Wellcome Centre for Human Neuroimaging, University College London, London, UK.
Developmental Neurosciences, Great Ormond Street Institute of Child Health, University College London, London, UK.
Epilepsia. 2020 Jul;61(7):1406-1416. doi: 10.1111/epi.16574. Epub 2020 Jun 13.
OBJECTIVE: This retrospective, cross-sectional study evaluated the feasibility and potential benefits of incorporating deep-learning on structural magnetic resonance imaging (MRI) into planning stereoelectroencephalography (sEEG) implantation in pediatric patients with diagnostically complex drug-resistant epilepsy. This study aimed to assess the degree of colocalization between automated lesion detection and the seizure onset zone (SOZ) as assessed by sEEG. METHODS: A neural network classifier was applied to cortical features from MRI data from three cohorts. (1) The network was trained and cross-validated using 34 patients with visible focal cortical dysplasias (FCDs). (2) Specificity was assessed in 20 pediatric healthy controls. (3) Feasibility of incorporation into sEEG implantation plans was evaluated in 34 sEEG patients. Coordinates of sEEG contacts were coregistered with classifier-predicted lesions. sEEG contacts in seizure onset and irritative tissue were identified by clinical neurophysiologists. A distance of <10 mm between SOZ contacts and classifier-predicted lesions was considered colocalization. RESULTS: In patients with radiologically defined lesions, classifier sensitivity was 74% (25/34 lesions detected). No clusters were detected in the controls (specificity = 100%). Of the total 34 sEEG patients, 21 patients had a focal cortical SOZ, of whom eight were histopathologically confirmed as having an FCD. The algorithm correctly detected seven of eight of these FCDs (86%). In patients with histopathologically heterogeneous focal cortical lesions, there was colocalization between classifier output and SOZ contacts in 62%. In three patients, the electroclinical profile was indicative of focal epilepsy, but no SOZ was localized on sEEG. In these patients, the classifier identified additional abnormalities that had not been implanted. SIGNIFICANCE: There was a high degree of colocalization between automated lesion detection and sEEG. We have created a framework for incorporation of deep-learning-based MRI lesion detection into sEEG implantation planning. Our findings support the prospective evaluation of automated MRI analysis to plan optimal electrode trajectories.
目的：本回顾性、横断面研究评估了将深度学习应用于结构性磁共振成像（MRI），并将其纳入到儿童药物难治性癫痫诊断性复杂患者立体脑电图（sEEG）植入计划中的可行性和潜在益处。本研究旨在评估自动病变检测与 sEEG 评估的致痫区（SOZ）之间的重合程度。
方法：应用神经网络分类器对来自三个队列的 MRI 数据的皮质特征进行分析。（1）使用 34 例可见局灶性皮质发育不良（FCD）的患者进行网络训练和交叉验证。（2）在 20 例儿科健康对照者中评估特异性。（3）在 34 例 sEEG 患者中评估纳入 sEEG 植入计划的可行性。sEEG 触点的坐标与分类器预测的病变进行配准。临床神经生理学家识别 sEEG 触点的起始发作和刺激性组织。SOZ 触点与分类器预测病变之间的距离<10mm 被认为是重合的。
结果：在有影像学定义病变的患者中，分类器的敏感性为 74%（25/34 个病变被检测到）。对照组中未检测到簇（特异性=100%）。在总共 34 例 sEEG 患者中，21 例患者有局灶性皮质 SOZ，其中 8 例经组织病理学证实为 FCD。该算法正确检测到 8 例 FCD 中的 7 例（86%）。在组织病理学上具有异质性局灶性皮质病变的患者中，分类器输出与 SOZ 触点之间有 62%的重合。在 3 例患者中，电临床特征提示为局灶性癫痫，但 sEEG 未定位到 SOZ。在这些患者中，分类器识别出了未植入的其他异常。
意义：自动病变检测与 sEEG 之间有高度的重合。我们已经创建了一个将基于深度学习的 MRI 病变检测纳入 sEEG 植入计划的框架。我们的发现支持前瞻性评估自动 MRI 分析，以规划最佳电极轨迹。
Dev Med Child Neurol. 2024-2
J Neurosurg Pediatr. 2018-10
World J Pediatr. 2025-5-4
Insights Imaging. 2024-9-12
Nat Rev Neurol. 2024-6
Sensors (Basel). 2023-8-10
BMJ Surg Interv Health Technol. 2022-1-27
Front Neurosci. 2021-6-22
JAMA Neurol. 2019-10-1
Wellcome Open Res. 2021-1-21
Epilepsia. 2019-2-12
J Neurosurg Pediatr. 2019-3-1
Ann Clin Transl Neurol. 2018-9-27
Zotero 插件
