用注意力增强的深度学习模型，自动区分乳腺密度高低。
Attention-Enhanced Deep Learning Ensemble for Breast Density Classification in Mammography
- 四款CNN模型结合通道注意力机制，提升特征捕捉能力。
- 新提出的损失函数使准确率达AUC 0.963，F1分数0.952。
- 适合临床辅助诊断，减少医生间判断差异。
乳腺密度评估是乳腺钼靶影像解读的关键环节，高密度（BI-RADS分类C和D）既是乳腺癌的重要风险因素，也给肿瘤检测带来技术挑战。本研究提出一种自动化深度学习系统，基于VinDr-Mammo数据集实现乳腺密度二分类（低：A/B vs. 高：C/D）。对比了四种先进卷积神经网络：ResNet18、ResNet50、EfficientNet-B0与DenseNet121，均引入通道注意力机制。为应对类别不平衡问题，设计了一种新型组合焦点标签平滑损失函数，融合焦点损失、标签平滑与类别平衡权重。预处理流程包含对比度受限自适应直方图均衡化（CLAHE）及全面的数据增强。通过优化的集成投票方法融合各模型，性能优于任一单个模型（AUC: 0.963，F1-score: 0.952）。该系统具有显著潜力，可标准化临床密度评估，提升筛查效率与早期癌症检出率，降低放射科医生间的判读差异。
原文摘要 · Abstract (English)
Breast density assessment is a crucial component of mammographic interpretation, with high breast density (BI-RADS categories C and D) representing both a significant risk factor for developing breast cancer and a technical challenge for tumor detection. This study proposes an automated deep learning system for robust binary classification of breast density (low: A/B vs. high: C/D) using the VinDr-Mammo dataset. We implemented and compared four advanced convolutional neural networks: ResNet18, ResNet50, EfficientNet-B0, and DenseNet121, each enhanced with channel attention mechanisms. To address the inherent class imbalance, we developed a novel Combined Focal Label Smoothing Loss function that integrates focal loss, label smoothing, and class-balanced weighting. Our preprocessing pipeline incorporated advanced techniques, including contrast-limited adaptive histogram equalization (CLAHE) and comprehensive data augmentation. The individual models were combined through an optimized ensemble voting approach, achieving superior performance (AUC: 0.963, F1-score: 0.952) compared to any single model. This system demonstrates significant potential to standardize density assessments in clinical practice, potentially improving screening efficiency and early cancer detection rates while reducing inter-observer variability among radiologists.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。