Functional Magnetic Resonance Imaging (fMRI) provides useful insights into the brain function both during task or rest. Representing fMRI data using correlation matrices is found to be a reliable method of analyzing the inherent connectivity of the brain in the resting and active states. Graph Neural Networks (GNNs) have been widely used for brain network analysis due to their inherent explainability capability. In this work, we introduce a novel framework using contrastive self-supervised learning graph transformers, incorporating a brain network transformer encoder with random graph alterations. The proposed network leverages both contrastive learning and graph alterations to effectively train the graph transformer for autism detection. Our approach, tested on Autism Brain Imaging Data Exchange (ABIDE) data, demonstrates superior autism detection, achieving an AUROC of 82.6 and an accuracy of 74%, surpassing current state-of-the-art methods.

In this work, the authors describe the use of detrended partial cross correlation (DPCCA) as a quantity to capture short and long memory connections among brain recordings, for connectivity analysis. DPPCA is complemented with CCA to study the efficacy of detecting connectivity on simulated data (generated with NatSim), and compared to partial correlation and regularized inverse covriance (ICOV). On real fMRI data, DPCCA is first used together with PCA to show representative correlation profiles and perform dimensionality reduction (with Isomap (Iso) and autoencorder (AutoE)). Second, various combinations of DPCCA values and dimensionality reduction methods are used as feature for predicting cocaine dependent class from control. The paper is sufficiently well written and most parts is described in enough detail to reproduce the technical steps of the proposed methodology. I appreciate the use of DPCCA which is definitely new to the neuroimaging data analysis domain.

Brain connectivity analysis is a critical component of ongoing human connectome projects to decipher the healthy and diseased brain. Recent work has highlighted the power-law (multi-time scale) properties of brain signals; however, there remains a lack of methods to specifically quantify short- vs. long- time range brain connections. In this paper, using detrended partial cross-correlation analysis (DPCCA), we propose a novel functional connectivity measure to delineate brain interactions at multiple time scales, while controlling for covariates. We use a rich simulated fMRI dataset to validate the proposed method, and apply it to a real fMRI dataset in a cocaine dependence prediction task. We show that, compared to extant methods, the DPCCA-based approach not only distinguishes short and long memory functional connectivity but also improves feature extraction and enhances classification accuracy.