Optimized multi-scale entropy to localize epileptogenic hemisphere of temporal lobe epilepsy based on resting-state functional magnetic resonance imaging.
10.7507/1001-5515.202011048
- Author:
Chong XIE
1
;
Manling GE
1
;
Xiaoxuan FU
1
;
Shenghua CHEN
1
;
Fuyi ZHANG
1
;
Zhitong GUO
1
;
Zhiqiang ZHANG
2
Author Information
1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, P.R.China.
2. Department of Medical Imaging, Jinling Hospital, Nanjing University School of Medicine/General Hospital of Eastern Theater, Nanjing 210002, P.R.China.
- Publication Type:Journal Article
- Keywords:
epileptogenic hemisphere;
multi-scale entropy;
resting-state functional magnetic resonance imaging;
support vector machine;
temporal lobe epilepsy
- MeSH:
Brain/diagnostic imaging*;
Brain Mapping;
Entropy;
Epilepsy, Temporal Lobe/diagnostic imaging*;
Humans;
Magnetic Resonance Imaging
- From:
Journal of Biomedical Engineering
2021;38(6):1163-1172
- CountryChina
- Language:Chinese
-
Abstract:
Entropy model is widely used in epileptic electroencephalogram (EEG) analysis, but there are few reports on how to objectively select the parameters to compute the entropy model in the analysis of resting-state functional magnetic resonance imaging (rfMRI). Therefore, an optimization algorithm to confirm the parameters in multi-scale entropy (MSE) model was proposed, and the location of epileptogenic hemisphere was taken as an example to test the optimization effect by supervised machine learning. The rfMRI data of 20 temporal lobe epilepsy (TLE) patients with hippocampal sclerosis, positive on structural magnetic resonance imaging, were divided into left and right groups. Then, the parameters in MSE model were optimized by the receiver operating characteristic curves (ROC) and area under ROC curve (AUC) values in sensitivity analysis, and the entropy value of the brain regions with statistically significant difference between the groups were taken as sensitive features to epileptogenic hemisphere lateral. The optimized entropy values of these bio-marker brain areas were considered as feature vectors input into the support vector machine (SVM). Finally, combining optimized MSE model with SVM could accurately distinguish epileptogenic hemisphere in TLE at an average accuracy rate of 95%, which was higher than the current level. The results show that the MSE model parameter optimization algorithm can accurately extract the functional imaging markers sensitive to the epileptogenic hemisphere, and achieve the purpose of objectively selecting the parameters for MSE in rfMRI, which provides the basis for the application of entropy in advanced technology detection.
