Liu Weixiang, Zeng Pengcheng, Jiang Jiale, Chen Jingyang, Chen Linghao, Hu Chuting, Jian Wenjing, Diao Xianfen, Wang Xianming
College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China.
School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, Guangdong, China; National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Shenzhen University, Shenzhen 518060, Guangdong, China; Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Shenzhen University, Shenzhen 518060, Guangdong, China.
Comput Methods Programs Biomed. 2024 Jun;251:108211. doi: 10.1016/j.cmpb.2024.108211. Epub 2024 May 3.
Mammography screening is instrumental in the early detection and diagnosis of breast cancer by identifying masses in mammograms. With the rapid development of deep learning, numerous deep learning-based object detection algorithms have been explored for mass detection studies. However, these methods often yield a high false positive rate per image (FPPI) while achieving a high true positive rate (TPR). To maintain a higher TPR while also ensuring lower FPPI, we improved the Probability Anchor Assignment (PAA) algorithm to enhance the detection capability for mammographic characteristics with our previous work. We considered three dimensions: the backbone network, feature fusion module, and dense detection heads. The final experiment showed the effectiveness of the proposed method, and the TPR/FPPI values of the final improved PAA algorithm were 0.96/0.56 on the INbreast datasets. Compared to other methods, our method stands distinguished with its effectiveness in addressing the imbalance between positive and negative classes in cases of single lesion detection.
乳腺钼靶筛查通过识别钼靶图像中的肿块，对乳腺癌的早期检测和诊断具有重要作用。随着深度学习的快速发展，人们探索了许多基于深度学习的目标检测算法用于肿块检测研究。然而，这些方法在实现高真阳性率（TPR）的同时，往往每张图像产生较高的假阳性率（FPPI）。为了在保持较高TPR的同时确保较低的FPPI，我们改进了概率锚点分配（PAA）算法，以增强我们之前工作中对乳腺钼靶特征的检测能力。我们考虑了三个维度：骨干网络、特征融合模块和密集检测头。最终实验表明了所提方法的有效性，最终改进的PAA算法在INbreast数据集上的TPR/FPPI值为0.96/0.56。与其他方法相比，我们的方法在解决单病变检测中正负类不平衡问题方面的有效性显著。
