Joël Chavas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Joël Chavas has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Jean-François Mangin
Université Paris-Saclay
4 shared publications - Benoit Dufumier
Université Paris-Saclay, CEA, CNRS, NeuroSpin, Baobab
3 shared publications - Denis Rivière
Université Paris-Saclay, CEA, CNRS, NeuroSpin, Baobab
3 shared publications - Vincent Frouin
NeuroSpin, CEA, Université Paris-Saclay, Gif-sur-Yvette, France
3 shared publications - Antoine Dufournet
Université Paris-Saclay, CEA, CNRS, Neurospin, UMR 9027 BAOBAB, GAIA Laboratory, Gif-sur-Yvette, France
2 shared publications Arnaud Cachia
UMR8240, Laboratory for the Psychology of Child Development and Education, Université Paris Cité, CNRS, Paris, 75005, France
2 shared publications
Latest Publications
- Open Access
Self-supervised representations reveal the genetic architecture of human cortical folding
1 Cortical folding emerges during fetal development, is under genetic control, and remains stable throughout life, offering a lasting window into early neurodevelopment. Conventional morphometric descriptors, however, only partially capture the shape variability of cortical folds. Here, we compare 56 regional self-supervised deep learning representations of cortical folds with classical sulcal morphometry via multivariate genome-wide association studies (GWAS) in 35,940 UK Biobank participants. The learned representations identified 567 independent genome-wide significant loci, versus 162 for classical morphometry, 87% of which were also detected by our approach. More than half of these associations replicated in the independent Adolescent Brain Cognitive Development (ABCD) cohort. Gene, gene-set, BrainSpan and single-cell expression enrichment converge on a shared prenatal window of neurogenesis and morphogenesis; spatial gene-association maps recapitulate known regional expression gradients, including for NR2F1 . Together, these results establish self-supervised representations of cortical folding as a powerful phenotypic framework for the genetic study of neurodevelopment.
Open AccessSelf-supervised representations reveal the genetic architecture of human cortical folding
1 Cortical folding emerges during fetal development, is under genetic control, and remains stable throughout life, offering a lasting window into early neurodevelopment. Conventional morphometric descriptors, however, only partially capture the shape variability of cortical folds. Here, we compare 56 regional self-supervised deep learning representations of cortical folds with classical sulcal morphometry via multivariate genome-wide association studies (GWAS) in 35,940 UK Biobank participants. The learned representations identified 567 independent genome-wide significant loci, versus 162 for classical morphometry, 87% of which were also detected by our approach. More than half of these associations replicated in the independent Adolescent Brain Cognitive Development (ABCD) cohort. Gene, gene-set, BrainSpan and single-cell expression enrichment converge on a shared prenatal window of neurogenesis and morphogenesis; spatial gene-association maps recapitulate known regional expression gradients, including for NR2F1 . Together, these results establish self-supervised representations of cortical folding as a powerful phenotypic framework for the genetic study of neurodevelopment.
- 8 July 2026
- Published by Springer Nature
- p. 334-339
Phenotypic Profile of Subclinical Alcohol Use Disorder and Liver Cancer in Type 2 Diabetes
- 8 July 2026
- Published by Springer Nature
- p. 334-339
Phenotypic Profile of Subclinical Alcohol Use Disorder and Liver Cancer in Type 2 Diabetes
- Open Access
- 7 February 2026
- Published by Springer Nature in Journal of Neural Transmission
Decoding cortical folding with deep learning: toward neurodevelopmental biomarkers of psychiatric disorders
Cortical folding is primarily determined during prenatal and early postnatal brain development and remains relatively stable throughout life. Accumulating evidence suggests that psychiatric disorders, including schizophrenia (SCZ), Bipolar Disorder (BD), and Autism Spectrum Disorder (ASD), result from intricate interactions between early neurodevelopmental disruptions and subsequent environmental influences. Therefore, cortical folding patterns are promising candidates as stable imaging biomarkers reflecting the neurodevelopmental component of psychiatric conditions. This study aims to demonstrate that deep learning can be used to learn meaningful representations of cortical folding patterns that enable the individual-level prediction of major psychiatric disorders, namely SCZ, BD, and ASD. We introduce a dedicated deep learning architecture leveraging self-supervised pre-training on large datasets of the general population to extract subject-level representations of cortical folding from structural magnetic resonance imaging (MRI) data. We demonstrate that the learned representations allow significant single-subject prediction of clinical status for SCZ, BD, and ASD. The proposed folding-based representation presents a novel approach for identifying imaging biomarkers related to the neurodevelopmental origins of psychiatric disorders. It opens the possibility of inferring early-life brain alterations from adult MRI data, offering potential tools for stratification and precision psychiatry.
- 7 February 2026
- Published by Springer Nature in Journal of Neural Transmission
Open AccessDecoding cortical folding with deep learning: toward neurodevelopmental biomarkers of psychiatric disorders
Cortical folding is primarily determined during prenatal and early postnatal brain development and remains relatively stable throughout life. Accumulating evidence suggests that psychiatric disorders, including schizophrenia (SCZ), Bipolar Disorder (BD), and Autism Spectrum Disorder (ASD), result from intricate interactions between early neurodevelopmental disruptions and subsequent environmental influences. Therefore, cortical folding patterns are promising candidates as stable imaging biomarkers reflecting the neurodevelopmental component of psychiatric conditions. This study aims to demonstrate that deep learning can be used to learn meaningful representations of cortical folding patterns that enable the individual-level prediction of major psychiatric disorders, namely SCZ, BD, and ASD. We introduce a dedicated deep learning architecture leveraging self-supervised pre-training on large datasets of the general population to extract subject-level representations of cortical folding from structural magnetic resonance imaging (MRI) data. We demonstrate that the learned representations allow significant single-subject prediction of clinical status for SCZ, BD, and ASD. The proposed folding-based representation presents a novel approach for identifying imaging biomarkers related to the neurodevelopmental origins of psychiatric disorders. It opens the possibility of inferring early-life brain alterations from adult MRI data, offering potential tools for stratification and precision psychiatry.
- Open Access
- 5 November 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
A self-supervised learning framework for discovering cortical folding patterns under genetic influence: Application to the Anterior Cingulate Cortex
Cortical folding patterns can serve as a macroscopic probe for hidden events that occur during the development of the human brain. However, the large inter-individual variability of these patterns makes them very difficult to associate with developmental pathologies. We propose a framework for discovering candidate patterns under genetic influence and illustrate its use in the anterior cingulate cortex region, where the paracingulate sulcus shapes have aroused interest in psychiatry. This framework is based on a comprehensive regional representation of fold variability inferred from a self-supervised deep learning algorithm applied to 36,000 white British ancestry subjects from the UK Biobank database. This representation can be used to train linear classification models, in order to learn to discern folding patterns from labeled databases and generalize to larger databases. In our case, the generalization of paracingulate sulcus labeling on UK BioBank subjects did not lead to clear genetic associations. Secondly, we show that new loci associated with cortical folding patterns can be discovered directly from the representation. We find in the discovery cohort 4 loci for the right hemisphere and 10 loci for the left hemisphere related to specific folding patterns of the anterior cingulate cortex (p<5×10−8). Even if only one locus is replicated on a smaller cohort of non white British ancestry subjects, many of the discovered loci have already been associated with brain anatomy or psychiatry.
- 5 November 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
Open AccessA self-supervised learning framework for discovering cortical folding patterns under genetic influence: Application to the Anterior Cingulate Cortex
Cortical folding patterns can serve as a macroscopic probe for hidden events that occur during the development of the human brain. However, the large inter-individual variability of these patterns makes them very difficult to associate with developmental pathologies. We propose a framework for discovering candidate patterns under genetic influence and illustrate its use in the anterior cingulate cortex region, where the paracingulate sulcus shapes have aroused interest in psychiatry. This framework is based on a comprehensive regional representation of fold variability inferred from a self-supervised deep learning algorithm applied to 36,000 white British ancestry subjects from the UK Biobank database. This representation can be used to train linear classification models, in order to learn to discern folding patterns from labeled databases and generalize to larger databases. In our case, the generalization of paracingulate sulcus labeling on UK BioBank subjects did not lead to clear genetic associations. Secondly, we show that new loci associated with cortical folding patterns can be discovered directly from the representation. We find in the discovery cohort 4 loci for the right hemisphere and 10 loci for the left hemisphere related to specific folding patterns of the anterior cingulate cortex (p<5×10−8). Even if only one locus is replicated on a smaller cohort of non white British ancestry subjects, many of the discovered loci have already been associated with brain anatomy or psychiatry.
- 22 June 2025
- Published by Springer Nature
- p. 218-223
AI-Driven Identification of Subclinical Alcohol Use Disorder in Type 2 Diabetes Patients
- 22 June 2025
- Published by Springer Nature
- p. 218-223
AI-Driven Identification of Subclinical Alcohol Use Disorder in Type 2 Diabetes Patients
- Open Access
Self-supervised contrastive learning unveils cortical folding pattern linked to prematurity
Brain folding patterns have been reported to carry clinically relevant information. The brain folds mainly during the last trimester of pregnancy, and the process might be durably disturbed by preterm birth. Yet little is known about preterm-specific patterns. In this work, we train a self-supervised model (SimCLR) on the UKBioBank cohort (21070 adults) to represent the right superior temporal sulcus (STS) region and apply it to sulci images of 374 babies from the dHCP database, containing preterms and full-terms, and acquired at 40 weeks post-menstrual age. We find a lower variability in the preterm embeddings, supported by the identification of a knob pattern, missing in the extremely preterm population.
Open AccessSelf-supervised contrastive learning unveils cortical folding pattern linked to prematurity
Brain folding patterns have been reported to carry clinically relevant information. The brain folds mainly during the last trimester of pregnancy, and the process might be durably disturbed by preterm birth. Yet little is known about preterm-specific patterns. In this work, we train a self-supervised model (SimCLR) on the UKBioBank cohort (21070 adults) to represent the right superior temporal sulcus (STS) region and apply it to sulci images of 374 babies from the dHCP database, containing preterms and full-terms, and acquired at 40 weeks post-menstrual age. We find a lower variability in the preterm embeddings, supported by the identification of a knob pattern, missing in the extremely preterm population.
- 15 September 2022
- Published by Springer Nature
- p. 77-87
Unsupervised Representation Learning of Cingulate Cortical Folding Patterns
- 15 September 2022
- Published by Springer Nature
- p. 77-87
Unsupervised Representation Learning of Cingulate Cortical Folding Patterns
- Open Access
- 28 August 2022
- Published by Wiley in Advanced Optical Materials
- Vol. 11 (13)
High Brightness, Highly Directional Organic Light‐Emitting Diodes as Light Sources for Future Light‐Amplifying Prosthetics in the Optogenetic Management of Vision Loss
Optogenetic control of retinal cells transduced with light‐sensitive channelrhodopsins can enable restoration of visual perception in patients with vision loss. However, a light intensity orders of magnitude higher than ambient light conditions is required to achieve robust cell activation. Relatively bulky wearable light amplifiers are currently used to deliver sufficient photon flux (>1016 photons/cm2/s in a ±10° emission cone) at a suitable wavelength (e.g., 600 nm for channelrhodopsin ChrimsonR). Here, ultrahigh brightness organic light‐emitting diodes (OLEDs) with highly directional emission are developed, with the ultimate aim of providing high‐resolution optogenetic control of thousands of retinal cells in parallel from a compact device. The orange‐emitting phosphorescent OLEDs use doped charge transport layers, generate narrowband emission peaking at 600 nm, and achieve a luminance of 684 000 cd m–2 at 15 V forward bias. In addition, tandem‐stack OLEDs with a luminance of 1 152 000 cd m–2 and doubled quantum efficiency are demonstrated, which greatly reduces electrical and thermal stress in these devices. At the photon flux required to trigger robust neuron firing in genetically modified retinal cells and when using heat sinking and realistic duty cycles (20% at 12.5 Hz), the tandem‐stack OLEDs therefore show a greatly improved half‐brightness lifetime of 800 h.
- 28 August 2022
- Published by Wiley in Advanced Optical Materials
- Vol. 11 (13)
Open AccessHigh Brightness, Highly Directional Organic Light‐Emitting Diodes as Light Sources for Future Light‐Amplifying Prosthetics in the Optogenetic Management of Vision Loss
Optogenetic control of retinal cells transduced with light‐sensitive channelrhodopsins can enable restoration of visual perception in patients with vision loss. However, a light intensity orders of magnitude higher than ambient light conditions is required to achieve robust cell activation. Relatively bulky wearable light amplifiers are currently used to deliver sufficient photon flux (>1016 photons/cm2/s in a ±10° emission cone) at a suitable wavelength (e.g., 600 nm for channelrhodopsin ChrimsonR). Here, ultrahigh brightness organic light‐emitting diodes (OLEDs) with highly directional emission are developed, with the ultimate aim of providing high‐resolution optogenetic control of thousands of retinal cells in parallel from a compact device. The orange‐emitting phosphorescent OLEDs use doped charge transport layers, generate narrowband emission peaking at 600 nm, and achieve a luminance of 684 000 cd m–2 at 15 V forward bias. In addition, tandem‐stack OLEDs with a luminance of 1 152 000 cd m–2 and doubled quantum efficiency are demonstrated, which greatly reduces electrical and thermal stress in these devices. At the photon flux required to trigger robust neuron firing in genetically modified retinal cells and when using heat sinking and realistic duty cycles (20% at 12.5 Hz), the tandem‐stack OLEDs therefore show a greatly improved half‐brightness lifetime of 800 h.
- 21 September 2021
- Published by Springer Nature
- p. 63-72
Detection of Abnormal Folding Patterns with Unsupervised Deep Generative Models
- 21 September 2021
- Published by Springer Nature
- p. 63-72
Detection of Abnormal Folding Patterns with Unsupervised Deep Generative Models
- 1 July 2013
- Published by IOP Publishing in Journal of Instrumentation
- Vol. 8 (07) , P07003
Sub-nanosecond clock synchronization and trigger management in the nuclear physics experiment AGATA
The new-generation spectrometer AGATA, the Advanced GAmma Tracking Array, requires sub-nanosecond clock synchronization among readout and front-end electronics modules that may lie hundred meters apart. We call GTS (Global Trigger and Synchronization System) the infrastructure responsible for precise clock synchronization and for the trigger management of AGATA. It is made of a central trigger processor and nodes, connected in a tree structure by means of optical fibers operated at 2Gb/s. The GTS tree handles the synchronization and the trigger data flow, whereas the trigger processor analyses and eventually validates the trigger primitives centrally. Sub-nanosecond synchronization is achieved by measuring two different types of round-trip times and by automatically correcting for phase-shift differences. For a tree of depth two, the peak-to-peak clock jitter at each leaf is 70 ps; the mean phase difference is 180 ps, while the standard deviation over such phase difference, namely the phase equalization repeatability, is 20 ps. The GTS system has run flawlessly for the two-year long AGATA campaign, held at the INFN Legnaro National Laboratories, Italy, where five triple clusters of the AGATA sub-array were coupled with a variety of ancillary detectors.
- 1 July 2013
- Published by IOP Publishing in Journal of Instrumentation
- Vol. 8 (07) , P07003
Sub-nanosecond clock synchronization and trigger management in the nuclear physics experiment AGATA
The new-generation spectrometer AGATA, the Advanced GAmma Tracking Array, requires sub-nanosecond clock synchronization among readout and front-end electronics modules that may lie hundred meters apart. We call GTS (Global Trigger and Synchronization System) the infrastructure responsible for precise clock synchronization and for the trigger management of AGATA. It is made of a central trigger processor and nodes, connected in a tree structure by means of optical fibers operated at 2Gb/s. The GTS tree handles the synchronization and the trigger data flow, whereas the trigger processor analyses and eventually validates the trigger primitives centrally. Sub-nanosecond synchronization is achieved by measuring two different types of round-trip times and by automatically correcting for phase-shift differences. For a tree of depth two, the peak-to-peak clock jitter at each leaf is 70 ps; the mean phase difference is 180 ps, while the standard deviation over such phase difference, namely the phase equalization repeatability, is 20 ps. The GTS system has run flawlessly for the two-year long AGATA campaign, held at the INFN Legnaro National Laboratories, Italy, where five triple clusters of the AGATA sub-array were coupled with a variety of ancillary detectors.