Voxel-based morphometry analysis and machine learning based classification in pediatric mesial temporal lobe epilepsy wi
- PDF / 2,718,833 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 94 Downloads / 227 Views
ORIGINAL RESEARCH
Voxel-based morphometry analysis and machine learning based classification in pediatric mesial temporal lobe epilepsy with hippocampal sclerosis Shihui Chen 1 & Jian Zhang 2,3 & Xiaolei Ruan 4 & Kan Deng 1,3 & Jianing Zhang 1,3 & Dongfang Zou 5 & Xiaoming He 6 & Feng Li 6 & Guo Bin 1,3 & Hongwu Zeng 5 & Bingsheng Huang 1,3
# Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract Mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE-HS) is a common type of pediatric epilepsy. We sought to evaluate whether the combination of voxel-based morphometry (VBM) and support vector machine (SVM), a machine learning method, was feasible for the classification of MTLE-HS. Three-dimensional T1-weighted MRI was acquired in 37 participants including 22 with MTLE-HS (16 left, 6 right) and 15 healthy controls (HCs). VBM was used to detect the regions of gray matter volume (GMV) abnormalities. The volumes of these regions were then calculated for each participant and used as the features in SVM. The SVM model was trained and tested with leave-one-out cross validation (LOOCV). We performed VBM-based comparison and SVM-based classification between left HS (LHS) and HC as well as between right HS (RHS) and HC. Both GMV increase and reduction were found in the group comparisons with VBM. Using SVM, we reached an area under the receiver operating characteristic curve (AUC) of 0.870, 0.976 and 0.902 for the classification between LHS and HC, between RHS and HC and between HS and HC respectively. The VBM findings were concordant with the clinical findings. Thus, our proposed method combining VBM findings with SVM, were applicable in the classification of padiatric MTLE-HS with high accuracy. Keywords Voxel-based morphometry . Machine learning . Classification . Pediatric mesial temporal lobe epilepsy with hippocampal sclerosis
Introduction Mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE-HS) is the most common type of drug-resistant epilepsy
(Berg et al. 2010). An accuracy of about 75% for MTLE identification might be achieved with electroclinical grounds (Wieser 2004). Brain structural information provided by magnetic resonance imaging (MRI) has been proven valuable for
Shihui Chen and Jian Zhang: equal contribution, co-first authors. Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11682-019-00138-z) contains supplementary material, which is available to authorized users. * Hongwu Zeng [email protected] * Bingsheng Huang [email protected] 1
School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, People’s Republic of China
2
Health Science Centre, Shenzhen University, Shenzhen, Guangdong, People’s Republic of China
3
Shenzhen University Clinical Research Center for Neurological Diseases, Shenzhen, Guangdong, People’s Republic of China
4
Jiuquan Satellite Launch Center, Lanzhou, Gansu, People’s Republic of China
5
Department of Radiology, Shenzhen Children’s Hospital, Shenzhen,
Data Loading...
