文献类型：期刊文献

英文题名：Automatic detection of interictal epileptiform discharges based on time-series sequence merging method

作者：Zhang, Jian[1];Zou, Junzhong[1];Wang, Min[1];Chen, Lanlan[1];Wang, Chunmei[2];Wang, Guisong[3]

机构：[1]E China Univ Sci & Technol, Sch Informat Sci & Engn, Dept Automat, Shanghai 200237, Peoples R China;[2]Shanghai Normal Univ, Dept Elect Engn, Shanghai 200234, Peoples R China;[3]Shanghai Jiao Tong Univ, Renji Hosp, Dept Neurosurg, Shanghai 200233, Peoples R China

年份：2013

卷号：110

起止页码：35

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20131616215064);WOS:【SCI-EXPANDED(收录号:WOS:000318457700005)】；

基金：This work is partly supported by Fundamental Research Funds for the Central Universities WH1114028 and National Natural Science Foundation of China, No. 61201124.

语种：英文

外文关键词：Merger of increasing and decreasing sequences (MIDS); Epileptic EEG; Automatic detection; Support vector machine

摘要：This paper proposes a new automatic detection method of Interictal Epileptiform Discharges (IED) based on the merger of the increasing and decreasing sequences (MIDS) to improve IED detection rate. Firstly, increasing and decreasing sequences as well as complete and incomplete waves are reviewed to highlight the characteristics of clinical visual detection of IED. The sequence merging rules and algorithms are consequently proposed for time-domain electroencephalogram (EEG) signals. Experimental results demonstrate that the performance MIDS detection on rhythm waves and slow waves are very close to clinical visual detection. Secondly, the MIDS detection method is applied to IED fragments according to LED features in the time-domain. The results show that most IED fragments are recognized, although with some false detection of non-IED fragments. To reduce such false detection rate, Support Vector Machine (SVM) was applied with 17 characteristics and a training over 232 fragments from 3 patients' EEG recordings. With the SVM improvement, out-of-sample clinical EEG recordings of 32 suspected epilepsy patients were analyzed and 95.9% of the LED fragments marked by clinicians were successfully detected. The results show that the proposed algorithm performs well in IED detection and is a promising candidate in assisting clinicians' epilepsy diagnosis. (C) 2013 Elsevier B.V. All rights reserved.