Lee Juhun, Nishikawa Robert M, Reiser Ingrid, Boone John M, Lindfors Karen K
Department of Radiology, University of Pittsburgh, Pittsburgh, Pennsylvania 15213.
Department of Radiology, University of Chicago, Chicago, Illinois 60637.
Med Phys. 2015 Sep;42(9):5479-89. doi: 10.1118/1.4928479.
The purpose of this study is to measure the effectiveness of local curvature measures as novel image features for classifying breast tumors.
A total of 119 breast lesions from 104 noncontrast dedicated breast computed tomography images of women were used in this study. Volumetric segmentation was done using a seed-based segmentation algorithm and then a triangulated surface was extracted from the resulting segmentation. Total, mean, and Gaussian curvatures were then computed. Normalized curvatures were used as classification features. In addition, traditional image features were also extracted and a forward feature selection scheme was used to select the optimal feature set. Logistic regression was used as a classifier and leave-one-out cross-validation was utilized to evaluate the classification performances of the features. The area under the receiver operating characteristic curve (AUC, area under curve) was used as a figure of merit.
Among curvature measures, the normalized total curvature (CT) showed the best classification performance (AUC of 0.74), while the others showed no classification power individually. Five traditional image features (two shape, two margin, and one texture descriptors) were selected via the feature selection scheme and its resulting classifier achieved an AUC of 0.83. Among those five features, the radial gradient index (RGI), which is a margin descriptor, showed the best classification performance (AUC of 0.73). A classifier combining RGI and CT yielded an AUC of 0.81, which showed similar performance (i.e., no statistically significant difference) to the classifier with the above five traditional image features. Additional comparisons in AUC values between classifiers using different combinations of traditional image features and CT were conducted. The results showed that CT was able to replace the other four image features for the classification task.
The normalized curvature measure contains useful information in classifying breast tumors. Using this, one can reduce the number of features in a classifier, which may result in more robust classifiers for different datasets.
本研究旨在测量局部曲率测量作为用于乳腺肿瘤分类的新型图像特征的有效性。
本研究使用了来自104名女性的非增强专用乳腺计算机断层扫描图像中的119个乳腺病变。使用基于种子的分割算法进行体积分割，然后从所得分割中提取三角化表面。接着计算总曲率、平均曲率和高斯曲率。归一化曲率用作分类特征。此外，还提取了传统图像特征，并使用前向特征选择方案选择最优特征集。使用逻辑回归作为分类器，并利用留一法交叉验证来评估特征的分类性能。使用接收器操作特征曲线下面积（AUC，曲线下面积）作为评估指标。
在曲率测量中，归一化总曲率（CT）显示出最佳分类性能（AUC为0.74），而其他曲率测量单独显示无分类能力。通过特征选择方案选择了五个传统图像特征（两个形状、两个边缘和一个纹理描述符），其所得分类器的AUC为0.83。在这五个特征中，作为边缘描述符的径向梯度指数（RGI）显示出最佳分类性能（AUC为0.73）。结合RGI和CT的分类器的AUC为0.81，与具有上述五个传统图像特征的分类器表现出相似的性能（即无统计学显著差异）。对使用传统图像特征和CT的不同组合的分类器之间的AUC值进行了额外比较。结果表明，CT能够替代其他四个图像特征用于分类任务。
归一化曲率测量在乳腺肿瘤分类中包含有用信息。使用此方法，可以减少分类器中的特征数量，这可能会为不同数据集带来更稳健的分类器。
