eduzhai > Applied Sciences > Engineering >

Dynamic Functional Connectivity and Graph Convolution Network for Alzheimers Disease Classification

  • Save

... pages left unread,continue reading

Document pages: 4 pages

Abstract: Alzheimer s disease (AD) is the most prevalent form of dementia. Traditionalmethods cannot achieve efficient and accurate diagnosis of AD. In this paper,we introduce a novel method based on dynamic functional connectivity (dFC) thatcan effectively capture changes in the brain. We compare and combine fourdifferent types of features including amplitude of low-frequency fluctuation(ALFF), regional homogeneity (ReHo), dFC and the adjacency matrix of differentbrain structures between subjects. We use graph convolution network (GCN) whichconsider the similarity of brain structure between patients to solve theclassification problem of non-Euclidean domains. The proposed method s accuracyand the area under the receiver operating characteristic curve achieved 91.3 and 98.4 . This result demonstrated that our proposed method can be used fordetecting AD.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×