Neuroimaging of Epilepsy Laboratory, Montreal Neurological Institute and Hospital, McGill University, Montreal, Quebec, Canada.
Department of Neurology, Yonsei University College of Medicine, Seoul, South Korea.
Neuroimage Clin. 2020;28:102438. doi: 10.1016/j.nicl.2020.102438. Epub 2020 Sep 18.
Focal cortical dysplasia (FCD) is the most common epileptogenic developmental malformation and a prevalent cause of surgically amenable epilepsy. While cellular and molecular biology data suggest that FCD lesional characteristics lie along a spectrum, this notion remains to be verified in vivo. We tested the hypothesis that machine learning applied to MRI captures FCD lesional variability at a mesoscopic scale.
We studied 46 patients with histologically verified FCD Type II and 35 age- and sex-matched healthy controls. We applied consensus clustering, an unsupervised learning technique that identifies stable clusters based on bootstrap-aggregation, to 3 T multicontrast MRI (T1-weighted MRI and FLAIR) features of FCD normalized with respect to distributions in controls.
Lesions were parcellated into four classes with distinct structural profiles variably expressed within and across patients: Class-1 with isolated white matter (WM) damage; Class-2 combining grey matter (GM) and WM alterations; Class-3 with isolated GM damage; Class-4 with GM-WM interface anomalies. Class membership was replicated in two independent datasets. Classes with GM anomalies impacted local function (resting-state fMRI derived ALFF), while those with abnormal WM affected large-scale connectivity (assessed by degree centrality). Overall, MRI classes reflected typical histopathological FCD characteristics: Class-1 was associated with severe WM gliosis and interface blurring, Class-2 with severe GM dyslamination and moderate WM gliosis, Class-3 with moderate GM gliosis, Class-4 with mild interface blurring. A detection algorithm trained on class-informed data outperformed a class-naïve paradigm.
Machine learning applied to widely available MRI contrasts uncovers FCD Type II variability at a mesoscopic scale and identifies tissue classes with distinct structural dimensions, functional and histopathological profiles. Integrating in vivo staging of FCD traits with automated lesion detection is likely to inform the development of novel personalized treatments.
局灶性皮质发育不良（FCD）是最常见的致痫性发育畸形，也是手术可治疗癫痫的常见原因。虽然细胞和分子生物学数据表明 FCD 病变特征呈连续谱分布，但这一概念仍有待在体内验证。我们检验了这样一个假设，即应用于 MRI 的机器学习可在介观尺度上捕捉 FCD 病变的可变性。
我们研究了 46 例经组织学证实的 FCD II 型患者和 35 名年龄和性别匹配的健康对照者。我们应用共识聚类（一种无监督学习技术，基于 bootstrap 聚合识别稳定的聚类），对 FCD 患者的 3T 多对比度 MRI（T1 加权 MRI 和 FLAIR）特征进行分析，这些特征经过与对照组分布归一化。
病变被分割成四个具有不同结构特征的类别，这些特征在患者之间和内部表现出不同的表达：第 1 类为孤立的白质（WM）损伤；第 2 类为灰质（GM）和 WM 改变的组合；第 3 类为孤立的 GM 损伤；第 4 类为 GM-WM 界面异常。类别成员在两个独立数据集得到复制。具有 GM 异常的类别影响局部功能（静息态 fMRI 衍生的 ALFF），而具有异常 WM 的类别影响大尺度连通性（通过度中心性评估）。总的来说，MRI 类别反映了典型的组织病理学 FCD 特征：第 1 类与严重的 WM 胶质增生和界面模糊有关，第 2 类与严重的 GM 层状结构紊乱和中度 WM 胶质增生有关，第 3 类与中度 GM 胶质增生有关，第 4 类与轻度界面模糊有关。基于类别信息训练的检测算法优于类别未知的范式。
应用于广泛可用的 MRI 对比的机器学习揭示了 FCD II 型在介观尺度上的可变性，并识别了具有不同结构维度、功能和组织病理学特征的组织类别。将 FCD 特征的体内分期与自动病变检测相结合，可能有助于开发新的个性化治疗方法。
