Detecting abnormalities in resting-state dynamics: An unsupervised learning approach
This work addresses the challenge of abnormality detection in brain imaging for medical diagnosis, but it appears incremental as it applies existing unsupervised methods to a new context.
The paper tackled the problem of detecting abnormalities in resting-state fMRI data by exploring autoencoder and next frame prediction strategies to capture normal variability, and demonstrated their application in discriminating autism patients from healthy controls.
Resting-state functional MRI (rs-fMRI) is a rich imaging modality that captures spontaneous brain activity patterns, revealing clues about the connectomic organization of the human brain. While many rs-fMRI studies have focused on static measures of functional connectivity, there has been a recent surge in examining the temporal patterns in these data. In this paper, we explore two strategies for capturing the normal variability in resting-state activity across a healthy population: (a) an autoencoder approach on the rs-fMRI sequence, and (b) a next frame prediction strategy. We show that both approaches can learn useful representations of rs-fMRI data and demonstrate their novel application for abnormality detection in the context of discriminating autism patients from healthy controls.