Extraction of One Time Point Dynamic Group Features via Tucker Decomposition of Multi-subject FMRI Data: Application to Schizophrenia

Group temporal and spatial features of multi-subject fMRI data are essential for studying mental disorders, especially those exhibiting dynamic properties of brain function. Taking advantages of a low-rank Tucker model in effectively extracting temporally and spatially shared features of multi-subject fMRI data, we propose to extract dynamic group features via Tucker decomposition for identifying patients with schizophrenia (SZs) from healthy controls (HCs). We segment multi-subject fMRI data using sliding-window technique with different lengths and step size of one time point, and analyze amplitude of low frequency fluctuations and voxel features for shared time courses and shared spatial maps obtained by Tucker decomposition of segmented data. Results of two-sample t-tests show that HCs have higher amplitudes of low frequency fluctuations within 0.01–0.08 Hz than SZs within window length of 40 s–160 s, and significant HC-SZ activation differences exist in such as the inferior parietal lobule and left part of auditory within 40 s window, providing new evidence for analyzing schizophrenia.