A0975
Title: Low-rank and sparse decomposition for brain functional connectivity in naturalistic fMRI data
Authors: Chee-Ming Ting - Monash University, Malaysia (Malaysia) [presenting]
Jeremy Skipper - University College London (United Kingdom)
Fuad Noman - Monash University Malaysia (Malaysia)
Steven Small - University of Texas at Dallas (United States)
Hernando Ombao - King Abdullah University of Science and Technology (KAUST) (Saudi Arabia)
Abstract: A novel, data-driven approach is presented, which is based on low-rank plus sparse (L+S) decomposition to isolate stimulus-driven dynamic changes in fMRI brain functional connectivity (FC) from the background noise by exploiting shared network structure among subjects receiving the same naturalistic stimuli. The time-resolved multi-subject FC matrices are modelled as a sum of a low-rank component of correlated FC patterns across subjects and a sparse component of subject-specific, idiosyncratic background activities. To recover the shared low-rank subspace, a fused version of principal component pursuit (PCP) is introduced by adding a fusion-type penalty on the differences between the rows of the low-rank matrix. The method improves the detection of stimulus-induced group-level homogeneity in the FC profile while capturing inter-subject variability. An efficient algorithm is developed via a linearized alternating direction method of multipliers to solve the fused PCP. Simulations show accurate recovery by the fused-PCP even when a large fraction of FC edges is severely corrupted. When applied to natural fMRI data, the method reveals FC changes that were time-locked to auditory processing during movie watching, with the dynamic engagement of sensorimotor systems for speech-in-noise. It also provides a better mapping to auditory content in the movie than ISC.
