Local curvature analysis for classifying breast tumors: Preliminary analysis in dedicated breast CT
Local curvature analysis for classifying breast tumors: Preliminary analysis in dedicated breast CT
复制标题
DOI：
10.1118/1.4928479
复制
发表时间：
2015-09-01
期刊：
影响因子：
3.8
通讯作者：
Lindfors, Karen K.
中科院分区：
文献类型：
--
作者：
Lee, Juhun;Nishikawa, Robert M.;Lindfors, Karen K.
目的：本研究的目的是衡量局部曲率测度作为乳腺肿瘤分类的新图像特征的有效性。方法：本研究采用104张女性非对比专用乳腺ct图像，共119个乳腺病变。采用基于种子的分割算法进行体积分割，然后从分割结果中提取三角曲面。然后计算总曲率、平均曲率和高斯曲率。归一化曲率作为分类特征。此外，还提取了传统图像特征，并采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，并使用留一交叉验证来评估特征的分类性能。用受者工作特性曲线下面积（AUC, area under curve）作为评价指标。结果：在曲率测度中，归一化总曲率（C-T）的分类性能最好（AUC为0.74），而其他测度没有单独的分类能力。通过特征选择方案选择5个传统图像特征（2个形状描述符、2个边缘描述符和1个纹理描述符），得到的分类器AUC为0.83。其中，作为边缘描述符的径向梯度指数（RGI）的分类效果最好，AUC为0.73。结合RGI和C-T的分类器的AUC为0.81，与具有上述五种传统图像特征的分类器性能相近（即无统计学显著差异）。对使用传统图像特征和CT不同组合的分类器之间的AUC值进行了额外的比较。结果表明，CT能够代替其他四种图像特征完成分类任务。结论：归一化曲率测量为乳腺肿瘤分类提供了有用的信息。使用它，可以减少分类器中的特征数量，这可能会产生针对不同数据集的更健壮的分类器。(C) 2015年美国医学物理学家协会。
Purpose: The purpose of this study is to measure the effectiveness of local curvature measures as novel image features for classifying breast tumors.Methods: 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.Results: Among curvature measures, the normalized total curvature (C-T) 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 C-T 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.Conclusions: 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. (C) 2015 American Association of Physicists in Medicine.