An Jiancheng, Yu Hui, Bai Ru, Li Jintong, Wang Yue, Cao Rui
College of Software, Taiyuan University of Technology, Taiyuan, China.
Methods. 2022 Jun;202:54-61. doi: 10.1016/j.ymeth.2021.04.022. Epub 2021 Apr 27.
In breast mass detection, there are many different sizes of masses in the image. However, when the existing target detection model is directly used to detect the breast mass, it is easy to appear the phenomenon of misdetection and missed detection. Therefore, in order to improve the detection accuracy of breast masses, this paper proposed a target detection model D-Mask R-CNN based on Mask R-CNN, which is suitable for breast masses detection. Firstly, this paper improved the internal structure of FPN, and modified the lateral connection mode in the original FPN structure to dense connection. Secondly, modified the size of the anchor of RPN to improve the location accuracy of breast masses. Finally, Soft-NMS was used to replace the NMS in the original model to reduce the possibility that the correct prediction results may be eliminated during the NMS process. This paper used the CBIS-DDSM dataset for all experiments. The results showed that the mAP value of the improved model for detecting breast masses reached 0.66 in the test set, which was 0.05 higher than that of the original Mask R-CNN.
在乳腺肿块检测中，图像中存在许多不同大小的肿块。然而，当直接使用现有的目标检测模型来检测乳腺肿块时，很容易出现误检和漏检现象。因此，为了提高乳腺肿块的检测精度，本文提出了一种基于Mask R-CNN的目标检测模型D-Mask R-CNN，适用于乳腺肿块检测。首先，本文改进了FPN的内部结构，将原始FPN结构中的横向连接方式修改为密集连接。其次，修改了RPN的锚点大小，以提高乳腺肿块的定位精度。最后，使用Soft-NMS代替原始模型中的NMS，以减少在NMS过程中正确预测结果可能被消除的可能性。本文使用CBIS-DDSM数据集进行所有实验。结果表明，改进后的模型在测试集中检测乳腺肿块的mAP值达到0.66，比原始Mask R-CNN高0.05。
