TY  - EJOUR
AU  - Schiffer, Christian
AU  - Boztoprak, Zeynep
AU  - Kropp, Jan-Oliver
AU  - Thönnißen, Julia
AU  - Berr, Katia
AU  - Spitzer, Hannah
AU  - Amunts, Katrin
AU  - Dickscheid, Timo
TI  - CytoNet: A Foundation Model for the Human Cerebral Cortex
PB  - arXiv
M1  - FZJ-2025-04528
PY  - 2025
AB  - 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.
KW  - Neurons and Cognition (q-bio.NC) (Other)
KW  - Artificial Intelligence (cs.AI) (Other)
KW  - Machine Learning (cs.LG) (Other)
KW  - FOS: Biological sciences (Other)
KW  - FOS: Computer and information sciences (Other)
KW  - I.2.6; I.2.10; I.4.7; I.5.1; I.5.4 (Other)
LB  - PUB:(DE-HGF)25
DO  - DOI:10.48550/ARXIV.2511.01870
UR  - https://juser.fz-juelich.de/record/1048160
ER  -