arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.05438q-bio.QMcs.CVcs.LG

人类大脑皮层折叠的表征学习揭示持久的神经发育特征

Representation learning of human cortical folding to reveal long lasting neurodevelopmental signatures

  • Université Paris-Saclay(巴黎萨克雷大学)
  • CEA(法国原子能和替代能源委员会)
  • CNRS(法国国家科学研究中心)
  • Institut Polytechnique de Paris(巴黎理工学院)
  • Télécom Paris(巴黎电信学院)
  • Geisinger Autism and Developmental Medicine Institute(盖辛格自闭症与发育医学研究所)
  • National Institute of Mental Health Intramural Research Program(美国国家精神卫生研究所院内研究项目)
  • University of Cambridge(剑桥大学)
  • A.J. Drexel Autism Institute(A.J.德雷克塞尔自闭症研究所)
  • Drexel University(德雷克塞尔大学)
  • GHU Paris(巴黎大学医院集团)
  • INSERM(法国国家健康与医学研究院)
  • Université Paris Cité(巴黎西岱大学)

机构由 AI 辅助整理,请以论文原文为准。

Julien Laval, Robin Guiavarch, Antoine Dufournet, Racim Menasria, Barthélémy Drabczuk, Cristobal Mendoza, Saeb Tounsi, Chikh Abdelghani Baroud, Merieme Bourenan… 展开作者

Julien Laval, Robin Guiavarch, Antoine Dufournet, Racim Menasria, Barthélémy Drabczuk, Cristobal Mendoza, Saeb Tounsi, Chikh Abdelghani Baroud, Merieme Bourenane, Vanessa Troiani, William Snyder, Marisa A Patti, Mylène Moyal, Marion Plaze, Arnaud Cachia, Federica Santacroce, Giorgia Committeri, Claire Cury, Kevin De Matos, Olivier Colliot, Zhong Yi Sun, Clara Fischer, Vincent Frouin, Pietro Gori, Denis Rivière, Joël Chavas, Jean-François Mangin

AI总结:

提出自监督框架Champollion,从结构MRI学习皮层折叠的可解释局部表征,在基准测试中优于现有模型,并揭示与遗传及神经发育条件相关的折叠特征。

AI中文摘要:

人类大脑在子宫内折叠,主要发生在妊娠晚期。出生后不久,皮层折叠模式即建立并在此后保持稳定,使其成为有前景的早期神经发育标志物。然而,目前尚不清楚现有神经影像基础模型给出的表征是否能捕捉皮层折叠的变异性。在此,我们引入Champollion,一种自监督学习框架,可从结构MRI中学习皮层折叠的可解释局部表征。针对有代表性的折叠相关任务进行优化,Champollion能准确捕捉跨皮层区域和外部数据集的已知折叠模式。在一项综合基准测试中,它持续优于神经影像和通用基础模型。此外,Champollion比传统形态计量描述符揭示出更丰富的遗传关联,并识别出与不完全海马反转、早产和母亲吸烟相关的局部折叠特征。这些结果确立了皮层折叠作为丰富且很大程度上未被开发的神经发育信息来源,并说明了预处理和架构归纳偏置如何恢复当前通用基础模型忽视的具有生物学意义的信号。

英文摘要:

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.

↑