Wang Yuan, Ombao Hernando, Chung Moo K
Department of Biostatistics and Medical Informatics, UW Madison, U.S.A.
Department of Statistics, UC Irvine, U.S.A.
Proc IEEE Int Symp Biomed Imaging. 2015 Apr;2015:351-354. doi: 10.1109/ISBI.2015.7163885. Epub 2015 Jul 23.
We propose a seizure detection method for electroencephalographic (EEG) epilepsy data based on a novel multi-scale topological technique called persistent homology (PH). Among several PH descriptors, persistence landscape (PL) possesses many desirable properties for rigorous statistical inference. By building PLs on EEG epilepsy signals smoothed by a weighted Fourier series (WFS) expansion, we compared the before and during phases of a seizure attack in a patient diagnosed with left temporal epilepsy and successfully identified site T3 as the origin of the seizure attack.
我们基于一种名为持久同调（PH）的新型多尺度拓扑技术，提出了一种针对脑电图（EEG）癫痫数据的癫痫发作检测方法。在多个PH描述符中，持久景观（PL）具有许多用于严格统计推断的理想属性。通过在经加权傅里叶级数（WFS）展开平滑处理的EEG癫痫信号上构建PL，我们比较了一名被诊断为左颞叶癫痫患者癫痫发作前和发作期间的阶段，并成功将T3位点确定为癫痫发作的起源。
