Performance change of mammographic CAD schemes optimized with most-recent and prior image databases
Performance change of mammographic CAD schemes optimized with most-recent and prior image databases
复制标题
DOI：
10.1016/s1076-6332(03)80102-2
复制
发表时间：
2003-03-01
影响因子：
4.8
通讯作者：
Gur, D
中科院分区：
文献类型：
--
作者：
Zheng, B;Good, WF;Gur, D
基本原理和目标。作者评估了计算机辅助诊断（CAD）方案在“当前”（最新）和“先前”图像上检测肿块的性能变化，该方案已与当前和先前乳房x线照片数据库进行了优化。材料与方法。作者选择了260对匹配的连续乳房x光检查。当前的每张图像都描绘了一个或两个经过验证的质量。所有先前的图像最初都被解释为阴性或可能是良性的。CAD方案最初在当前图像上检测到261个质量区域和465个假阳性区域，在先前图像上检测到252个相应的质量区域（早期迹象）和471个假阳性区域。这些区域被分为两个训练数据库和两个测试数据库。利用现有和先验训练数据库，采用遗传算法对两种CAD方案进行优化。用两个独立的测试数据库对这些方案进行了评价。该方案优化后，当前图像在接收机工作特性曲线下产生的面积分别为0.89 +/- 0.01和0.65 +/- 0.02。在现有图像和先验图像下，接收机工作特性曲线下产生的区域分别为0.81 +/- 0.02和0.71 +/- 0.02。当前和先前测试数据库的性能变化都是显著的(P
Rationale and Objectives. The authors evaluated performance changes in the detection of masses on "current" (latest) and "prior" images by computer-aided diagnosis (CAD) schemes that had been optimized with databases of current and prior mammograms.Materials and Methods. The authors selected 260 pairs of matched consecutive mammograms. Each current image depicted one or two verified masses. All prior images had been interpreted originally as negative or probably benign. A CAD scheme initially detected 261 mass regions and 465 false-positive regions on the current images, and 252 corresponding mass regions (early signs) and 471 false-positive regions on prior images. These regions were divided into two training and two testing databases. The current and prior training databases were used to optimize two CAD schemes with a genetic algorithm. These schemes were evaluated with two independent testing databases.Results. The scheme optimized with current images produced areas under the receiver operating characteristic curve of 0.89 +/- 0.01 and 0.65 +/- 0.02 when tested with current images and prior images, respectively. The scheme optimized with prior images produced areas under the receiver operating characteristic curve of 0.81 +/- 0.02 and 0.71 +/- 0.02 when tested with current images and prior images, respectively. Performance changes for both current and prior testing databases were significant (P