| Title: | SF-DisenNet: Self-Supervised Function-Guided Disentanglement for Fine-Tuning-Free Brain Representation |
| Journal: | IEEE Transactions on Medical Imaging |
| Published: | 26 Aug 2026 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/42647690/ |
| DOI: | https://doi.org/10.1109/tmi.2026.3727625 |
Publication 21142
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Neuroimaging AI remains constrained by a model-per-disease paradigm-where separate frameworks are trained for individual disorders-limiting knowledge transfer and direct cross-disorder comparisons. While resting-state fMRI provides a powerful subject-specific functional connectivity (FC) fingerprint, it suffers from low spatial resolution and limited clinical accessibility. Conversely, structural MRI (sMRI) is widely available and spatially detailed, yet existing representations typically rely on predefined features or disease labels, failing to explicitly encode the individual-level functional organization.We propose SF-DisenNet, a self-supervised framework that uses each subject's own FC matrix as a neurobiological supervision signal to learn function-aligned sMRI representations without disease labels. A ResNet-DC patch encoder and an atlas-guided Anatomical Mapping Unit (AMU) aggregate local patches into AAL-90 regional embeddings, whose pairwise relationships define a representation-based structural connectivity (SC) matrix aligned with the subject's FC. An independence regularization further promotes spatially disentangled regional representations. After one pretraining stage on UK Biobank, the encoder is transferred to downstream tasks without further updating. SF-DisenNet achieves 95.1% cross-modal fingerprint matching between sMRI-derived SC and fMRI-derived FC. The AMU exhibits emergent hemispheric lateralization across all 45 AAL-90 anatomical pairs with a median effective patch count close to one. On longitudinal ADNI data, the structural fingerprint achieves 83.5% 24-month re-identification accuracy; its drift (ΔSC) is 2.1× larger in mismatched subjects and correlates with hippocampal atrophy rate. Ultimately, this unified feature space supports fine-tuning-free transfer to AD/MCI, ASD, PD, and SWEDD tasks, enabling cross-disorder analysis within a single sMRI framework. The source code is available at https://github.com/k-Jayus/BRAIN.</p>
6 Authors
- Kaixiang Shu
- Ronglin Zhang
- Jiaqiang Li
- Xuegang Song
- Tianfu Wang
- Baiying Lei
Enabling scientific discoveries that improve human health