COMPARE: Classification of morphological patterns using adaptive regional elements
COMPARE: Classification of morphological patterns using adaptive regional elements
复制标题
DOI：
10.1109/tmi.2006.886812
复制
发表时间：
2007-01-01
影响因子：
10.6
通讯作者：
Davatzikos, Christos
中科院分区：
文献类型：
--
作者：
Fan, Yong;Shen, Dinggang;Davatzikos, Christos
提出了一种结合基于变形的形态测量学和机器学习方法对结构性脑磁共振（MR）图像进行分类的方法。首先使用高维质量保持模板变形方法获得感兴趣的解剖结构的形态表示，该方法导致构成局部组织体积测量的组织密度图。使用分水岭分割算法提取显示组织体积和分类（临床）变量之间强相关性的区域，同时考虑到通过交叉验证策略估计的相关图的区域平滑度，以实现对离群值的鲁棒性。然后，体积增量算法应用到这些区域提取区域体积特征，从其中使用支持向量机（SVM）为基础的标准的特征选择技术被用来选择最具鉴别力的功能，根据他们的效果上界的留一法泛化误差。最后，基于SVM的分类应用于使用最佳的功能集，并使用留一交叉验证策略进行测试。健康对照组和精神分裂症患者的MR脑图像的结果表明，不仅高的分类准确率（91.8%的女性受试者和90.8%的男性受试者），但也具有良好的稳定性，相对于所选择的特征的数量和所使用的SVM核的大小。
This paper presents a method for classification of structural brain magnetic resonance (MR) images, by using a combination of deformation- based morphometry and machine learning methods. A morphological representation of the anatomy of interest is first obtained using a high-dimensional mass-preserving template warping method, which results in tissue density maps that constitute local tissue volumetric measurements. Regions that display strong correlations between tissue volume and classification (clinical) variables are extracted using a watershed segmentation algorithm, taking into account the regional smoothness of the correlation map which is estimated by a cross-validation strategy to achieve robustness to outliers. A volume increment algorithm is then applied to these regions to extract regional volumetric features, from which a feature selection technique using support vector machine (SVM)-based criteria is used to select the most discriminative features, according to their effect on the upper bound of the leave-one-out generalization error. Finally, SVM-based classification is applied using the best set of features, and it is tested using a leave-one-out cross-validation strategy. The results on MR brain images of healthy controls and schizophrenia patients demonstrate not only high classification accuracy (91.8% for female subjects and 90.8% for male subjects), but also good stability with respect to the number of features selected and the size of SVM kernel used.