Exploring intrinsic functional differences of gyri, sulci and 2-hinge, 3-hinge joints on cerebral cortex

The human cerebral cortex has been commonly known as a highly-folded region which consists of convex gyri and concave sulci. Many previous studies have already revealed the fundamental differences of these convex and concave areas by analyzing structural and functional connectivity patterns. However, to our best knowledge, rare work has been done to explore their intrinsic functional differences from the perspective of neural activity, especially for 3-hinge gyral folding joints. Inspired by current evidences, in this paper, experiments based on classification models learned by convolutional neural network (CNN) are designed and performed on resting state functional magnetic resonance imaging (rsfMRI) data of both healthy controls and autism patients from the publicly available ABIDE II database. In our work, gyral and sulcal, 2-hinge and 3-hinge joint rsfMRI signals are modeled and predicted using CNNs with an average testing classification accuracy of 94.24% for controls, 95.24% for patients and 87.53% for controls, 87.72% for patients at individual level separately, which confirms different functional roles of neural activities under resting state in gyri and sulci, as well as 2-hinge and 3-hinge gyral folding joints in healthy subjects and autism groups. Besides, further analyses on learned characteristic features to differentiate gyral/sulcal, 2-hinge/3-hinge joint rsfMRI signals are also designed and performed to interpret our findings.