Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition
Open access

Self-supervised representations reveal the genetic architecture of human cortical folding

Antoine Dufournet Julien Laval J. Chavas C. Fisher Denis Rivière Vincent Frouin Jean-François Mangin
Jul 2026 · bioRxiv · 0 citations · 65 references
Biology Medicine

TL;DR

Self-supervised representations of cortical folding are established as a powerful phenotype for the genetic study of neurodevelopment through multivariate genome-wide association studies (GWAS).

DOI PubMed Semantic Scholar
Read PDF

Similar papers

Open access Sep 2026

Motifs of brain cortical folding from birth to adulthood

This study uses Multimodal Surface Matching with Hierarchical Templates (MSM-HT), a hierarchical surface registration, to parse cortical folding patterns into a representative family of distinct anatomical templates, offering a robust framework to generalise the uncovered cortical folding motifs across datasets and dev...

You-Rong Guo, Mohamed A. Suliman, L. Williams et al. · 0 citations
Open access Aug 2026

Genome-wide analysis of subcortical aging identifies a spatially structured pattern of genetic associations.

This work presents the first genome-wide association study (GWAS) of subcortical LBA, estimated using a deep neural network applied to T1-weighted MRI scans from 41,957 cognitively normal participants in the UK Biobank, and identifies 14 significant single-nucleotide polymorphisms across nine independent loci.

Nicholas J. Kim, Ayati Mishra, Jeremy S Yu et al. · 0 citations
Open access Jul 2026

An interpretable omnigenic neural network architecture for the human genome

Genetic prediction of complex phenotypes typically relies on additive linear models, which scale well but cannot capture non-additive effects or deeply integrate molecular and clinical data. Domain-specific neural networks have driven advances in images, text, and other modalities, but genome-scale neural networks rema...

J. Upmeier zu Belzen, L. Arnoldt, N. Hollmann et al. · 0 citations
Open access Sep 2026

Field-of-view confounding shapes genetic discovery from self-supervised cardiac-imaging phenotypes

Video masked-autoencoder training identified new associated loci beyond those detected using supervised phenotypes at matched sample size, which shared genetic architecture selectively with cardiac-conduction traits and were localised to cardiac structures within the imaged field of view.

D. Pandey, V. Narasimhan · 0 citations
Jul 2026

Cortical Hub Vulnerability and Molecular Signatures of Sulcal Widening in Schizophrenia.

These findings demonstrate that aberrant cortical folding in schizophrenia is constrained by network topology and molecular architecture, and establishes sulcal morphology as a mechanistically grounded biomarker that may help differentiate the neurodevelopmental trajectories of psychiatric disorders.

J. González-Peñas, H. Schnack, Carmen Rueda Hernández et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.