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.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Click here for more information on becoming a member.
