Digital breast tomosynthesis (DBT) is a newly developed three-dimensional tomographic imaging modality in the field of breast cancer screening designed to alleviate the limitations of conventional digital mammography-based breast screening methods. A computer-aided detection (CAD) system was designed for masses in DBT using a faster region-based convolutional neural network (faster-RCNN). To this end, a data set was collected, including 89 patients with 105 masses. An efficient detection architecture of convolution neural network with a region proposal network (RPN) was used for each slice to generate region proposals (i.e., bounding boxes) with a mass likelihood score. In each DBT volume, a slice fusion procedure was used to merge the detection results on consecutive 2D slices into one 3D DBT volume. The performance of the CAD system was evaluated using free-response receiver operating characteristic (FROC) curves. Our RCNN-based CAD system was compared with a deep convolutional neural network (DCNN)-based CAD system. The RCNN-based CAD generated a performance with an area under the ROC (AUC) of 0.96, whereas the DCNN-based CAD achieved a performance with AUC of 0.92. For lesion-based mass detection, the sensitivity of RCNN-based CAD was 90% at 1.54 false positive (FP) per volume, whereas the sensitivity of DCNN-based CAD was 90% at 2.81 FPs/volume. For breast-based mass detection, RCNN-based CAD generated a sensitivity of 90% at 0.76 FP/breast, which is significantly increased compared with the DCNN-based CAD with a sensitivity of 90% at 2.25 FPs/breast. The results suggest that the faster R-CNN has the potential to augment the prescreening and FP reduction in the CAD system for masses.

中文翻译：

---

使用更快的基于区域的卷积神经网络计算机辅助检测数字乳房断层合成中的质量

数字乳房断层扫描 (DBT) 是乳腺癌筛查领域新开发的一种三维断层扫描成像方式，旨在减轻传统的基于数字乳房 X 光检查的乳房筛查方法的局限性。使用更快的基于区域的卷积神经网络 (faster-RCNN) 为 DBT 中的质量设计了计算机辅助检测 (CAD) 系统。为此，收集了一个数据集，包括 89 名患者，105 个肿块。对每个切片使用具有区域提议网络（RPN）的卷积神经网络的高效检测架构来生成具有质量似然分数的区域提议（即边界框）。在每个 DBT 体积中，使用切片融合程序将连续 2D 切片上的检测结果合并为一个 3D DBT 体积。使用自由响应接收器操作特性 (FROC) 曲线评估 CAD 系统的性能。我们基于 RCNN 的 CAD 系统与基于深度卷积神经网络 (DCNN) 的 CAD 系统进行了比较。基于 RCNN 的 CAD 产生的 ROC 下面积 (AUC) 为 0.96，而基于 DCNN 的 CAD 实现了 AUC 为 0.92 的性能。对于基于病变的肿块检测，基于 RCNN 的 CAD 在每体积 1.54 假阳性 (FP) 时的灵敏度为 90%，而基于 DCNN 的 CAD 在每体积 2.81 FPs 时的灵敏度为 90%。对于基于乳房的肿块检测，基于 RCNN 的 CAD 在 0.76 FP/breast 时产生了 90% 的灵敏度，与基于 DCNN 的 CAD 在 2.25 FPs/breast 时的灵敏度为 90% 相比显着提高。