Representation learning of human cortical folding to reveal long lasting neurodevelopmental signatures
Year: 2026
Type: preprint
Abstract: The human brain folds in utero, primarily during late gestation. Shortly after birth, cortical folding patterns are established and remain stable thereafter, making them promising early neurodevelopmental markers. Yet it is unclear whether the representations given by current neuroimaging foundation models capture cortical folding variability. Here, we introduce Champollion, a self-supervised learning framework that learns interpretable local representations of cortical folding from structural MRI. Optimized on representative folding-related tasks, Champollion accurately captures known folding patterns across cortical regions and external datasets. In a comprehensive benchmark, it consistently outperforms neuroimaging and general-purpose foundation models. Furthermore, Champollion reveals richer genetic associations than conventional morphometric descriptors and identifies localized folding signatures associated with incomplete hippocampal inversion, prematurity, and maternal smoking. These results establish cortical folding as a rich and largely untapped source of neurodevelopmental information, and Champollion provides a unified framework for discovering, localizing and interpreting long lasting cortical folding signatures.
Source: PubMed
Authors: Laval, Julien, Guiavarch, Robin, Dufournet, Antoine, Menasria, Racim, Drabczuk, Barthélémy, Mendoza, Cristobal, Tounsi, Saeb, Baroud, Chikh Abdelghani, Bourenane, Merieme, Troiani, Vanessa, Snyder, William, Patti, Marisa A, Moyal, Mylène, Plaze, Marion, Cachia, Arnaud, Santacroce, Federica, Committeri, Giorgia, Cury, Claire, De Matos, Kevin, Colliot, Olivier, Sun, Zhong Yi, Fischer, Clara, Frouin, Vincent, Gori, Pietro, Rivière, Denis, Chavas, Joël, Mangin, Jean-François
Institutions: Centre National de la Recherche Scientifique, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Université Paris-Saclay, Building large instruments for neuroimaging: from population imaging to ultra-high magnetic fields, Télécom Paris, Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information, Maison de la Simulation, University of Cambridge, National Institute of Mental Health, Drexel University, Inserm, Institut de Psychiatrie et Neurosciences de Paris, Institut Universitaire de France, Université Paris Cité, University of Chieti-Pescara, Institut de Recherche en Informatique et Systèmes Aléatoires, Empenn, Université de Rennes, Sorbonne Université, Institut du Cerveau
Language: English
Field: Medicine
Domain: Health Sciences
Open Access status: green
Awards: G1190173965, G1258743643, G1584056304, Institut Robert-Debré du Cerveau de l’Enfant, PR[AI]RIE-PSAI - Paris School of Artificial Intelligence, G3103753459, G4510828401, Center for Artificial Intelligence and Quantum Computing in System Brain Research, Brain Health Trajectories, G7080048889, G7191615016, G7240651115, G7811813413, G8052140988
OpenAlex ID: W7206152134