Journal Article

Sparsity‐guided multiple functional connectivity patterns for classification of schizophrenia via convolutional network

Bian, Lingbin, Shen, Dinggang, Yu, Renping, Pan, Cong, Fei, Xuan, Chen, Mingming

2023

Overview

The explorations of brain functional connectivity network (FCN) using resting‐state functional magnetic resonance imaging can provide crucial insights into discriminative analysis of neuropsychiatric disorders, such as schizophrenia (SZ). Pearson's correlation (PC) is widely used to construct a densely connected FCN which may overlook some complex interactions of paired regions of interest (ROIs) under confounding effect of other ROIs. Although the method of sparse representation takes into account this issue, it penalizes each edge equally, which often makes the FCN look like a random network. In this paper, we establish a new framework, called convolutional neural network with sparsity‐guided multiple functional connectivity, for SZ classification. The framework consists of two components. (1) The first component constructs a sparse FCN by integrating PC and weighted sparse representation (WSR). The FCN retains the intrinsic correlation between paired ROIs, and eliminates false connection simultaneously, resulting in sparse interactions among multiple ROIs with the confounding effect regressed out. (2) In the second component, we develop a functional connectivity convolution to learn discriminative features for SZ classification from multiple FCNs by mining the joint spatial mapping of FCNs. Finally, an occlusion strategy is employed to explore the contributive regions and connections, to derive the potential biomarkers in identifying associated aberrant connectivity of SZ. The experiments on SZ identification verify the rationality and advantages of our proposed method. This framework also can be used as a diagnostic tool for other neuropsychiatric disorders. We first propose sparsity‐guided multiple functional connectivity patterns, by integrating Pearson's correlation and connectivity strength‐weighted sparse representation. Then an improved convolutional neural network module is introduced to learn the discriminative features of brain networks with different sparsity and the occlusion method is used to find potential biomarkers related to schizophrenia. The experimental results from the Center of Biomedical Research Excellence database demonstrate the promising performance of our method.

• Publisher: John Wiley & Sons, Inc
• Subject: Alzheimer's disease / Artificial neural networks / Biomarkers / Biomedical research / Brain / Brain diseases / Brain mapping / Brain Mapping - methods / Brain research / Cerebral blood flow / Classification / Cognitive ability / convolutional neural network / Datasets / Deep learning / Disorders / Drug abuse / Functional magnetic resonance imaging / Head injuries / Humans / Ischemia / Magnetic resonance imaging / Magnetic Resonance Imaging - methods / Medical diagnosis / Mental disorders / multiple sparse patterns learning / Neural networks / Neural Pathways - diagnostic imaging / Neuroimaging / Occlusion / Physiology / Representations / resting‐state functional MRI / Schizophrenia / Sparsity / Teaching methods / Time series / weighted sparse functional connectivity