Temporal Lobe Epilepsy Surgical Outcomes Can Be Inferred Based on Structural Connectome Hubs: A Machine Learning Study.
Temporal Lobe Epilepsy Surgical Outcomes Can Be Inferred Based on Structural Connectome Hubs: A Machine Learning Study.
复制标题
DOI：
10.1002/ana.25888
复制
发表时间：
2020-11
影响因子：
11.2
通讯作者：
Bonilha L
中科院分区：
文献类型：
--
作者：
Gleichgerrcht E;Keller SS;Drane DL;Munsell BC;Davis KA;Kaestner E;Weber B;Krantz S;Vandergrift WA;Edwards JC;McDonald CR;Kuzniecky R;Bonilha L
内侧颞叶癫痫（TLE）是成人中最常见的耐药局灶性癫痫。尽管切除了内侧颞结构，但超过三分之一的患者术后仍有致残癫痫发作。癫痫难治性意味着内侧外区域能够影响大脑网络并引起癫痫发作。我们测试了结构网络整合的异常是否与手术结果有关。来自三个独立癫痫中心的121例耐药TLE患者的术前磁共振图像用于训练基于全脑弥散张量成像结构连接体的组织体积或图论测量的前馈神经网络模型。使用来自其他三个癫痫中心的47例TLE患者的独立数据集来评估每个模型的预测值和区域解剖学对手术治疗结果的贡献。基于区域中间度中心性的受试者工作特征曲线下面积（ROC）为0.88，显著高于随机模型或基于灰质体积、程度、强度和聚类系数的模型。对预测模型贡献最大的节点包括双侧海马旁回和颞上回。内侧和外侧颞区的网络整合与手术结果有关。结构网络节点整合异常的患者癫痫发作自由的可能性较小。这些发现与之前关于颞叶神经网络异常的观察结果一致，并扩展了潜在异常可塑性的概念。我们的发现为手术难治性的机制提供了额外的信息。
Medial temporal lobe epilepsy (TLE) is the most common form of medication-resistant focal epilepsy in adults. Despite removal of medial temporal structures, over a third of patients continue to have disabling seizures post-operatively. Seizure refractoriness implies that extra-medial regions are capable of influencing the brain network and generating seizures. We tested whether abnormalities of structural network integration could be associated with surgical outcomes. Presurgical magnetic resonance images from 121 patients with drug-resistant TLE across three independent epilepsy centers were used to train feed-forward neural network models based on tissue volume or graph-theory measures from whole-brain diffusion tensor imaging structural connectomes. An independent dataset of 47 patients with TLE from three other epilepsy centers was used to assess the predictive values of each model and regional anatomical contributions towards surgical treatment results. The receiver-operating characteristic (ROC) area under the curve (AUC) based on regional betweenness centrality was 0.88, significantly higher than a random model or models based on gray matter volumes, degree, strength, and clustering coefficient. Nodes most strongly contributing to the predictive models involved the bilateral parahippocampal gyri, as well as the superior temporal gyri. Network integration in the medial and lateral temporal regions was related to surgical outcomes. Patients with abnormally integrated structural network nodes were less likely to achieve seizure freedom. These findings are in line with previous observations related to network abnormalities in TLE and expand on the notion of underlying aberrant plasticity. Our findings provide additional information on the mechanisms of surgical refractoriness.
登录
查看更多内容
影响因子：
5.6
作者：
Bonilha, Leonardo;Yasuda, Clarissa Lin;Cendes, Fernando
通讯作者：
Cendes, Fernando
影响因子：
5.7
作者：
Bernasconi, N;Duchesne, S;Bernasconi, A
通讯作者：
Bernasconi, A
影响因子：
3.4
作者：
Del Gaizo, John;Fridriksson, Julius;Bonilha, Leonardo
通讯作者：
Bonilha, Leonardo
影响因子：
9.9
作者：
Engel, J;Wiebe, S;Enos, B
通讯作者：
Enos, B
影响因子：
14.5
作者：
Hatton, Sean N.;Huynh, Khoa H.;McDonald, Carrie R.
通讯作者：
McDonald, Carrie R.