Li L, Zheng Y, Zhang L, Clark R A
Department of Radiology, College of Medicine, and the H. Lee Moffitt Cancer Center and Research Institute at the University of South Florida, Tampa 33612, USA.
Med Phys. 2001 Feb;28(2):250-8. doi: 10.1118/1.1344203.
High false-positive (FP) rate remains to be one of the major problems to be solved in CAD study because too many false-positively cued signals will potentially degrade the performance of detecting true-positive regions and increase the call-back rate in CAD environment. In this paper, we proposed a novel classification method for FP reduction, where the conventional "hard" decision classifier is cascaded with a "soft" decision classification with the objective to reduce false-positives in the cases with multiple FPs retained after the "hard" decision classification. The "soft" classification takes a competitive classification strategy in which only the "best" ones are selected from the pre-classified suspicious regions as the true mass in each case. A neural network structure is designed to implement the proposed competitive classification. Comparative studies of FP reduction on a database of 79 images by a "hard" decision classification and a combined "hard"-"soft" classification method demonstrated the efficiency of the proposed classification strategy. For example, for the high FP sub-database which has only 31.7% of total images but accounts for 63.5% of whole FPs generated in single "hard" classification, the FPs can be reduced for 56% (from 8.36 to 3.72 per image) by using the proposed method at the cost of 1% TP loss (from 69% to 68%) in whole database, while it can only be reduced for 27% (from 8.36 to 6.08 per image) by simply increasing the threshold of "hard" classifier with a cost of TP loss as high as 14% (from 69% to 55%). On the average in whole database, the FP reduction by hybrid "hard"-"soft" classification is 1.58 per image as compared to 1.11 by "hard" classification at the TP costs described above. Because the cases with high dense tissue are of higher risk of cancer incidence and false-negative detection in mammogram screening, and usually generate more FPs in CAD detection, the method proposed in this paper will be very helpful in improving the performance of early detection of breast cancer with CAD.
高假阳性（FP）率仍然是计算机辅助检测（CAD）研究中有待解决的主要问题之一，因为过多的假阳性提示信号可能会降低检测真阳性区域的性能，并增加CAD环境中的召回率。在本文中，我们提出了一种用于减少FP的新型分类方法，其中传统的“硬”决策分类器与“软”决策分类器级联，目的是在“硬”决策分类后保留多个FP的情况下减少假阳性。“软”分类采用竞争分类策略，在每种情况下，仅从预分类的可疑区域中选择“最佳”区域作为真正的肿块。设计了一种神经网络结构来实现所提出的竞争分类。通过“硬”决策分类和“硬”-“软”组合分类方法对79幅图像数据库进行FP减少的比较研究，证明了所提出分类策略的有效性。例如，对于高FP子数据库，其仅占总图像的31.7%，但在单次“硬”分类中占整个FP的63.5%，使用所提出的方法可以将FP减少56%（从每幅图像8.36个减少到3.72个），代价是整个数据库中真阳性（TP）损失1%（从69%降至68%），而仅通过简单提高“硬”分类器的阈值只能将FP减少27%（从每幅图像8.36个减少到6.08个），TP损失高达14%（从69%降至55%）。在整个数据库中，平均而言，“硬”-“软”混合分类减少的FP为每幅图像1.58个，而上述TP代价下“硬”分类减少的FP为每幅图像1.11个。由于高密度组织的病例在乳房X光筛查中患癌风险更高且假阴性检测率更高，并且在CAD检测中通常会产生更多的FP，本文提出的方法将非常有助于提高CAD对乳腺癌的早期检测性能。
