Aug 2026
SF-DisenNet: Self-Supervised Function-Guided Disentanglement for Fine-Tuning-Free Brain Representation.
SF-DisenNet is proposed, 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, enabling cross-disorder analysis within a single sMRI framework.
Kai-Xiang Shu, Rongling Zhang, Jia-Qiang Li et al.
· IEEE Transactions on Medical... · 0 citations