinct disorders of the brain. Howev… (voir plus)er, a few similarities in neuropathology and clinical symptoms have been documented over the years. Traditional single gene-centric genetic studies, including GWAS and differential gene expression analyses, have struggled to unravel the molecular links between AD and PD. To address this, we tailor a pattern-learning framework to analyze synchronous gene co-expression at sub-cell-type resolution. Utilizing recently published single-nucleus AD (70,634 nuclei) and PD (340,902 nuclei) datasets from postmortem human brains, we systematically extract and juxtapose disease-critical gene modules. Our findings reveal extensive molecular similarities between AD and PD gene cliques. In neurons, disrupted cytoskeletal dynamics and mitochondrial stress highlight convergence in key processes; glial modules share roles in T-cell activation, myelin synthesis, and synapse pruning. This multi-module sub-cell-type approach offers insights into the molecular basis of shared neuropathology in AD and PD.
A hierarchical Bayesian brain parcellation framework for fusion of functional imaging datasets
Da Zhi
Caroline Nettekoven
Ana Lúısa Pinho
Jörn Diedrichsen
ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images
Chen Liu
Ke Xu
Liangbo L. Shen
Jay Stewart
Jay C. Wang
Lucian V. Del Priore
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.
Pain can’t be carved at the joints: defining function-based pain profiles and their relevance to chronic disease management in healthcare delivery design
Daniel S. Barron
Hannah Kiesow
Melanie Fu
Jessica Cohen-Tanugi
Paul Geha
Dustin Scheinost
Zacharia Isaac
David Silbersweig
BACKGROUND: Pain is a complex problem that is triaged, diagnosed, treated, and billed based on which body part is painful, almost without ex… (voir plus)ception. While the "body part framework" guides the organization and treatment of individual patients' pain conditions, it remains unclear how to best conceptualize, study, and treat pain conditions at the population level. Here, we investigate (1) how the body part framework agrees with population-level, biologically derived pain profiles; (2) how do data-derived pain profiles interface with other symptom domains from a whole-body perspective; and (3) whether biologically derived pain profiles capture clinically salient differences in medical history. METHODS: To understand how pain conditions might be best organized, we applied a carefully designed a multi-variate pattern-learning approach to a subset of the UK Biobank (n = 34,337), the largest publicly available set of real-world pain experience data to define common population-level profiles. We performed a series of post hoc analyses to validate that each pain profile reflects real-world, clinically relevant differences in patient function by probing associations of each profile across 137 medication categories, 1425 clinician-assigned ICD codes, and 757 expert-curated phenotypes. RESULTS: We report four unique, biologically based pain profiles that cut across medical specialties: pain interference, depression, medical pain, and anxiety, each representing different facets of functional impairment. Importantly, these profiles do not specifically align with variables believed to be important to the standard pain evaluation, namely painful body part, pain intensity, sex, or BMI. Correlations with individual-level clinical histories reveal that our pain profiles are largely associated with clinical variables and treatments of modifiable, chronic diseases, rather than with specific body parts. Across profiles, notable differences include opioids being associated only with the pain interference profile, while antidepressants linked to the three complimentary profiles. We further provide evidence that our pain profiles offer valuable, additional insights into patients' wellbeing that are not captured by the body-part framework and make recommendations for how our pain profiles might sculpt the future design of healthcare delivery systems. CONCLUSION: Overall, we provide evidence for a shift in pain medicine delivery systems from the conventional, body-part-based approach to one anchored in the pain experience and holistic profiles of patient function. This transition facilitates a more comprehensive management of chronic diseases, wherein pain treatment is integrated into broader health strategies. By focusing on holistic patient profiles, our approach not only addresses pain symptoms but also supports the management of underlying chronic conditions, thereby enhancing patient outcomes and improving quality of life. This model advocates for a seamless integration of pain management within the continuum of care for chronic diseases, emphasizing the importance of understanding and treating the interdependencies between chronic conditions and pain.
Follow the CSF flow: probing multiciliated ependymal cells in brain pathology
Adam M.R. Groh
L. M. Hodgson
Jo Anne Stratton
Inhibition of the inferior parietal lobe triggers state-dependent network adaptations
Kathleen A. Williams
Ole Numssen
Juan David Guerra
Gesa Hartwigsen
The human brain comprises large-scale networks that flexibly interact to support diverse cognitive functions and adapt to variability in dai… (voir plus)ly life. The inferior parietal lobe (IPL) is a hub of multiple brain networks that sustain various cognitive domains. It remains unclear how networks respond to acute regional perturbations to maintain normal function. To provoke network-level adaptive responses to local inhibition, we combined offline transcranial magnetic stimulation (TMS) over left or right IPL with neuroimaging during attention, semantic and social cognition tasks, and rest. Across tasks, TMS specifically affected task-active network activity with inhibition and facilitation. Network interaction responses differed between rest and tasks. After TMS over both IPL regions, large-scale network interactions were exclusively facilitated at rest, but mainly inhibited during tasks. Overall, responses to TMS primarily occurred in and between domain-general default mode and frontoparietal subnetworks. These findings elucidate short-term adaptive plasticity in response to network node inhibition.
Genetic Interplay Between White Matter Hyperintensities and Alzheimer's Disease: A Brain-Body Perspective
Manpreet Singh
Kimia Shafighi
Flavie E. Detcheverry
Fanta Dabo
Ikrame Housni
Sridar Narayanan
Sarah A. Gagliano Taliun
AmanPreet Badhwar
MRI-detected white matter hyperintensities (WMH) are often recognized as markers of cerebrovascular abnormalities and an index of vascular b… (voir plus)rain injury, and are frequently present in individuals with Alzheimer’s disease (AD). Given the emerging bidirectional communication between the brain-body axis in both WMHs and AD, it is important to understand their genetic underpinnings across the whole body. However, literature on this is scarce. We investigated the brain-body axis by breaking down heritability estimates of these phenotypes across the whole body, – i.e., partitioning heritability. Our aims were to identify genetic underpinnings specific to WMHs, and common between WMHs and AD, by assessing (a) the partitioned heritability of WMHs and AD across the brain-body axis with tissue-specific annotations, (b) the partitioned heritability of WMHs and AD across the brain-body axis with cell-specific annotations, and (c) the genes associated with WMHs and AD, and verifying their expression levels across the whole body. Our tissue-specific analysis revealed that WMH-associated SNPs were significantly enriched in tissues beyond the brain, namely liver, cardiovascular, and kidney – with liver being a common tissue enriched for both WMHs and AD. Our cell-specific analysis showed enrichment of vascular endothelial cells across the tissue types enriched for WMHs, highlighting their central role in the development of WMHs. Additionally, our gene-level analysis highlighted overlapping patterns of tissue enrichment for both WMHs and AD, and showed interactions between WMH and AD associated genes. Our findings provide new insights into the systemic influences potentially contributing to WMH pathology, in particular, multi-system endothelial disorder. We hope that our multisystemic genetic findings will stimulate future WMH-research into specific pathways across the brain-body axis.
Harnessing population diversity: in search of tools of the trade
Big neuroscience datasets are not big small datasets when it comes to quantitative data analysis. Neuroscience has now witnessed the advent … (voir plus)of many population cohort studies that deep-profile participants, yielding hundreds of measures, capturing dimensions of each individual’s position in the broader society. Indeed, there is a rebalancing from small, strictly selected, and thus homogenized cohorts toward always larger, more representative, and thus diverse cohorts. This shift in cohort composition is prompting the revision of incumbent modeling practices. Major sources of population stratification increasingly overshadow the subtle effects that neuroscientists are typically studying. In our opinion, as we sample individuals from always wider diversity backgrounds, we will require a new stack of quantitative tools to realize diversity-aware modeling. We here take inventory of candidate analytical frameworks. Better incorporating driving factors behind population structure will allow refining our understanding of how brain–behavior relationships depend on human subgroups.
Harnessing population diversity: in search of tools of the trade
Abstract Big neuroscience datasets are not big small datasets when it comes to quantitative data analysis. Neuroscience has now witnessed th… (voir plus)e advent of many population cohort studies that deep-profile participants, yielding hundreds of measures, capturing dimensions of each individual’s position in the broader society. Indeed, there is a rebalancing from small, strictly selected, and thus homogenized cohorts toward always larger, more representative, and thus diverse cohorts. This shift in cohort composition is prompting the revision of incumbent modeling practices. Major sources of population stratification increasingly overshadow the subtle effects that neuroscientists are typically studying. In our opinion, as we sample individuals from always wider diversity backgrounds, we will require a new stack of quantitative tools to realize diversity-aware modeling. We here take inventory of candidate analytical frameworks. Better incorporating driving factors behind population structure will allow refining our understanding of how brain–behavior relationships depend on human subgroups.
Three Subtypes of Autism Spectrum Disorder with Transcriptomic Signatures Derived from Morphometric Similarity Networks
Hongxiu Jiang
Raúl Rodríguez‐Cruces
Ke Xie
Valeria Kebets
Yezhou Wang
Clara F. Weber
Ying He
Jonah Kember
Jean‐Baptiste Poline
Seok‐Jun Hong
Boris C. Bernhardt
Xiaoqian J. Chai
ABSTRACT Autism spectrum disorder (ASD) is a prevalent and highly heterogeneous neurodevelopmental disorder. Previous studies have attempted… (voir plus) to identify ASD subgroups by analyzing isolated cortical structural features. However, these studies have not considered the relationship between multiple structural features, which provide information on the structural organization of the brain. Morphometric similarity network (MSN), a structural brain network contributed by multiple anatomical features (gray matter volume, mean cortical thickness, surface area, mean curvature, Gaussian curvature, curvature index, and fold index), strongly relates to cytoarchitectonic and genomic measures of histological similarity between cortical areas. We applied K-means clustering on MSN from 236 individuals with ASD and identified three subtypes. Subtype-1 showed relatively similar MSN values with typically developmental individuals (TD). Subtype-2 showed higher morphometric similarities in the lateral frontal and temporal cortical regions and lower in anterior prefrontal and occipital regions compared to TD. These patterns were the opposite in subtype-3. Behaviorally, subtype-3 had more severe verbal and social deficits compared to subtype-2. The weaker resting-state functional connectivity (rs-FC) between the language and salience networks was observed between subtype-2 and TD. Subtype-3 had stronger rs-FC between salience and default mode networks (DMN), between frontoparietal and visual networks, and between language and dorsal attention networks, while weaker rs-FC within DMN, within sensorimotor, and within salience networks. In addition, genes with expression patterns associated with regional MS changes in ASD subtypes were functionally enriched in neuron-specific biological processes related to nervous system development, synaptic signaling and chromatin organization. These genes were particularly enriched in GABAergic neurons, glutamatergic neurons, astrocytes and microglia. Taken together, our findings suggest the existence of different neuroanatomical subtypes based on multiple anatomical features in ASD with distinct transcriptomic signatures and functional connectome patterns.