Singh Swatee, Tourassi Georgia D, Baker Jay A, Samei Ehsan, Lo Joseph Y
Department of Radiology, Duke University Medical Center, Durham, North Carolina 27705, USA.
Med Phys. 2008 Aug;35(8):3626-36. doi: 10.1118/1.2953562.
The purpose of this study was to propose and implement a computer aided detection (CADe) tool for breast tomosynthesis. This task was accomplished in two stages-a highly sensitive mass detector followed by a false positive (FP) reduction stage. Breast tomosynthesis data from 100 human subject cases were used, of which 25 subjects had one or more mass lesions and the rest were normal. For stage 1, filter parameters were optimized via a grid search. The CADe identified suspicious locations were reconstructed to yield 3D CADe volumes of interest. The first stage yielded a maximum sensitivity of 93% with 7.7 FPs/breast volume. Unlike traditional CADe algorithms in which the second stage FP reduction is done via feature extraction and analysis, instead information theory principles were used with mutual information as a similarity metric. Three schemes were proposed, all using leave-one-case-out cross validation sampling. The three schemes, A, B, and C, differed in the composition of their knowledge base of regions of interest (ROIs). Scheme A's knowledge base was comprised of all the mass and FP ROIs generated by the first stage of the algorithm. Scheme B had a knowledge base that contained information from mass ROIs and randomly extracted normal ROIs. Scheme C had information from three sources of information-masses, FPs, and normal ROIs. Also, performance was assessed as a function of the composition of the knowledge base in terms of the number of FP or normal ROIs needed by the system to reach optimal performance. The results indicated that the knowledge base needed no more than 20 times as many FPs and 30 times as many normal ROIs as masses to attain maximal performance. The best overall system performance was 85% sensitivity with 2.4 FPs per breast volume for scheme A, 3.6 FPs per breast volume for scheme B, and 3 FPs per breast volume for scheme C.
本研究的目的是提出并实现一种用于乳腺断层合成的计算机辅助检测（CADe）工具。这项任务分两个阶段完成——一个高灵敏度的肿块检测器，随后是一个减少假阳性（FP）的阶段。使用了来自100例人体受试者的乳腺断层合成数据，其中25名受试者有一个或多个肿块病变，其余为正常。对于第一阶段，通过网格搜索优化滤波器参数。将CADe识别出的可疑位置进行重建，以生成感兴趣的3D CADe体积。第一阶段的最大灵敏度为93%，每乳房体积有7.7个假阳性。与传统的CADe算法不同，传统算法的第二阶段假阳性减少是通过特征提取和分析来完成的，这里使用信息论原理，以互信息作为相似性度量。提出了三种方案，均采用留一法交叉验证抽样。方案A、B和C这三种方案在其感兴趣区域（ROI）知识库的组成上有所不同。方案A的知识库由算法第一阶段生成的所有肿块和假阳性ROI组成。方案B的知识库包含来自肿块ROI和随机提取的正常ROI的信息。方案C的信息来自三个信息源——肿块、假阳性和正常ROI。此外，根据系统达到最佳性能所需的假阳性或正常ROI数量，将性能评估为知识库组成的函数。结果表明，知识库所需的假阳性数量不超过肿块数量的20倍，正常ROI数量不超过肿块数量的30倍，以达到最大性能。方案A的最佳整体系统性能为灵敏度85%，每乳房体积有2.4个假阳性；方案B为每乳房体积3.6个假阳性；方案C为每乳房体积3个假阳性。
