Zhou Chunyao, Xie Fangfang, Wang Dongcui, Huang Xiaoting, Guo Danni, Du Yangsa, Xiao Ling, Liu Dingyang, Xiao Bo, Yang Zhiquan, Feng Li
Department of Neurology, Xiangya Hospital, Central South University, Changsha, China.
Department of Neurosurgery, Xiangya Hospital, Central South University, Changsha, China.
Epilepsia. 2024 Apr;65(4):1115-1127. doi: 10.1111/epi.17921. Epub 2024 Feb 23.
Structural-functional coupling (SFC) has shown great promise in predicting postsurgical seizure recurrence in patients with temporal lobe epilepsy (TLE). In this study, we aimed to clarify the global alterations in SFC in TLE patients and predict their surgical outcomes using SFC features.
This study analyzed presurgical diffusion and functional magnetic resonance imaging data from 71 TLE patients and 48 healthy controls (HCs). TLE patients were categorized into seizure-free (SF) and non-seizure-free (nSF) groups based on postsurgical recurrence. Individual functional connectivity (FC), structural connectivity (SC), and SFC were quantified at the regional and modular levels. The data were compared between the TLE and HC groups as well as among the TLE, SF, and nSF groups. The features of SFC, SC, and FC were categorized into three datasets: the modular SFC dataset, regional SFC dataset, and SC/FC dataset. Each dataset was independently integrated into a cross-validated machine learning model to classify surgical outcomes.
Compared with HCs, the visual and subcortical modules exhibited decoupling in TLE patients (p < .05). Multiple default mode network (DMN)-related SFCs were significantly higher in the nSF group than in the SF group (p < .05). Models trained using the modular SFC dataset demonstrated the highest predictive performance. The final prediction model achieved an area under the receiver operating characteristic curve of .893 with an overall accuracy of .887.
Presurgical hyper-SFC in the DMN was strongly associated with postoperative seizure recurrence. Furthermore, our results introduce a novel SFC-based machine learning model to precisely classify the surgical outcomes of TLE.
结构-功能耦合（SFC）在预测颞叶癫痫（TLE）患者术后癫痫复发方面显示出巨大潜力。在本研究中，我们旨在阐明TLE患者SFC的整体变化，并使用SFC特征预测其手术结果。
本研究分析了71例TLE患者和48例健康对照（HC）术前的扩散和功能磁共振成像数据。根据术后复发情况，将TLE患者分为无癫痫发作（SF）组和非无癫痫发作（nSF）组。在区域和模块水平上对个体功能连接性（FC）、结构连接性（SC）和SFC进行量化。比较了TLE组和HC组以及TLE组、SF组和nSF组之间的数据。将SFC、SC和FC的特征分为三个数据集：模块化SFC数据集、区域SFC数据集和SC/FC数据集。每个数据集被独立整合到一个交叉验证的机器学习模型中，以对手术结果进行分类。
与HC相比，TLE患者的视觉和皮质下模块表现出解耦（p <.05）。nSF组中多个与默认模式网络（DMN）相关的SFC显著高于SF组（p <.05）。使用模块化SFC数据集训练的模型表现出最高的预测性能。最终的预测模型在受试者工作特征曲线下的面积为0.893，总体准确率为0.887。
DMN术前的高SFC与术后癫痫复发密切相关。此外，我们的结果引入了一种基于SFC的新型机器学习模型，以精确分类TLE的手术结果。
