Transfer Learning of fMRI Dynamics

As a mental disorder progresses, it may affect brain structu re, but brain function expressed in brain dynamics is affected much earlier. Captu ring the moment when brain dynamics express the disorder is crucial for early dia gnosis. The traditional approach to this problem via training classifiers either pro ceeds from handcrafted features or requires large datasets to combat the m n problem when a high dimensional fMRI volume only has a single label that carries le arning signal. Large datasets may not be available for a study of each disorder, or rare disorder types or subpopulations may not warrant for them. In this paper, w e demonstrate a self-supervised pre-training method that enables us to pre -train directly on fMRI dynamics of healthy control subjects and transfer the learn ing to much smaller datasets of schizophrenia. Not only we enable classificatio n of disorder directly based on fMRI dynamics in small data but also significantly sp eed up the learning when possible. This is encouraging evidence of informat ive transfer learning across datasets and diagnostic categories.