Comprehensive Breast Cancer Center, Laboratory of Cancer Research, Changhua Christian Hospital, Changhua, Taiwan.
Comput Med Imaging Graph. 2011 Apr;35(3):220-6. doi: 10.1016/j.compmedimag.2010.11.003. Epub 2010 Dec 4.
Computer-aided diagnosis (CAD) systems provided second beneficial support reference and enhance the diagnostic accuracy. This paper was aimed to develop and evaluate a CAD with texture analysis in the classification of breast tumors for ultrasound images.
The ultrasound (US) dataset evaluated in this study composed of 1020 sonograms of region of interest (ROI) subimages from 255 patients. Two-view sonogram (longitudinal and transverse views) and four different rectangular regions were utilized to analyze each tumor. Six practical textural features from the US images were performed to classify breast tumors as benign or malignant. However, the textural features always perform as a high dimensional vector; high dimensional vector is unfavorable to differentiate breast tumors in practice. The principal component analysis (PCA) was used to reduce the dimension of textural feature vector and then the image retrieval technique was performed to differentiate between benign and malignant tumors. In the experiments, all the cases were sampled with k-fold cross-validation (k=10) to evaluate the performance with receiver operating characteristic (ROC) curve.
The area (A(Z)) under the ROC curve for the proposed CAD system with the specific textural features was 0.925±0.019. The classification ability for breast tumor with textural information is satisfactory.
This system differentiates benign from malignant breast tumors with a good result and is therefore clinically useful to provide a second opinion.
计算机辅助诊断（CAD）系统提供了二次有益的辅助参考，并提高了诊断准确性。本文旨在开发和评估一种基于纹理分析的 CAD 系统，用于对超声图像中的乳腺肿瘤进行分类。
本研究评估的超声（US）数据集由 255 名患者的 1020 个感兴趣区域（ROI）子图像的超声图像组成。利用两视图超声（纵向和横向视图）和四个不同的矩形区域来分析每个肿瘤。从 US 图像中提取了 6 个实用的纹理特征，用于将乳腺肿瘤分类为良性或恶性。然而，纹理特征通常表现为高维向量；高维向量不利于实际区分乳腺肿瘤。本研究采用主成分分析（PCA）来降低纹理特征向量的维数，然后采用图像检索技术来区分良性和恶性肿瘤。在实验中，所有病例均采用 k 折交叉验证（k=10）进行采样，以接收者操作特征（ROC）曲线评估性能。
所提出的 CAD 系统与特定纹理特征的 ROC 曲线下面积（A(Z)）为 0.925±0.019。基于纹理信息的乳腺肿瘤分类能力令人满意。
该系统能够很好地区分良性和恶性乳腺肿瘤，因此在临床上具有提供二次诊断的实用价值。
