Interpretable Disorder Signatures: Probing Neural Latent Spaces for Schizophrenia, Alzheimer’s, and Autism Stratification
Time Reversal pretraining enhances both the performance and interpretability of deep learning models for fMRI classification. By enabling more stable and biologically plausible representations, TR pretraining supports clinically relevant insights into disorder-specific network disruptions. This study demonstrates the utility of interpretable self-supervised models in neuroimaging, offering a promising step toward transparent and trustworthy AI applications in psychiatry.
Authors
- Zening Fu (ORCID: https://orcid.org/0000-0002-1591-4900)
- Vince D. Calhoun (ORCID: https://orcid.org/0000-0001-9058-0747)
- Sergey Plis (ORCID: https://orcid.org/0000-0003-0040-0365)
- Md Mahfuzur Rahman (ORCID: https://orcid.org/0000-0002-4162-6152)
- Qasim Zia (ORCID: https://orcid.org/0009-0004-2028-5960)
- Pavel Popov (ORCID: https://orcid.org/0000-0002-6407-4098)
- Zafar Iqbal
Institutions
- Georgia State University (US)
- Center for Translational Research in Neuroimaging and Data Science (US)
Publication Details
- Journal
- Brain Sciences
- Published
- 2025-09-01
- DOI
- https://doi.org/10.3390/brainsci15090954
- Primary Topic
- Functional Brain Connectivity Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00