Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping

Hao-Chun Yang13, Ole Andreassen2, Lars Tjelta Westlye2
Andre F. Marquand3, Christian F. Beckmann3, Thomas Wolfers123
1Department of Psychiatry and Psychotherapy, Tübingen Center for Mental Health (TÜCMH), Germany, 2Norwegian Centre for Mental Disorders Research, Division of Mental Health and Addiction, Norway, 3Donders Institute for Brain, Cognition, and Behaviour, Radboud University, Netherlands
2024 IEEE International Symposium on Biomedical Imaging (ISBI24)
Paper Code arXiv
MY ALT TEXT

Cortical Anomaly detection through Masked image modeling (CAM) framework.

Abstract

The detection of heterogeneous mental disorders based on brain readouts remains challenging due to the complexity of symptoms and the absence of reliable biomarkers. This paper introduces CAM (Cortical Anomaly Detection through Masked Image Modeling), a novel self-supervised framework designed for the unsupervised detection of complex brain disorders using cortical surface features. We employ this framework for the detection of individuals on the psychotic spectrum and demonstrate its capabilities compared to state-of-the-art methods, achieving an AUC of 0.696 for Schizoaffective and 0.769 for Schizophreniform, without the need for any labels. Furthermore, the analysis of atypical cortical regions, including Pars Triangularis and several frontal areas often implicated in schizophrenia, provides further confidence in our approach. Altogether, we demonstrate a scalable approach for anomaly detection of complex brain disorders based on cortical abnormalities.

Poster

BibTeX

@article{yang2023learning,
      title={Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping},
      author={Yang, Hao-Chun and Andreassen, Ole and Westlye, Lars Tjelta and Marquand, Andre F and Beckmann, Christian F and
      Wolfers, Thomas},
      journal={arXiv preprint arXiv:2312.02762},
      year={2023}
}