Functional connectivity derived from resting-state functional near infrared spectroscopy has gained attention of recent scholars because of its capability in providing valuable insight into intrinsic networks and various neurological disorders in a human brain. Several progressive methodologies in detecting resting-state functional connectivity patterns in functional near infrared spectroscopy, such as seed-based correlation analysis and independent component analysis as the most widely used methods, were adopted in previous studies. Although these two methods provide complementary information each other, the conventional seed-based method shows degraded performance compared to the independent component analysis-based scheme in terms of the sensitivity and specificity. In this study, artificial neural network and convolutional neural network were utilized in order to overcome the performance degradation of the conventional seed-based method. First of all, the results of artificial neural network- and convolutional neural network-based method illustrated the superior performance in terms of specificity and sensitivity compared to both conventional approaches. Second, artificial neural network, convolutional neural network, and independent component analysis methods showed more robustness compared to seed-based method. Moreover, resting-state functional connectivity patterns derived from artificial neural network- and convolutional neural network-based methods in sensorimotor and motor areas were consistent with the previous findings. The main contribution of the present work is to emphasize that artificial neural network as well as convolutional neural network can be exploited for a high-performance seed-based method to estimate the temporal relation among brain networks during resting state.
Explainable Convolutional Neural Network to Investigate the Age-Related Changes in Multi-Order Functional Connectivity
