System and method for task-less mapping of brain activity

A computer-implemented method for mapping one or more brain resting state networks (RSNs) in a brain of an individual subject, the method comprising:

• (a) receiving, by a processor, measurements of a brain feature for the individual subject obtained by a magnetic resonance imaging device;
• (b) generating, by the processor, a region-wise connectivity matrix having connectivity values based on the received brain feature measurements for the individual subject, the region-wise connectivity matrix comprising an [n×m] matrix of connectivity values, wherein each connectivity value represents a measure of connectivity between different brain regions;
• and
• (c) producing at least one map of an RSN topography for the individual subject based at least in part on the region-wise connectivity matrix;
• wherein producing the at least one map of the RSN topography comprises at least one process of propagating the region-wise connectivity matrix through a trained machine learning model and generating a set of membership values or categorizations for each brain region;
• wherein the trained machine learning model has been calibrated using a plurality of calibration connectivity measurements corresponding to RSNs previously obtained from a plurality of calibration subjects;
• and
• wherein each membership value or categorization represents an estimate of each region's membership within at least one brain RSN.