文献速递乳腺技术与安全US

利用特征融合与注意力机制的深度学习改进超声图像乳腺癌诊断

Improving Breast Cancer Diagnosis in Ultrasound Images Using Deep Learning with Feature Fusion and Attention Mechanism.
PubMed 文献 · Acad Radiol · 2025-05-27

研究提出基于特征融合与注意力机制的深度学习模型,用于超声图像乳腺良恶性病变分类。在自建数据集(1758例患者2171张图像)上AUC为0.9320,在公开BUSI数据集(780张图像)上AUC为0.9834,表现优于传统深度卷积神经网络模型和不同经验水平的放射科医生。

要点

  • 模型在自建数据集上AUC为0.9320,在公开BUSI数据集上AUC为0.9834,均优于传统深度卷积神经网络模型。
  • 模型诊断表现超过不同经验水平的放射科医生,提示其作为医学图像分类辅助工具的潜力。
  • Grad-CAM、Saliency Maps和SHAP等可解释性技术可展示模型决策所关注的图像特征。

核心结论

  • 所提出的深度学习模型在超声图像乳腺良恶性病变分类中准确率优于传统模型和放射科医生,结合可解释性技术,展示其作为可靠高效医学诊断工具的潜力。

研究设计与样本

  • 研究论文;自建临床数据集包含2020年12月至2024年5月期间1758例患者的2171张超声图像;公开BUSI数据集包含2018年采集的780张女性患者(年龄25至75岁)图像;模型采用MobileNetV2和DenseNet121架构,结合特征融合与注意力机制;并与不同经验水平的放射科医生进行对比分析。

诊断标准与关键数值

  • 自建数据集上模型AUC为0.9320,公开BUSI数据集上AUC为0.9834;模型性能显著优于传统深度卷积神经网络模型,并超过放射科医生的诊断表现。

临床应用与阅片要点

  • Grad-CAM、Saliency Maps和SHAP等可解释性技术可展示模型决策所关注的图像特征,有助于理解模型分类依据;原文未据此给出临床推荐。

局限性

  • 原文未报告局限性。

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

RATIONALE AND OBJECTIVES: Early detection of malignant lesions in ultrasound images is crucial for effective cancer diagnosis and treatment. While traditional methods rely on radiologists, deep learning models can improve accuracy, reduce errors, and enhance efficiency. This study explores the application of a deep learning model for classifying benign and malignant lesions, focusing on its performance and interpretability.

MATERIALS AND METHODS: In this study, we proposed a feature fusion-based deep learning model for classifying benign and malignant lesions in ultrasound images. The model leverages advanced architectures such as MobileNetV2 and DenseNet121, enhanced with feature fusion and attention mechanisms to boost classification accuracy. The clinical dataset comprises 2171 images collected from 1758 patients between December 2020 and May 2024. Additionally, we utilized the publicly available BUSI dataset, consisting of 780 images from female patients aged 25 to 75, collected in 2018. To enhance interpretability, we applied Grad-CAM, Saliency Maps, and shapley additive explanations (SHAP) techniques to explain the model's decision-making. A comparative analysis with radiologists of varying expertise levels is also conducted.

RESULTS: The proposed model exhibited the highest performance, achieving an AUC of 0.9320 on our private dataset and an area under the curve (AUC) of 0.9834 on the public dataset, significantly outperforming traditional deep convolutional neural network models. It also exceeded the diagnostic performance of radiologists, showcasing its potential as a reliable tool for medical image classification. The model's success can be attributed to its incorporation of advanced architectures, feature fusion, and attention mechanisms. The model's decision-making process was further clarified using interpretability techniques like Grad-CAM, Saliency Maps, and SHAP, offering insights into its ability to focus on relevant image features for accurate classification.

CONCLUSION: The proposed deep learning model offers superior accuracy in classifying benign and malignant lesions in ultrasound images, outperforming traditional models and radiologists. Its strong performance, coupled with interpretability techniques, demonstrates its potential as a reliable and efficient tool for medical diagnostics.

DATA AVAILABILITY: The datasets generated and analyzed during the current study are not publicly available due to the nature of this research and participants of this study, but may be available from the corresponding author on reasonable request.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Asif S, Yan Y, Feng B, et al. Improving Breast Cancer Diagnosis in Ultrasound Images Using Deep Learning with Feature Fusion and Attention Mechanism. Acad Radiol. 2025. PMID: 40436710. doi:10.1016/j.acra.2025.05.007

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。