Danilo Bzdok

Pourquoi les modèles d'IA hallucinent et comment y remédier

A tab representation of the Pre trained CLIP Vision Transformer

8 octobre 2025

par

Praneet Suresh

Jack Stanley

Danilo Bzdok

Sonia Joseph

Luca Scimeca

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

25 mars 2025

par

Jack Stanley

Danilo Bzdok

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

Towards Precision Medicine: Understanding Inference and Prediction Divergence in Biomedicine

8 octobre 2020

par

Danilo Bzdok

Publications

Inhibition of the inferior parietal lobe triggers state-dependent network adaptations

Kathleen A. Williams

Ole Numssen

Juan David Guerra

Jakub Kopal

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.

2024-10-31

Heliyon (publié)

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.

2024-09-27

medRxiv (prépublication)

Harnessing population diversity: in search of tools of the trade

Guy Wolf

Jakub Kopal

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.

2024-09-26

GigaScience (publié)

Harnessing population diversity: in search of tools of the trade

Guy Wolf

Jakub Kopal

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.

2024-09-26

GigaScience (publié)

Large language models auto-profile conscious awareness changes under psychedelic drug effects

Robin Carhart-Harris

Chloé Savignac

Gregory Bell

Steven Laureys

Abstract

Psychedelic experiences open a colorful view into drug-induced changes in conscious awareness. Small-samp… (voir plus)le studies on psychedelic drug action have gained traction in recent years. Yet, today’s means for measuring changes in subjective experience are mostly limited to legacy questionnaires of pre-assumed relevance, which could be complemented by bottom-up explorations of semantic facets that underlie experience reports. Here, we show how to harness large language models (LLMs) to i) design from scratch, ii) annotate at scale, and iii) evaluate with rigor a vast portfolio of experience dimensions during psychoactive drug influence, yielding > 2 million automatic dimension ratings that would otherwise have been done by hand. Investigator-independent LLM scoring of these drug effects on the human mind alone allowed to robustly discriminate the unique mental effects of 30 psychoactive substances. Successful knowledge integration of how psychedelics mediate shifts in subjective awareness will be an unavoidable milestone towards charting the full drug design space.

2024-08-07

Research Square (prépublication)

Nonlinear latent representations of high-dimensional task-fMRI data: Unveiling cognitive and behavioral insights in heterogeneous spatial maps

Mariam Zabihi

Seyed Mostafa Kia

Thomas Wolfers

Stijn de Boer

Charlotte Fraza

Richard Dinga

Alberto Llera Arenas

Christian F. Beckmann

Andre Marquand

Finding an interpretable and compact representation of complex neuroimaging data is extremely useful for understanding brain behavioral mapp… (voir plus)ing and hence for explaining the biological underpinnings of mental disorders. However, hand-crafted representations, as well as linear transformations, may inadequately capture the considerable variability across individuals. Here, we implemented a data-driven approach using a three-dimensional autoencoder on two large-scale datasets. This approach provides a latent representation of high-dimensional task-fMRI data which can account for demographic characteristics whilst also being readily interpretable both in the latent space learned by the autoencoder and in the original voxel space. This was achieved by addressing a joint optimization problem that simultaneously reconstructs the data and predicts clinical or demographic variables. We then applied normative modeling to the latent variables to define summary statistics (‘latent indices’) and establish a multivariate mapping to non-imaging measures. Our model, trained with multi-task fMRI data from the Human Connectome Project (HCP) and UK biobank task-fMRI data, demonstrated high performance in age and sex predictions and successfully captured complex behavioral characteristics while preserving individual variability through a latent representation. Our model also performed competitively with respect to various baseline models including several variants of principal components analysis, independent components analysis and classical regions of interest, both in terms of reconstruction accuracy and strength of association with behavioral variables.

2024-08-07

Public Library of Science ONE (publié)

Contributions of network structure, chemoarchitecture and diagnostic categories to transitions between cognitive topographies

Andrea I. Luppi

S. Parker Singleton

Justine Y. Hansen

Keith W. Jamison

Amy Kuceyeski

Richard F. Betzel

Bratislav Misic

The mechanisms linking the brain’s network structure to cognitively relevant activation patterns remain largely unknown. Here, by leveragi… (voir plus)ng principles of network control, we show how the architecture of the human connectome shapes transitions between 123 experimentally defined cognitive activation maps (cognitive topographies) from the NeuroSynth meta-analytic database. Specifically, we systematically integrated large-scale multimodal neuroimaging data from functional magnetic resonance imaging, diffusion tractography, cortical morphometry and positron emission tomography to simulate how anatomically guided transitions between cognitive states can be reshaped by neurotransmitter engagement or by changes in cortical thickness. Our model incorporates neurotransmitter-receptor density maps (18 receptors and transporters) and maps of cortical thickness pertaining to a wide range of mental health, neurodegenerative, psychiatric and neurodevelopmental diagnostic categories (17,000 patients and 22,000 controls). The results provide a comprehensive look-up table charting how brain network organization and chemoarchitecture interact to manifest different cognitive topographies, and establish a principled foundation for the systematic identification of ways to promote selective transitions between cognitive topographies.

2024-08-04

Nature Biomedical Engineering (publié)

Diversity-aware Population Models: Quantifying Associations between Socio-Spatial Factors and Cognitive Development in the ABCD Cohort

Avram Holmes

Sarah W. Yip

Population-level analyses are inherently complex due to a myriad of latent confounding effects that underlie the interdisciplinary topics of… (voir plus) research interest. Despite the mounting demand for generative population models, the limited generalizability to underrepresented groups hinders their widespread adoption in downstream applications. Interpretability and reliability are essential for clinicians and policymakers, while accuracy and precision are prioritized from an engineering standpoint. Thus, in domains such as population neuroscience, the challenge lies in determining a suitable approach to model population data effectively. Notably, the traditional strata-agnostic nature of existing methods in this field reveals a pertinent gap in quantitative techniques that directly capture major sources of population stratification. The emergence of population-scale cohorts, like the Adolescent Brain Cognitive DevelopmentSM (ABCD) Study, provides unparalleled opportunities to explore and characterize neurobehavioral and sociodemographic relationships comprehensively. We propose diversity-aware population modeling, a framework poised to standardize systematic incorporation of diverse attributes, structured with respect to intrinsic population stratification to obtain holistic insights. Here, we leverage Bayesian multilevel regression and poststratification, to elucidate inter-individual differences in the relationships between socioeconomic status (SES) and cognitive development. We constructed 14 varying-intercepts and varying-slopes models to investigate 3 cognitive phenotypes and 5 sociodemographic variables (SDV), across 17 US states and 5 race subgroups. SDVs exhibited systemic socio-spatial effects that served as fundamental drivers of variation in cognitive outcomes. Low SES was disproportionately associated with cognitive development among Black and Hispanic children, while high SES was a robust predictor of cognitive development only among White and Asian children, consistent with the minorities’ diminished returns (MDRs) theory. Notably, adversity-susceptible subgroups demonstrated an expressive association with fluid cognition compared to crystallized cognition. Poststratification proved effective in correcting group attribution biases, particularly in Pennsylvania, highlighting sampling discrepancies in US states with the highest percentage of marginalized participants in the ABCD Study©. Our collective analyses underscore the inextricable link between race and geographic location within the US. We emphasize the importance of diversity-aware population models that consider the intersectional composition of society to derive precise and interpretable insights across applicable domains.

2024-07-29

Research Square (publié)

Intrinsic structural covariation links cerebellum subregions to the cerebral cortex

Zilong Wang

Jörn Diedrichsen

Karin Saltoun

Christopher Steele

Sheeba Rani Arnold-Anteraper

B.T. Thomas Yeo

Jeremy Schmahmann

The human cerebellum is increasingly recognized to be involved in non-motor and higher-order cognitive functions. Yet, its ties with the ent… (voir plus)ire cerebral cortex have not been holistically studied in a whole-brain exploration with a unified analytical framework. Here, we characterized disso-ciable cortical-cerebellar structural covariation patterns across the brain in n=38,527 UK Bio-bank participants. Our results invigorate previous observations in that important shares of corti-cal-cerebellar structural covariation are described as i) a dissociation between the higher-level cognitive system and lower-level sensorimotor system, as well as ii) an anticorrelation between the visual-attention system and advanced associative networks within the cerebellum. We also discovered a novel pattern of ipsilateral, rather than contralateral, cerebral-cerebellar associations. Furthermore, phenome-wide association assays revealed key phenotypes, including cognitive phenotypes, lifestyle, physical properties, and blood assays, associated with each decomposed covariation pattern, helping to understand their real-world implications. This systems neurosci-ence view paves the way for future studies to explore the implications of these structural covaria-tions, potentially illuminating new pathways in our understanding of neurological and cognitive disorders.

2024-07-24

Journal of Neurophysiology (publié)

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

Zilong Wang

Jörn Diedrichsen

Karin Saltoun

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.

2024-07-24

Journal of Neurophysiology (inconnu)

Estimating Unknown Population Sizes Using the Hypergeometric Distribution

Liam Hodgson

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.

2024-07-22

ICML (Accept (Spotlight))

proceedings.mlr.press

Multilayer meta-matching: Translating phenotypic prediction models from multiple datasets to small data

Pansheng Chen

Lijun An

Naren Wulan

Chen Zhang

Shaoshi Zhang

Leon Qi Rong Ooi

Ru Kong

Jianzhong Chen

Jianxiao Wu

Sidhant Chopra

Simon B. Eickhoff

Avram J. Holmes

B.T. Thomas Yeo

Resting-state functional connectivity (RSFC) is widely used to predict phenotypic traits in individuals. Large sample sizes can significantl… (voir plus)y improve prediction accuracies. However, for studies of certain clinical populations or focused neuroscience inquiries, small-scale datasets often remain a necessity. We have previously proposed a “meta-matching” approach to translate prediction models from large datasets to predict new phenotypes in small datasets. We demonstrated a large improvement over classical kernel ridge regression (KRR) when translating models from a single source dataset (UK Biobank) to the Human Connectome Project Young Adults (HCP-YA) dataset. In the current study, we propose two meta-matching variants (“meta-matching with dataset stacking” and “multilayer meta-matching”) to translate models from multiple source datasets across disparate sample sizes to predict new phenotypes in small target datasets. We evaluate both approaches by translating models trained from five source datasets (with sample sizes ranging from 862 participants to 36,834 participants) to predict phenotypes in the HCP-YA and HCP-Aging datasets. We find that multilayer meta-matching modestly outperforms meta-matching with dataset stacking. Both meta-matching variants perform better than the original “meta-matching with stacking” approach trained only on the UK Biobank. All meta-matching variants outperform classical KRR and transfer learning by a large margin. In fact, KRR is better than classical transfer learning when less than 50 participants are available for finetuning, suggesting the difficulty of classical transfer learning in the very small sample regime. The multilayer meta-matching model is publicly available athttps://github.com/ThomasYeoLab/Meta_matching_models/tree/main/rs-fMRI/v2.0.

2024-07-16

Imaging Neuroscience (publié)