Ficici Cansel, Telatar Ziya, Kocak Onur, Erogul Osman
Department of Electrical and Electronics Engineering, Ankara University, 06830 Ankara, Turkey.
Department of Biomedical Engineering, Başkent University, 06790 Ankara, Turkey.
Diagnostics (Basel). 2023 Jul 4;13(13):2261. doi: 10.3390/diagnostics13132261.
Temporal lobe epilepsy, a neurological disease that causes seizures as a result of excessive neural activities in the brain, is the most common type of focal seizure, accounting for 30-35% of all epilepsies. Detection of epilepsy and localization of epileptic focus are essential for treatment planning and epilepsy surgery. Currently, epileptic focus is decided by expert physician by examining the EEG records and determining EEG channel where epileptic patterns begins and continues intensely during seizure. Examination of long EEG recordings is very time-consuming process, requires attention and decision can vary depending on physician. In this study, to assist physicians in detecting epileptic focus side from EEG recordings, a novel deep learning-based computer-aided diagnosis system is presented. In the proposed framework, ictal epochs are detected using long short-term memory network fed with EEG subband features obtained by discrete wavelet transform, and then, epileptic focus identification is realized by using asymmetry score. This algorithm was tested on EEG database obtained from the Ankara University hospital. Experimental results showed ictal and interictal epochs were classified with accuracy of 86.84%, sensitivity of 86.96% and specificity of 89.68% on Ankara University hospital dataset, and 96.67% success rate was obtained on Bonn EEG dataset. In addition, epileptic focus was identified with accuracy of 96.10%, sensitivity of 100% and specificity of 93.80% by using the proposed deep learning-based algorithm and university hospital dataset. These results showed that proposed method can be used properly in clinical applications, epilepsy treatment and surgical planning as a medical decision support system.
颞叶癫痫是一种由于大脑中过度的神经活动而导致癫痫发作的神经系统疾病，是最常见的局灶性癫痫类型，占所有癫痫病例的30 - 35%。癫痫的检测和癫痫病灶的定位对于治疗规划和癫痫手术至关重要。目前，癫痫病灶由专家医生通过检查脑电图记录并确定癫痫发作期间癫痫模式开始并强烈持续的脑电图通道来确定。检查长时间的脑电图记录是一个非常耗时的过程，需要注意力，而且决策可能因医生而异。在本研究中，为了协助医生从脑电图记录中检测癫痫病灶侧，提出了一种基于深度学习的新型计算机辅助诊断系统。在所提出的框架中，使用由离散小波变换获得的脑电图子带特征输入的长短期记忆网络来检测发作期片段，然后，通过使用不对称分数来实现癫痫病灶识别。该算法在从安卡拉大学医院获得的脑电图数据库上进行了测试。实验结果表明，在安卡拉大学医院数据集上，发作期和发作间期片段的分类准确率为86.84%，灵敏度为86.96%，特异性为89.68%，在波恩脑电图数据集上获得了96.67%的成功率。此外，使用所提出的基于深度学习的算法和大学医院数据集，癫痫病灶识别的准确率为96.10%，灵敏度为100%，特异性为93.80%。这些结果表明，所提出的方法作为一种医学决策支持系统，可以在临床应用、癫痫治疗和手术规划中得到恰当应用。
