1. Epileptic focus localization based on entropy and convolutional neural network
Authors : Xuyang Zhao, Lihua Gui, Jianting Cao, Qibin Zhao
Pages : 14-17
DOI : http://dx.doi.org/10.21172/1.144.04
Keywords : EpilepsyLocalizationEntropyConvolutional Neural Network. Abstract :Focal location is a necessary step before surgery in epileptic patients and directly affects the outcome of the surgery. However, this is a time-consuming and difficult process for clinical experts. Recent researches have shown that we can use machine learning approaches to reduce the workload of the focal location. In this paper, we proposed a method for extracting features by calculating the entropy of the intracranial electroencephalogram (iEEG) and use a one- dimensional convolutional neural network (1D-CNN) for classification, in this way, we can automatically locate the epileptic foci. More specifically, because epilepsy is caused by abnormal discharge of brain cells, entropy is a very suitable evaluation method. Experimental results show that our approach is effective for epilepsy localization and got an average test accuracy of 85.6%.
Citing this Journal Article :Xuyang Zhao, Lihua Gui, Jianting Cao, Qibin Zhao, "Epileptic focus localization based on entropy and convolutional neural network", Volume 14 Issue 4 - October 2019, 14-17
Click here to Submit Copyright Takedown Notice for this article.