Chan Heang-Ping, Wei Jun, Sahiner Berkman, Rafferty Elizabeth A, Wu Tao, Roubidoux Marilyn A, Moore Richard H, Kopans Daniel B, Hadjiiski Lubomir M, Helvie Mark A
Department of Radiology, University of Michigan, 1500 E Medical Center Dr, UHB1F510B, Ann Arbor, MI 48109-0030, USA.
Radiology. 2005 Dec;237(3):1075-80. doi: 10.1148/radiol.2373041657. Epub 2005 Oct 19.
The purpose of the study was to design a computer-aided detection (CAD) system for breast mass detection on digital breast tomosynthesis (DBT) mammograms and to perform a preliminary evaluation of the performance of this system. Twenty-six patients were imaged with a prototype DBT system. Institutional review board approval and written informed patient consent were obtained. Use of the data set in this study was HIPAA compliant. The CAD system first screened the three-dimensional volume of the mass candidates by means of gradient-field analysis. Each mass candidate was segmented from the structured background, and its image features were extracted. A feature classifier was designed to differentiate true masses from normal tissues. The CAD system was trained and tested by using a leave-one-case-out method. The classifier calculated a mean area under the test receiver operating characteristic curve of 0.91 +/- 0.03 (standard error of mean). The CAD system achieved a sensitivity of 85%, with 2.2 false-positive objects per case. The results demonstrate the feasibility of the authors' approach to the development of a CAD system for DBT mammography.
本研究的目的是设计一种用于数字乳腺断层合成（DBT）乳房X光片上乳腺肿块检测的计算机辅助检测（CAD）系统，并对该系统的性能进行初步评估。26名患者使用原型DBT系统进行了成像。获得了机构审查委员会的批准和患者的书面知情同意。本研究中数据集的使用符合健康保险流通与责任法案（HIPAA）规定。CAD系统首先通过梯度场分析对肿块候选者的三维体积进行筛选。从结构化背景中分割出每个肿块候选者，并提取其图像特征。设计了一个特征分类器来区分真正的肿块与正常组织。CAD系统采用留一法进行训练和测试。该分类器计算出测试接收器操作特征曲线下的平均面积为0.91±0.03（平均标准误差）。CAD系统的灵敏度达到85%，每个病例有2.2个假阳性物体。结果证明了作者开发用于DBT乳房X光摄影的CAD系统方法的可行性。
