基于术中脑电信号的（非）癫痫组织的机器学习检测。

Machine learning for (non-)epileptic tissue detection from the intraoperative electrocorticogram.

机构信息

Department of Neurology and Neurosurgery, University Medical Center Utrecht Brain Center, University Medical Center Utrecht, Part of ERN EpiCARE, P.O. box 85500, 3508 GA Utrecht, The Netherlands; Stichting Epilepsie Instellingen Nederland (SEIN), The Netherlands; Technical Medicine, University of Twente, Enschede, The Netherlands.

Department of Neurology and Neurosurgery, University Medical Center Utrecht Brain Center, University Medical Center Utrecht, Part of ERN EpiCARE, P.O. box 85500, 3508 GA Utrecht, The Netherlands.

出版信息

Clin Neurophysiol. 2024 Nov;167:14-25. doi: 10.1016/j.clinph.2024.08.012. Epub 2024 Aug 24.

DOI:10.1016/j.clinph.2024.08.012

PMID:39265288

Abstract

OBJECTIVE

Clinical visual intraoperative electrocorticography (ioECoG) reading intends to localize epileptic tissue and improve epilepsy surgery outcome. We aimed to understand whether machine learning (ML) could complement ioECoG reading, how subgroups affected performance, and which ioECoG features were most important.

METHODS

We included 91 ioECoG-guided epilepsy surgery patients with Engel 1A outcome. We allocated 71 training and 20 test set patients. We trained an extra trees classifier (ETC) with 14 spectral features to classify ioECoG channels as covering resected or non-resected tissue. We compared the ETC's performance with clinical ioECoG reading and assessed whether patient subgroups affected performance. Explainable artificial intelligence (xAI) unveiled the most important ioECoG features learnt by the ETC.

RESULTS

The ETC outperformed clinical reading in five test set patients, was inferior in six, and both were inconclusive in nine. The ETC performed best in the tumor subgroup (area under ROC curve: 0.84 [95%CI 0.79-0.89]). xAI revealed predictors of resected (relative theta, alpha, and fast ripple power) and non-resected tissue (relative beta and gamma power).

CONCLUSIONS

Combinations of subtle spectral ioECoG changes, imperceptible by the human eye, can aid healthy and pathological tissue discrimination.

SIGNIFICANCE

ML with spectral ioECoG features can support, rather than replace, clinical ioECoG reading, particularly in tumors.

摘要

目的

临床视觉术中脑电图（ioECoG）阅读旨在定位癫痫病灶并改善癫痫手术效果。我们旨在了解机器学习（ML）是否可以补充 ioECoG 阅读，哪些亚组会影响性能，以及哪些 ioECoG 特征最重要。

方法

我们纳入了 91 例接受 ioECoG 引导的癫痫手术患者，术后结果为 Engel 1A。我们将 71 例训练和 20 例测试集患者进行了分配。我们使用 14 个光谱特征训练了一个额外的树分类器（ETC），以对 ioECoG 通道进行分类，确定其覆盖切除或未切除的组织。我们比较了 ETC 的性能与临床 ioECoG 阅读，并评估了患者亚组是否会影响性能。可解释的人工智能（xAI）揭示了 ETC 学习到的最重要的 ioECoG 特征。

结果

ETC 在 5 名测试集患者中的表现优于临床阅读，在 6 名患者中的表现不如临床阅读，在 9 名患者中的表现则无法确定。ETC 在肿瘤亚组中的表现最佳（ROC 曲线下面积：0.84 [95%CI 0.79-0.89]）。xAI 揭示了切除（相对θ、α和快波功率）和未切除组织（相对β和γ功率）的预测因素。