Department of Radiology, University of Michigan, 1500 E. Medical Center Drive, Med Inn Building C478, Ann Arbor, Michigan 48109-5842, USA.
Med Phys. 2009 Oct;36(10):4451-60. doi: 10.1118/1.3220669.
The purpose of this study is to develop a computer-aided detection (CAD) system that combined a dual system approach with a two-view fusion method to improve the accuracy of mass detection on mammograms.
The authors previously developed a dual CAD system that merged the decision from two mass detection systems in parallel, one trained with average masses and another trained with subtle masses, to improve sensitivity without excessively increasing false positives (FPs). In this study, they further designed a two-view fusion method to combine the information from different mammographic views. Mass candidates detected independently by the dual system on the two-view mammograms were first identified as potential pairs based on a regional registration technique. A similarity measure was designed to differentiate TP-TP pairs from other pairs (TP-FP and FP-FP pairs) using paired morphological features, Hessian feature, and texture features. A two-view fusion score for each object was generated by weighting the similarity measure with the cross correlation measure of the object pair. Finally, a linear discriminant analysis classifier was trained to combine the mass likelihood score of the object from the single-view dual system and the two-view fusion score for classification of masses and FPs. A total of 2332 mammograms from 735 subjects including 800 normal mammograms from 200 normal subjects was collected with Institutional Review Board (IRB) approval.
When the single-view CAD system that was trained with average masses only were applied to the test sets, the average case-based sensitivities were 50.6% and 63.6% for average masses on current mammograms and 22.6% and 36.2% for subtle masses on prior mammograms at 0.5 and 1 FPs/image, respectively. With the new two-view dual system approach, the average case-based sensitivities were improved to 67.4% and 83.7% for average masses and 44.8% and 57.0% for subtle masses at the same FP rates.
The improvement with the proposed method was found to be statistically significant (p<0.0001) by JAFROC analysis.
本研究旨在开发一种计算机辅助检测 (CAD) 系统，该系统结合了双系统方法和两视图融合方法，以提高乳腺 X 线摄影中肿块检测的准确性。
作者先前开发了一种双 CAD 系统，该系统融合了两个并行的肿块检测系统的决策，一个系统使用平均肿块进行训练，另一个系统使用细微肿块进行训练，以在不增加过多假阳性 (FP) 的情况下提高灵敏度。在这项研究中，他们进一步设计了一种两视图融合方法，以结合来自不同乳腺 X 线视图的信息。双系统在两视图乳腺 X 线片上独立检测到的肿块候选者首先基于区域配准技术被识别为潜在的对。设计了一种相似性度量标准，使用配对形态特征、Hessian 特征和纹理特征来区分 TP-TP 对与其他对 (TP-FP 和 FP-FP 对)。通过用对象对的互相关测量加权相似性度量，为每个对象生成两视图融合得分。最后，使用线性判别分析分类器结合单视图双系统的对象似然评分和两视图融合得分来对肿块和 FP 进行分类。在机构审查委员会 (IRB) 的批准下，共收集了 735 名受试者的 2332 张乳腺 X 线片，其中包括 200 名正常受试者的 800 张正常乳腺 X 线片。
当仅使用平均肿块训练的单视图 CAD 系统应用于测试集时，在 0.5 和 1 FP/图像的平均肿块在当前乳腺 X 线上的平均病例敏感性分别为 50.6%和 63.6%，在先前乳腺 X 线上的细微肿块分别为 22.6%和 36.2%。使用新的两视图双系统方法，平均病例敏感性提高到平均肿块在当前乳腺 X 线上的 67.4%和 83.7%，以及在先前乳腺 X 线上的细微肿块的 44.8%和 57.0%，在相同的 FP 率下。
通过 JAFROC 分析发现，该方法的改进具有统计学意义 (p<0.0001)。
