基于双模态互补深度学习网络整合注意力机制融合B型超声与剪切波弹性成像的乳腺癌诊断
回顾性分析218例患者的387对B型超声与剪切波弹性成像图像,构建双模态互补特征注意力网络(DCFAN),用于乳腺肿瘤良恶性分类及腋窝淋巴结转移预测。任务1中DCFAN准确率94.36%±1.45%、AUC最高0.97,特异度94.9%高于有经验放射科医师(p=0.002);任务2准确率91.70%±3.77%、平均AUC 0.83。双模态模型在两个任务中均显著优于单模态模型。
要点
- DCFAN融合B型超声结构特征与剪切波弹性成像硬度特征,任务1良恶性分类AUC达0.97。
- 任务1中DCFAN特异度94.9%,高于有经验放射科医师(p=0.002),F1分数亦高于两位医师。
- 任务2三分类(良性、恶性无腋窝淋巴结转移、恶性伴转移)准确率91.70%±3.77%,平均AUC 0.83。
核心结论
- DCFAN在乳腺肿瘤分类和腋窝淋巴结转移预测中均表现出优于现有CNN方法及放射科医师的性能,可能作为辅助工具提升乳腺超声诊断准确率。
研究设计与样本
- 回顾性分析218例患者的387对B型超声与剪切波弹性成像图像,构建双模态互补特征注意力网络(DCFAN),并与常规CNN模型及两位不同经验放射科医师比较。
诊断标准与关键数值
- 任务1(良恶性分类):DCFAN准确率94.36%±1.45%,AUC最高0.97,特异度94.9%。
- 任务2(良性、恶性无腋窝淋巴结转移、恶性伴腋窝淋巴结转移三分类):DCFAN准确率91.70%±3.77%,平均AUC 0.83。
- 任务1中DCFAN特异度94.9%高于有经验放射科医师,p=0.002。
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
OBJECTIVE: To develop and evaluate a Dual-modality Complementary Feature Attention Network (DCFAN) that integrates spatial and stiffness information from B-mode ultrasound and shear wave elastography (SWE) for improved breast tumor classification and axillary lymph node (ALN) metastasis prediction.
METHODS: A total of 387 paired B-mode and SWE images from 218 patients were retrospectively analyzed. The proposed DCFAN incorporates attention mechanisms to effectively fuse structural features from B-mode ultrasound with stiffness features from SWE. Two classification tasks were performed: (1) differentiating benign from malignant tumors, and (2) classifying benign tumors, malignant tumors without ALN metastasis, and malignant tumors with ALN metastasis. Model performance was assessed using accuracy, sensitivity, specificity, and AUC, and compared with conventional CNN-based models and two radiologists with varying experience.
RESULTS: In Task 1, DCFAN achieved an accuracy of 94.36% ± 1.45% and the highest AUC of 0.97. In Task 2, it attained 91.70% ± 3.77% accuracy and an average AUC of 0.83. The multimodal approach significantly outperformed the single-modality models in both tasks. Notably, in Task 1, DCFAN demonstrated higher specificity (94.9%) compared to the experienced radiologist (p = 0.002), and yielded higher F1-scores than both radiologists. It also outperformed several state-of-the-art deep learning models in diagnostic accuracy.
CONCLUSIONS: DCFAN demonstrated robust and superior performance over existing CNN-based methods and radiologists in both breast tumor classification and ALN metastasis prediction. This approach may serve as a valuable assistive tool to enhance diagnostic accuracy in breast ultrasound.
引用
- Dong L, Cai X, Ge H, et al. Breast Cancer Diagnosis Using a Dual-Modality Complementary Deep Learning Network With Integrated Attention Mechanism Fusion of B-Mode Ultrasound and Shear Wave Elastography. Ultrasound Med Biol. 2025. PMID: 40858483. doi:10.1016/j.ultrasmedbio.2025.08.007
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。