Institute for Medical Statistics and Epidemiology, Technische Universität München, Ismaninger Str. 22, 81675 München, Germany.
Int J Comput Assist Radiol Surg. 2011 Nov;6(6):721-35. doi: 10.1007/s11548-011-0549-5. Epub 2011 Mar 5.
Breast cancer is a common but treatable disease for adult women. Improvements in breast cancer detection and treatment have helped to lower mortality, but there is still a need for further improvements, particularly for better computer-aided diagnosis (CADx) and computer-aided detection (CADe).
Two new CAD prototypes, one CADx and one CADe prototype, were evaluated. The core modules are segmentation of lesions, feature extraction, and classification. The evaluation of microcalcifications and mass lesions is based on the currently largest publicly available Digital Database for Screening Mammography (DDSM) with digitized film mammograms and a smaller data source with high-quality mammograms from digital mammography devices. Two different image analysis approaches used by the respective CAD prototypes were examined and compared. These include the 'machine learning' approach and the new 'knowledge-driven' approach. Particular emphasis is put on a profound discussion of statistical methods with recommendations for their proper application in order to avoid common errors including feature selection, model fitting, and sampling schemes.
The results show that the classification performance of the investigated CADx prototypes for microcalcifications produced a higher AUC =.777 for 44 machine learning features than for 10 knowledge-driven features (AUC =.657). A combination of both feature sets (53 features) did not substantially raise the classification performance (AUC =.771). These analyses were based on 1,347 and 1,359 ROIs, respectively. Evaluating the CADx prototype with 242 machine learning features on DDSM masses data resulted in an AUC of .862 using 1,934 ROIs. Furthermore, a CADe prototype was applied to three own databases giving information about the true positive detection rate for mass lesions. Depending on the definition of a true positive detection, it produced AUC values of .953, .818, and .954 using 12, 17, and 18 features, respectively.
The comparison of CAD prototypes revealed that the quality of results is highly dependent on the correct usage of statistical models, feature selection methods, and evaluation schemes.
乳腺癌是成年女性常见但可治疗的疾病。乳腺癌检测和治疗的改进有助于降低死亡率，但仍需要进一步改进，特别是在更好的计算机辅助诊断（CADx）和计算机辅助检测（CADe）方面。
评估了两个新的 CAD 原型，一个 CADx 和一个 CADe 原型。核心模块包括病变分割、特征提取和分类。微钙化和肿块病变的评估基于目前最大的公开可用数字筛查乳腺数据库（DDSM），其中包含数字化胶片乳腺 X 线照片，以及来自数字乳腺成像设备的高质量乳腺 X 线照片的较小数据源。分别检查和比较了两个不同的 CAD 原型使用的图像分析方法。这些方法包括“机器学习”方法和新的“知识驱动”方法。特别强调对统计方法进行深入讨论，并提出适当应用这些方法的建议，以避免包括特征选择、模型拟合和抽样方案在内的常见错误。
结果表明，针对微钙化的调查 CADx 原型的分类性能产生了更高的 AUC =.777，用于 44 个机器学习特征，而 10 个知识驱动特征的 AUC =.657（AUC =.777）。将这两种特征集（53 个特征）结合起来并没有显著提高分类性能（AUC =.771）。这些分析分别基于 1347 和 1359 个 ROI。使用 242 个机器学习特征在 DDSM 肿块数据上评估 CADx 原型，使用 1934 个 ROI 得到 AUC =.862。此外，还应用了一个 CADe 原型到三个自己的数据库，提供了关于肿块病变的真阳性检测率的信息。根据真阳性检测的定义，使用 12、17 和 18 个特征分别产生 AUC 值为.953、.818 和.954。
CAD 原型的比较表明，结果的质量高度依赖于统计模型、特征选择方法和评估方案的正确使用。
