%0 Electronic Article
%A Schiffer, Christian
%A Boztoprak, Zeynep
%A Kropp, Jan-Oliver
%A Thönnißen, Julia
%A Berr, Katia
%A Spitzer, Hannah
%A Amunts, Katrin
%A Dickscheid, Timo
%T CytoNet: A Foundation Model for the Human Cerebral Cortex
%I arXiv
%M FZJ-2025-04528
%D 2025
%X To study how the human brain works, we need to explore the organization of the cerebral cortex and its detailed cellular architecture. We introduce CytoNet, a foundation model that encodes high-resolution microscopic image patches of the cerebral cortex into highly expressive feature representations, enabling comprehensive brain analyses. CytoNet employs self-supervised learning using spatial proximity as a powerful training signal, without requiring manual labelling. The resulting features are anatomically sound and biologically relevant. They encode general aspects of cortical architecture and unique brain-specific traits. We demonstrate top-tier performance in tasks such as cortical area classification, cortical layer segmentation, cell morphology estimation, and unsupervised brain region mapping. As a foundation model, CytoNet offers a consistent framework for studying cortical microarchitecture, supporting analyses of its relationship with other structural and functional brain features, and paving the way for diverse neuroscientific investigations.
%K Neurons and Cognition (q-bio.NC) (Other)
%K Artificial Intelligence (cs.AI) (Other)
%K Machine Learning (cs.LG) (Other)
%K FOS: Biological sciences (Other)
%K FOS: Computer and information sciences (Other)
%K I.2.6; I.2.10; I.4.7; I.5.1; I.5.4 (Other)
%F PUB:(DE-HGF)25
%9 Preprint
%R 10.48550/ARXIV.2511.01870
%U https://juser.fz-juelich.de/record/1048160