Abstract #0227
Multimodal imaging classification of ADHD: brain functional connectivity and cortical thickness
Po-Hsiang Chan 1 , Yu-Sheng Tseng 1 , Chun-jung Chen 1 , Teng-Yi Huang 1 , and Tzu-Chao Chuang 2
1
Department of Electrical Engineering,
National Taiwan University of Science and Technology,
Taipe, Taipei, Taiwan,
2
Department
of Electrical Engineering, National Sun Yat-Sen
University, Kaohsiung, Taiwan, R.O.C, Taipei, Taiwan
This study aims to develop a classification method based
on support vector machine (SVM) for attention deficit
hyperactivity disorder (ADHD) patients. We proposed to
use SVM to classify subject groups based on the brain
functional connectivity obtained from resting-state fMRI
datasets and brain cortical thickness obtained from 3D
T1 MPRAGE datasets. We identified that SVM classifier
did not perform well (accuracy of ~ 57%) if all the
available features were selected into SVM training.
Using the proposed feature selection approach, the
maximum accuracies increased to 68 V 99 %. The results
support that feature selection according to absolute
weightings of a pre-trained SVM hyperplane is an
efficient method to increase the classification
accuracies.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
