可解释WinDWS-SwinNet超声深度影像组学用于乳腺多病理分类
本研究基于五个中心/数据库的3256张乳腺超声图像(活检证实良性2068例、恶性1188例),开发可解释注意力深度网络WinDWS-SwinNet进行分类。模型对乳腺良恶性二分类曲线下面积达0.96,测试准确率95.79%;多病理分类测试准确率93%,外部独立验证集准确率95.36%。
要点
- 该模型对恶性病变敏感度90.86%,对良性病变敏感度98.51%,可用于辅助减少良恶性判定不确定性。
- 多病理分类各类别准确率范围为94%至99.5%,提示对乳腺病变亚型区分有潜在辅助价值。
- 外部独立数据集准确率95.36%,显示模型泛化性较好,但临床部署前仍需本地数据验证。
核心结论
- WinDWS-SwinNet在乳腺超声图像良恶性分类中曲线下面积达0.96,测试准确率95.79%,外部独立验证准确率95.36%。
- 多病理分类测试准确率为93%,各类别准确率范围94%至99.5%,显示该网络对乳腺病变病理亚型区分具有潜力。
研究设计与样本
- 研究类型为多中心回顾性研究,数据来自五个不同中心/数据库,共3256张乳腺超声图像。
- 样本包括活检证实的2068例良性病变和1188例恶性病变,采用自研WinDWS-SwinNet轻量级注意力网络分析。
- 提出优化图像预处理算法以增强超声影像组学特征;参考标准为活检病理结果。
诊断标准与关键数值
- 二分类良性组:精确度95.11%,敏感度98.51%;恶性组:精确度97.13%,敏感度90.86%。
- 二分类总测试准确率95.79%,曲线下面积0.96;多病理分类测试准确率93%,各类别准确率94%–99.5%。
- 外部独立验证集准确率95.36%,用于评估模型泛化能力;原文未报告置信区间及P值。
临床应用与阅片要点
- 该模型以超声图像为输入,可模拟乳腺病变多病理分型的诊断工作流程,辅助放射科医生降低诊断不确定性。
- 良性组敏感度较高,适合作为低风险病变筛查辅助以减少不必要的活检;恶性组精确度较高,阳性预测更可靠。
- 阅片时应将模型输出作为第二意见,并结合形态、回声、边界等常规超声征象综合判断。
局限性
- 研究为回顾性设计,多中心数据来源可能存在图像采集协议和设备差异。
- 原文未报告置信区间及统计显著性检验结果,诊断效能的估计精度不确定。
- 外部验证仅在一个独立数据集进行,对更广泛临床场景的泛化性仍需进一步验证。
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: Timely and accurate characterization of breast lesions into different pathological classes through noninvasive imaging techniques is crucial for early cancer diagnosis and effective patient management. This study aims to develop a novel, explainable attention-based deep network to analyze radiomic patterns for predicting heterogeneous breast cancer types using ultrasound imaging.
MATERIALS AND METHODS: A multicentric retrospective dataset comprises brightness-mode ultrasound images of breast tissue collected across five different centers/databases. A total of 3256 images, having biopsy-proven 2068 benign and 1188 malignant lesions, were analyzed. A lightweight and computationally scalable network, WinDWS-SwinNet, is developed for binary and multipathology breast cancer classification. An optimized image preprocessing algorithm is proposed to enhance ultrasound radiomic features, thereby improving data generalizability and diagnostic accuracy.
RESULTS: The WinDWS-SwinNet architecture demonstrated superior performance in breast cancer classification, achieving an area under the curve of 0.96, an overall test accuracy of 95.79%, and robust class-wise results with 95.11% precision and 98.51% sensitivity for benign tumors and 97.13% precision and 90.86% sensitivity for malignant tumors. For multipathology classification, the model achieved a test accuracy of 93%, with class-wise accuracies ranging from 94% to 99.5%. External validation on the independent unseen dataset resulted in an accuracy of 95.36%, highlighting the robustness and generalizability of the proposed model beyond the training data.
CONCLUSION: The developed methodology shows promising results in characterizing breast lesions into pathological subtypes noninvasively, effectively mimicking real-world diagnostic workflows, thereby supporting radiologists in reducing diagnostic uncertainty and enhancing confidence in clinical decision-making.
引用
- Sharma, Chauhan. Explainable WinDWS-SwinNet: Optimizing Ultrasound Deep Radiomics for Multipathology Breast Lesion Classification. Acad Radiol. 2026. PMID: 42926176. doi:10.1016/j.acra.2026.10.003
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。