EM-DETR 基础模型：多数据集联合训练提升医学病灶检测
Toward Foundation Detection Models via Example-Based Grounding in EM-DETR
医学影像检测一直被数据标注不一致卡着，这篇把 EM-DETR 扩成多数据集基础模型，胸片 AUC 涨了 1 个点，mAP50 比单数据集高 2-3 个点。做医学 AI 的研究者可以看看 student-teacher 那套融合异构标签的思路。
一篇 arXiv 论文提出在 EM-DETR 框架上构建医学影像病灶检测基础模型的方法，目标是解决医学标注数据稀缺、数据集异构的问题。核心是先设计 student-teacher 训练策略，把标注体系不一致的多个数据集整合起来联合训练，缓解灾难性遗忘并改善特征学习。
在此基础上，作者将此前提出的 example-based EM-DETR 扩展为同时从多个领域数据集学习，实现跨模态（如胸片 CXR 与乳腺钼靶）的细粒度、样例驱动检测。成绩方面，图像级 AUC 在 CXR 四类关键病灶上超过此前 SOTA 1 个百分点；mAP50 在 CXR 和乳腺钼靶上领先，比只用单一数据集训练的 EM-DETR 高出 2-3 个百分点。
这条路线的意义在于：用异构数据训出可泛化的医学检测基础模型，不必依赖单一大型标注数据集，对做医学影像 CAD 系统的团队有直接参考价值。
Toward Foundation Detection Models via Example-Based Grounding in EM-DETR
DeepLearning (DL)-based Computer-Aided Diagnostic (CAD) systems have shown great promise in supporting clinicians, but their performance heavily depends on the availability of large, well-annotated datasets. In medical lesion detection, the scarcity of comprehensive, stan dardized annotations and the heterogeneity of existing datasets limit the development of robust foundation models. In this work, we introduce a novel approach to building a multi-domain foundation model for le sion detection by integrating diverse medical image datasets annotated for both anatomical structures and abnormalities. We first propose a student-teacher training strategy to effectively combine datasets with heterogeneous label spaces, mitigating catastrophic forgetting, and im proving feature learning. In addition, building on our previously pro posed example-based EM-DETR framework, we adapt it to jointly learn from multiple domain-specific datasets, enabling fine-grained, example driven detection across modalities. Our model achieves state-of-the-art (SOTA) results, with image-level AUC scores exceeding previous SOTA by 1% point on four key findings in CXRs. We achieve a leading mAP50 in CXRs and mammography, surpassing EM-DETR trained on a single dataset by 2-3% points. This approach paves the way for scalable foundation models in medical imaging that leverage heterogeneous data while maintaining robust and generalizable performance.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include EM-DETR, 医学影像, 病灶检测, student-teacher.
Source attribution: curated from arXiv cs.AI (@Sheethal Bhat, Bogdan Georgescu, Awais Mansoor, Florin C. Ghesu, Sasa Grbic, Andreas Maier).