Robust brain parcellation using sparse representation on resting-state fMRI.

Resting-state fMRI (rs-fMRI) has been widely used to segregate the brain into individual modules based on the presence of distinct connectivity patterns. Many parcellation methods have been proposed for brain parcellation using rs-fMRI, but their results have been somewhat inconsistent, potentially due to various types of noise. In this study, we provide a robust parcellation method for rs-fMRI-based brain parcellation, which constructs a sparse similarity graph based on the sparse representation coefficients of each seed voxel and then uses spectral clustering to identify distinct modules. Both the local time-varying BOLD signals and whole-brain connectivity patterns may be used as features and yield similar parcellation results. The robustness of our method was tested on both simulated and real rs-fMRI datasets. In particular, on simulated rs-fMRI data, sparse representation achieved good performance across different noise levels, including high accuracy of parcellation and high robustness to noise. On real rs-fMRI data, stable parcellation of the medial frontal cortex (MFC) and parietal operculum (OP) were achieved on three different datasets, with high reproducibility within each dataset and high consistency across these results. Besides, the parcellation of MFC was little influenced by the degrees of spatial smoothing. Furthermore, the consistent parcellation of OP was also well corresponding to cytoarchitectonic subdivisions and known somatotopic organizations. Our results demonstrate a new promising approach to robust brain parcellation using resting-state fMRI by sparse representation.