Weighted graph regularized sparse brain network construction for MCI identification

作者：

Highlights：

• Integrate the data similarity and locality to sparse modeling of brain functional network.

• A unified framework integrates intrinsic correlation, local manifold structure, and sparsity.

• Solve the controversial point of graph Laplacian in the self-representation model.

• MCI classification based on fMRI shows our method is more effective (accuracy = 88.89%).

摘要

•Integrate the data similarity and locality to sparse modeling of brain functional network.•A unified framework integrates intrinsic correlation, local manifold structure, and sparsity.•Solve the controversial point of graph Laplacian in the self-representation model.•MCI classification based on fMRI shows our method is more effective (accuracy = 88.89%).

论文关键词：Graph Laplacian regularization,Sparse representation,Brain functional network,Mild cognitive impairment (MCI)

论文评审过程：Received 17 August 2018, Revised 3 December 2018, Accepted 7 January 2019, Available online 8 January 2019, Version of Record 1 February 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.01.015