Department of Neurology, University of California, San Francisco, San Francisco, CA, USA; Department of Neurology, National Neuroscience Institute, Singapore.
Laboratory of Neuro Imaging, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA.
Neuroimage. 2018 Feb 1;166:10-18. doi: 10.1016/j.neuroimage.2017.10.065. Epub 2017 Oct 31.
Focal cortical dysplasias (FCDs) often cause pharmacoresistant epilepsy, and surgical resection can lead to seizure-freedom. Magnetic resonance imaging (MRI) and positron emission tomography (PET) play complementary roles in FCD identification/localization; nevertheless, many FCDs are small or subtle, and difficult to find on routine radiological inspection. We aimed to automatically detect subtle or visually-unidentifiable FCDs by building a classifier based on an optimized cortical surface sampling of combined MRI and PET features.
Cortical surfaces of 28 patients with histopathologically-proven FCDs were extracted. Morphology and intensity-based features characterizing FCD lesions were calculated vertex-wise on each cortical surface, and fed to a 2-step (Support Vector Machine and patch-based) classifier. Classifier performance was assessed compared to manual lesion labels.
Our classifier using combined feature selections from MRI and PET outperformed both quantitative MRI and multimodal visual analysis in FCD detection (93% vs 82% vs 68%). No false positives were identified in the controls, whereas 3.4% of the vertices outside FCD lesions were also classified to be lesional ("extralesional clusters"). Patients with type I or IIa FCDs displayed a higher prevalence of extralesional clusters at an intermediate distance to the FCD lesions compared to type IIb FCDs (p < 0.05). The former had a correspondingly lower chance of positive surgical outcome (71% vs 91%).
Machine learning with multimodal feature sampling can improve FCD detection. The spread of extralesional clusters characterize different FCD subtypes, and may represent structurally or functionally abnormal tissue on a microscopic scale, with implications for surgical outcomes.
局灶性皮质发育不良（FCD）常导致药物难治性癫痫，手术切除可实现无癫痫发作。磁共振成像（MRI）和正电子发射断层扫描（PET）在 FCD 识别/定位中发挥互补作用；然而，许多 FCD 较小或较细微，在常规影像学检查中难以发现。我们旨在通过构建基于优化的 MRI 和 PET 特征的皮质表面采样的分类器来自动检测细微或肉眼无法识别的 FCD。
提取 28 例经组织病理学证实的 FCD 患者的皮质表面。在每个皮质表面上计算特征化 FCD 病变的基于形态和强度的顶点特征，并将其输入到 2 步（支持向量机和基于补丁的）分类器中。评估分类器的性能与手动病变标签进行比较。
我们的分类器使用 MRI 和 PET 的组合特征选择在 FCD 检测中优于定量 MRI 和多模态视觉分析（93%比 82%比 68%）。在对照组中未发现假阳性，而在 FCD 病变外的 3.4%顶点也被分类为病变（“病变外簇”）。与 IIb 型 FCD 相比，I 型或 IIa 型 FCD 患者在与 FCD 病变的中间距离处具有更高的病变外簇发生率（p<0.05）。前者的手术阳性结果的可能性较低（71%比 91%）。
使用多模态特征采样的机器学习可以提高 FCD 的检测能力。病变外簇的扩散特征描述了不同的 FCD 亚型，可能代表微观尺度上结构或功能异常的组织，对手术结果具有重要意义。
