用兴趣区域增强提升乳腺摄影分类，无需额外标注
Region-of-Interest Augmentation for Mammography Classification under Patient-Level Cross-Validation
- 从预存框中随机裁剪兴趣区替换原图，训练时增强数据多样性
- 在迷你DDSM数据集上平均提升ROC-AUC，PR-AUC基本持平或略降
- 轻量级方案，不增加推理开销，适合小样本医学图像任务
乳腺癌筛查中，乳腺摄影仍是早期发现与降低死亡率的核心手段。深度学习在自动化解读方面展现出强大潜力，但受限于低分辨率数据集和小样本，性能仍受制约。我们重新评估了Mini-DDSM数据集（9,684张图像；2,414名患者），提出一种轻量级的感兴趣区域（ROI）增强策略。训练时，全图以概率方式被来自预先构建的无标签边界框库的随机ROI裁剪替代，可选抖动进一步提升变异性。在严格的患者级别交叉验证下评估，报告了ROC-AUC、PR-AUC及训练效率指标（吞吐量与GPU内存占用）。由于ROI增强仅用于训练，推理成本不变。在Mini-DDSM上，最佳设置（p_roi=0.10, alpha=0.10）带来适度的平均ROC-AUC提升，各折叠间表现有差异；而PR-AUC基本持平或略有下降。结果表明，无需额外标注或模型修改，简单的数据驱动式ROI策略即可在资源受限场景下提升乳腺摄影分类效果。
原文摘要 · Abstract (English)
Breast cancer screening with mammography remains central to early detection and mortality reduction. Deep learning has shown strong potential for automating mammogram interpretation, yet limited-resolution datasets and small sample sizes continue to restrict performance. We revisit the Mini-DDSM dataset (9,684 images; 2,414 patients) and introduce a lightweight region-of-interest (ROI) augmentation strategy. During training, full images are probabilistically replaced with random ROI crops sampled from a precomputed, label-free bounding-box bank, with optional jitter to increase variability. We evaluate under strict patient-level cross-validation and report ROC-AUC, PR-AUC, and training-time efficiency metrics (throughput and GPU memory). Because ROI augmentation is training-only, inference-time cost remains unchanged. On Mini-DDSM, ROI augmentation (best: p_roi = 0.10, alpha = 0.10) yields modest average ROC-AUC gains, with performance varying across folds; PR-AUC is flat to slightly lower. These results demonstrate that simple, data-centric ROI strategies can enhance mammography classification in constrained settings without requiring additional labels or architectural modifications.
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。