Meeting Banner
Abstract #1375

Machine learning approach for lateralization of temporal lobe epilepsy utilizing DTI structural connectome

Kouhei Kamiya 1 , Yuichi Suzuki 2 , Shiori Amemiya 1 , Naoto Kunii 3 , Kensuke Kawai 4 , Harushi Mori 1 , Akira Kunimatsu 1 , Nobuhito Saito 3 , Shigeki Aoki 5 , and Kuni Ohtomo 1

1 Department of Radiology, The University of Tokyo, Bunkyo, Tokyo, Japan, 2 Department of Radiological Technology, The University of Tokyo Hospital, Bunkyo, Tokyo, Japan, 3 Department of Neurosurgery, The University of Tokyo, Bunkyo, Tokyo, Japan, 4 Department of Neurosurgery, NTT Medical Center Tokyo, Shinagawa, Tokyo, Japan, 5 Department of Radiology, Juntendo University School of Medicine, Bunkyo, Tokyo, Japan

This study aimed to investigate the utility of machine learning approach with DTI structural connectome for lateralization of epileptogenicity in TLE. DTI (b=0, 1000 s/mm2; 13 MPGs; 3mm iso-voxel) and 3D-T1WI were obtained in 41 patients with TLE (right/left 13/28). For each patient, an 83x83 connectome matrix was generated and graph theoretic regional network measures (degree, clustering coefficient, local efficiency, and betweeness centrality) were calculated. The regional measures were used to train the classifier using the sparse linear regression and support vector machine (SVM). SVM demonstrated excellent discrimination between left and right TLE, with 92.7% accuracy in leave-one-out cross validation.

This abstract and the presentation materials are available to members only; a login is required.

Join Here