González-Castro Víctor, Valdés Hernández María Del C, Chappell Francesca M, Armitage Paul A, Makin Stephen, Wardlaw Joanna M
Department of Neuroimaging Sciences, Centre for Clinical Brain Sciences, University of Edinburgh, 49 Little France Crescent, Edinburgh EH16 4SB, U.K.
Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Royal Hallamshire Hospital, Sheffield S10 2JF, United Kingdom.
Clin Sci (Lond). 2017 Jun 28;131(13):1465-1481. doi: 10.1042/CS20170051. Print 2017 Jul 1.
In the brain, enlarged perivascular spaces (PVS) relate to cerebral small vessel disease (SVD), poor cognition, inflammation and hypertension. We propose a fully automatic scheme that uses a support vector machine (SVM) to classify the burden of PVS in the basal ganglia (BG) region as low or high. We assess the performance of three different types of descriptors extracted from the BG region in T2-weighted MRI images: (i) statistics obtained from Wavelet transform's coefficients, (ii) local binary patterns and (iii) bag of visual words (BoW) based descriptors characterizing local keypoints obtained from a dense grid with the scale-invariant feature transform (SIFT) characteristics. When the latter were used, the SVM classifier achieved the best accuracy (81.16%). The output from the classifier using the BoW descriptors was compared with visual ratings done by an experienced neuroradiologist (Observer 1) and by a trained image analyst (Observer 2). The agreement and cross-correlation between the classifier and Observer 2 (κ = 0.67 (0.58-0.76)) were slightly higher than between the classifier and Observer 1 (κ = 0.62 (0.53-0.72)) and comparable between both the observers (κ = 0.68 (0.61-0.75)). Finally, three logistic regression models using clinical variables as independent variable and each of the PVS ratings as dependent variable were built to assess how clinically meaningful were the predictions of the classifier. The goodness-of-fit of the model for the classifier was good (area under the curve (AUC) values: 0.93 (model 1), 0.90 (model 2) and 0.92 (model 3)) and slightly better (i.e. AUC values: 0.02 units higher) than that of the model for Observer 2. These results suggest that, although it can be improved, an automatic classifier to assess PVS burden from brain MRI can provide clinically meaningful results close to those from a trained observer.
在大脑中，扩大的血管周围间隙（PVS）与脑小血管疾病（SVD）、认知功能差、炎症和高血压有关。我们提出了一种全自动方案，使用支持向量机（SVM）将基底神经节（BG）区域的PVS负担分类为低或高。我们评估了从T2加权MRI图像的BG区域提取的三种不同类型描述符的性能：（i）从小波变换系数获得的统计数据，（ii）局部二值模式，以及（iii）基于视觉词袋（BoW）的描述符，用于表征从具有尺度不变特征变换（SIFT）特征的密集网格获得的局部关键点。当使用后者时，SVM分类器实现了最佳准确率（81.16%）。使用BoW描述符的分类器输出与经验丰富的神经放射科医生（观察者1）和训练有素的图像分析师（观察者2）进行的视觉评分进行了比较。分类器与观察者2之间的一致性和交叉相关性（κ = 0.67（0.58 - 0.76））略高于分类器与观察者1之间的一致性和交叉相关性（κ = 0.62（0.53 - 0.72）），并且在两个观察者之间具有可比性（κ = 0.68（0.61 - 0.75））。最后，构建了三个逻辑回归模型，使用临床变量作为自变量，每个PVS评级作为因变量，以评估分类器的预测在临床上的意义有多大。分类器模型的拟合优度良好（曲线下面积（AUC）值：0.93（模型1）、0.90（模型2）和0.92（模型3）），并且比观察者2的模型略好（即AUC值高0.02个单位）。这些结果表明，虽然可以改进，但用于从脑部MRI评估PVS负担的自动分类器可以提供与训练有素的观察者相近的具有临床意义的结果。
