Hybrid Functional Brain Network With First-Order and Second-Order Information for Computer-Aided Diagnosis of Schizophrenia

Brain functional connectivity network (BFCN) analysis has been widely used in the diagnosis of mental disorders, such as schizophrenia. In BFCN methods, brain network construction is one of the core tasks due to its great influence on the diagnosis result. Most of the existing BFCN construction methods only consider the first-order relationship existing in each pair of brain regions and ignore the useful high-order information, including multi-region correlation in the whole brain. Some early schizophrenia patients have subtle changes in brain function networks, which cannot be detected in conventional BFCN construction methods. It is well-known that the high-order method is usually more sensitive to the subtle changes in signal than the low-order method. To exploit high-order information among brain regions, we define the triplet correlation among three brain regions, and derive the second-order brain network based on the connectivity difference and ordinal information in each triplet. For making full use of the complementary information in different brain networks, we proposed a hybrid approach to fuse the first- and second-order brain networks. The proposed method is applied to identify the biomarkers of schizophrenia. The experimental results on six schizophrenia datasets (totally including 439 patients and 426 controls) show that the proposed method outperforms the existing brain network methods in the diagnosis of schizophrenia.