文献速递乳腺US

DGANet:用于超声图像乳腺病灶检测的双全局注意力神经网络

DGANet: A Dual Global Attention Neural Network for Breast Lesion Detection in Ultrasound Images.
PubMed 文献 · Ultrasound Med Biol · 2022-10-04

研究提出双全局注意力神经网络DGANet,通过双边空间注意力模块和全局通道注意力模块增强特征,在自建7040张超声图像数据集和公开乳腺超声数据集上进行乳腺病灶检测实验。以YOLOv3、RetinaNet、Faster R-CNN、YOLOv5和YOLOX为对比模型,DGANet在总平均精度均值上优于对比方法0.2%–5.9%。

要点

  • DGANet通过空间与通道双注意力增强超声乳腺病灶特征。
  • 在7040张自建超声图像上验证,总mAP优于五种对比模型0.2%–5.9%。
  • 该网络旨在为放射科医生提供客观的乳腺病灶检测建议。

核心结论

  • DGANet在乳腺超声病灶检测中总平均精度均值优于YOLOv3、RetinaNet、Faster R-CNN、YOLOv5和YOLOX。

研究设计与样本

  • 研究为深度学习模型开发与实验验证,使用自建7040张乳腺超声图像数据集和公开乳腺超声图像数据集,以YOLOv3、RetinaNet、Faster R-CNN、YOLOv5和YOLOX为对比模型。

诊断标准与关键数值

  • DGANet相比对比模型在总平均精度均值上提升0.2%–5.9%,具体敏感度、特异度、AUC及阈值原文未报告。

临床应用与阅片要点

  • 该模型可作为乳腺超声病灶检测的计算机辅助工具,为阅片提供客观参考建议。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Deep learning-based breast lesion detection in ultrasound images has demonstrated great potential to provide objective suggestions for radiologists and improve their accuracy in diagnosing breast diseases. However, the lack of an effective feature enhancement approach limits the performance of deep learning models. Therefore, in this study, we propose a novel dual global attention neural network (DGANet) to improve the accuracy of breast lesion detection in ultrasound images. Specifically, we designed a bilateral spatial attention module and a global channel attention module to enhance features in spatial and channel dimensions, respectively. The bilateral spatial attention module enhances features by capturing supporting information in regions neighboring breast lesions and reducing integration of noise signal. The global channel attention module enhances features of important channels by weighted calculation, where the weights are decided by the learned interdependencies among all channels. To verify the performance of the DGANet, we conduct breast lesion detection experiments on our collected data set of 7040 ultrasound images and a public data set of breast ultrasound images. YOLOv3, RetinaNet, Faster R-CNN, YOLOv5, and YOLOX are used as comparison models. The results indicate that DGANet outperforms the comparison methods by 0.2%-5.9% in total mean average precision.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Meng, Liu, Niu, et al. DGANet: A Dual Global Attention Neural Network for Breast Lesion Detection in Ultrasound Images. Ultrasound Med Biol. 2022. PMID: 36202677. doi:10.1016/j.ultrasmedbio.2022.07.006

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。