Cortical feature analysis and machine learning improves detection of "MRI-negative" focal cortical dysplasia.
Cortical feature analysis and machine learning improves detection of "MRI-negative" focal cortical dysplasia.
复制标题
DOI：
10.1016/j.yebeh.2015.04.055
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Thesen T
中科院分区：
文献类型：
--
作者：
Ahmed B;Brodley CE;Blackmon KE;Kuzniecky R;Barash G;Carlson C;Quinn BT;Doyle W;French J;Devinsky O;Thesen T
局灶性皮质发育不良(FCD)是儿童癫痫最常见的原因，也是成人难治性癫痫的第三大常见病变。MRI的进步使FCD的诊断发生了革命性的变化，导致了癫痫切除手术的更高成功率。然而，许多经组织学证实的FCD患者的术前MRI检查正常(‘MRI阴性’)，这使得术前诊断变得困难。本研究的目的是测试一种新的MRI后处理方法是否成功地在没有视觉上可察觉的病变的患者样本中检测到经组织病理学验证的FCD。我们应用了一种自动定量形态测量方法，该方法计算了五个基于表面的MRI特征，并将它们组合在一个机器学习模型中，以分类病变和非病变顶点。当相邻的顶点落在手术切除区域内时，将它们归类为“病变”，以此来定义准确性。我们的多变量方法在7例MRI阳性患者中正确检测出6例病变，这与单变量顶点形态计量学研究中已报道的检测率相当。更重要的是，在MRI阴性的患者中，机器学习正确地识别了24个FCD病变中的14个(58%)。这是在将异常厚度和异常厚度划分为不同的分类器以及分离脑沟和脑回区域后实现的。结果表明，MRI阴性图像包含了足够的信息来帮助在体检测视觉上难以捉摸的FCD病变。
Focal cortical dysplasia (FCD) is the most common cause of pediatric epilepsy and the third most common lesion in adults with treatment-resistant epilepsy. Advances in MRI have revolutionized the diagnosis of FCD, resulting in higher success rates for resective epilepsy surgery. However, many histologically confirmed FCD patients have normal pre-surgical MRI studies (‘MRI-negative’), making pre-surgical diagnosis difficult. The purpose of this study is to test whether a novel MRI post-processing method successfully detects histopathologically-verified FCD in a sample of patients without visually appreciable lesions. We applied an automated quantitative morphometry approach which computed five surface-based MRI features and combined them in a machine learning model to classify lesional and non-lesional vertices. Accuracy was defined by classifying contiguous vertices as “lesional” when they fell within the surgical resection region. Our multivariate method correctly detected the lesion in 6 of 7 MRI-positive patients, which is comparable with the detection rates that have been reported in univariate vertex-based morphometry studies. More significantly, in patients that were MRI-negative, machine learning correctly identified 14 out of 24 FCD lesions (58%). This was achieved after separating abnormal thickness and thinness into distinct classifiers, as well as separating sulcal and gyral regions. Results demonstrate that MRI-negative images contain sufficient information to aid in the in-vivo detection of visually elusive FCD lesions.