Metraipolis › archive › dc_29e644168efb

Representation learning of human cortical folding to reveal long lasting neurodevelopmental signatures — arXiv:2609.05438

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05438
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:32.983Z
SHA-256 of the archived text
60bb21208b3851af32a65a6e415a7d61be3b2ce3c7d002158a2293d850d35018
Stable URL of this page
https://metraipolis.com/documento/dc_29e644168efb

How to cite

Representation learning of human cortical folding to reveal long lasting neurodevelopmental signatures — arXiv:2609.05438 — arXiv (en), https://arxiv.org/abs/2609.05438 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29e644168efb (Metraipolis archive dc_29e644168efb, sha256 60bb21208b3851af32a65a6e415a7d61be3b2ce3c7d002158a2293d850d35018)
BibTeX
@misc{dc29e644168efb,
  title = {Representation learning of human cortical folding to reveal long lasting neurodevelopmental signatures — arXiv:2609.05438},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05438},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29e644168efb; sha256 60bb21208b3851af32a65a6e415a7d61be3b2ce3c7d002158a2293d850d35018},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05438. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Quantitative Methods (q-bio.QM) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.05438 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:39:43.101Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).