Convolutional neural networks for real-time epileptic seizure detection
Convolutional neural networks for real-time epileptic seizure detection
复制标题
DOI：
10.1080/21681163.2016.1141062
复制
发表时间：
2018-01-01
影响因子：
1.6
通讯作者：
Navab, Nassir
中科院分区：
文献类型：
--
作者：
Achilles, Felix;Tombari, Federico;Navab, Nassir
癫痫发作是患者的一种严重的神经疾病，如果不治疗，会极大地降低他们的生活质量。早期正确的症状分析诊断是治疗和改善病情的主要途径。为了获得可靠和可量化的信息，医学专业人员在专门的癫痫监测单位使用昂贵的视频脑电系统进行癫痫发作检测和随后的分析。然而，癫痫发作的检测，特别是在困难的情况下，如被毯子堵塞或在没有预测性脑电模式的情况下，是高度主观的，因此应该得到自动化系统的支持。在这项工作中，我们推测，通过卷积神经网络学习的特征提供了从视频中区分检测癫痫发作的能力，甚至允许我们的系统推广到不同的癫痫发作类型。通过将我们的方法与最先进的方法进行比较，我们显示了学习特征在癫痫发作检测中的优越性能。
Epileptic seizures constitute a serious neurological condition for patients and, if untreated, considerably decrease their quality of life. Early and correct diagnosis by semiological seizure analysis provides the main approach to treat and improve the patients' condition. To obtain reliable and quantifiable information, medical professionals perform seizure detection and subsequent analysis using expensive video-EEG systems in specialized epilepsy monitoring units. However, the detection of seizures, especially under difficult circumstances such as occlusion by the blanket or in the absence of predictive EEG patterns, is highly subjective and should therefore be supported by automated systems. In this work, we conjecture that features learned via a convolutional neural network provide the ability to distinctively detect seizures from video, and even allow our system to generalize to different seizure types. By comparing our method to the state of the art we show the superior performance of learned features for epileptic seizure detection.