Gui Haitian, Su Tao, Jiang Xinhua, Li Li, Xiong Lang, Zhou Ji, Pang Zhiyong
School of Biomedical Engineering, Shenzhen Campus of Sun Yat-Sen University, Shenzhen 518107, China (H.G.).
School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, China (T.S., Z.P.).
Acad Radiol. 2025 Mar;32(3):1228-1240. doi: 10.1016/j.acra.2024.09.048. Epub 2024 Oct 15.
Breast cancer screening is critical for reducing mortality rates. YOLOv9, a new real-time object-detection model, is ideal for cancer screening. A customized YOLOv9 model with enhancements for detecting breast cancer on the basis of species and morphological diversity has potential clinical significance.
The internal dataset consisted of 687 cases split 3:1 for cross-validation. Additionally, 98 cases from external datasets were used for testing. We developed an FS-YOLOv9 model customized for breast cancer detection that incorporated an extra max-pooling layer before the Conv1 of the Adown to enhance high-brightness features. The Adown of the P3 in the backbone was replaced with a high-frequency Haar wavelet convolution kernel, which ignored the low-frequency components during down-sampling to enhance morphology and texture features. The reliability and robustness of our model was determined by measuring the F1 score, the area under curve of free-response receiver operating characteristic (FAUC), mean average precision (mAP), recall, and precision, and comparing them with the findings for the official YOLOv9, YOLOv8, YOLOv5 models.
In comparison with the official YOLOv9 model, FS-YOLOv9 showed a higher average F1 score (0.700 vs. 0.669), FAUC (0.695 vs. 0.662), and mAP50 (0.713 vs. 0.679) in the internal dataset; in the external testing dataset, the FS-YOLOv9 improved the average F1 score, FAUC, and mAP50 by 4.58%, 5.78%, and 4.41% respectively.
Our FS-YOLOv9 model showed significantly improved performance in detecting breast cancer, making it more practical for high-risk breast cancer diagnosis.
乳腺癌筛查对于降低死亡率至关重要。YOLOv9是一种新型实时目标检测模型，非常适合癌症筛查。基于物种和形态多样性进行增强的定制化YOLOv9模型在乳腺癌检测方面具有潜在的临床意义。
内部数据集由687例病例组成，按3:1划分用于交叉验证。此外，还使用了来自外部数据集的98例病例进行测试。我们开发了一种专为乳腺癌检测定制的FS-YOLOv9模型，该模型在Adown的Conv1之前加入了一个额外的最大池化层，以增强高亮度特征。主干中P3的Adown被高频哈尔小波卷积核取代，该卷积核在降采样过程中忽略低频分量，以增强形态和纹理特征。通过测量F1分数、自由响应接收器操作特征曲线下面积（FAUC）、平均精度均值（mAP）、召回率和精确率，并将其与官方YOLOv9、YOLOv8、YOLOv5模型的结果进行比较，来确定我们模型的可靠性和稳健性。
与官方YOLOv9模型相比，FS-YOLOv9在内部数据集中显示出更高的平均F1分数（0.700对0.669）、FAUC（0.695对0.662）和mAP50（0.713对0.679）；在外部测试数据集中，FS-YOLOv9的平均F1分数、FAUC和mAP50分别提高了4.58%、5.78%和4.41%。
我们的FS-YOLOv9模型在乳腺癌检测中表现出显著提高的性能，使其在高危乳腺癌诊断中更具实用性。
