Advanced Epilepsy Unit, Mater Adult Hospital Brisbane, Queensland, 4101, Australia; School of Engineering and Built Environment, Griffith University, Queensland, 4111, Australia.
Advanced Epilepsy Unit, Mater Adult Hospital Brisbane, Queensland, 4101, Australia; School of Engineering and Built Environment, Griffith University, Queensland, 4111, Australia.
J Neurosci Methods. 2019 Sep 1;325:108347. doi: 10.1016/j.jneumeth.2019.108347. Epub 2019 Jul 19.
The successful delineation of the epileptogenic zone in epilepsy monitoring is crucial for achieving seizure freedom after epilepsy surgery.
We aim to improve epileptogenic zone localization by utilizing a computer-assisted tool for the automated grading of the seizure activity recorded in various locations for 20 patients undergoing stereo electroencephalography. Their epileptic seizures were processed to extract two potential biomarkers. The concentration of these biomarkers from within each patient's implantation were then graded to identify their epileptogenic zone and were compared to the clinical assessment.
Our technique was capable of ranking the clinically defined epileptogenic zone with high accuracy, above 95%, with a true to false positive ratio of 1:1.52, and was effective with both temporal and extra-temporal onset epilepsies.
We compared our method to two other groups performing localization using similar biomarkers. Our classification metrics, sensitivity and precision together were comparable to both groups and our overall accuracy from a larger population was also higher then both.
Our method is highly accurate, automated and non-parametric providing clinicians another tool that can be used to help identify the epileptogenic zone in patients undergoing the stereo electroencephalography procedure for epilepsy monitoring.
在癫痫监测中成功划定致痫区对于癫痫手术后实现无癫痫至关重要。
我们旨在通过使用计算机辅助工具来提高致痫区定位的准确性，该工具可对 20 名接受立体脑电图监测的患者在不同部位记录的癫痫发作活动进行自动分级。对他们的癫痫发作进行处理，以提取两个潜在的生物标志物。然后对每个患者植入物内的这些生物标志物的浓度进行分级，以确定其致痫区，并与临床评估进行比较。
我们的技术能够以超过 95%的高精度对临床定义的致痫区进行排序，真阳性与假阳性的比例为 1:1.52，对颞叶和颞叶外起源的癫痫均有效。
我们将我们的方法与使用类似生物标志物进行定位的另外两组进行了比较。我们的分类指标、敏感性和精确度与这两组都相当，并且我们从更大的人群中获得的总体准确性也高于这两组。
我们的方法具有高度准确性、自动化和非参数化的特点，为临床医生提供了另一种工具，可以帮助识别接受立体脑电图监测的癫痫患者的致痫区。
