A Multilayer Maximum Spanning Tree Kernel For Brain Networks

The brain network has been widely used for the construction of diverse brain disease diagnosis models. Among these models, an important and challenging task is how to quantify the network similarity. Although many graph kernels have been proposed for estimating topological similarity of a pair of networks, most of them ignore the global structure of networks by only focusing on subgraphs (i.e., a subset of original graph). To address this issue, we propose a novel multilayer graph kernel method based on maximum spanning tree (MST) for measuring the similarity of pair-wise brain networks. For two given networks, the proposed kernel estimates their similarity at each layer of MST generation to capture the topological properties of brain networks from local to global levels. Meanwhile, since the construction of MST is completely data-driven, MST based kernel can retain individual differences without destroying the individual inherent connectivity patterns. To validate our method, we apply our proposed graph kernel to the classifications of mild cognitive impairment (MCI). Experimental results demonstrate that our method outperforms the state-of-the-art graph kernel methods.