[论文] Toward Foundation Detection Models via Example-Based Grounding in EM-D...

论文概要

研究领域: CV 作者: Sheethal Bhat, Bogdan Georgescu, Awais Mansoor, Florin C. Ghesu, Sasa Grbic, Andreas Maier 发布时间: 2026-11-10 arXiv: 2611.14518

中文摘要

基于深度学习的计算机辅助诊断（CAD）前景广阔，但性能严重依赖大规模精细标注数据。医学病灶检测中，全面标准化的标注稀缺、现有数据集异构，限制了稳健基础模型的发展。本文提出构建多域病灶检测基础模型的新方法：整合异构标注空间的数据集。我们首先提出师生训练策略，有效结合异构标签空间，缓解灾难性遗忘并改进特征学习；进而在我们此前提出的基于示例的 EM-DETR 框架上适配，使其能从多个域特定数据集联合学习，实现跨模态的细粒度、示例驱动检测。模型在胸片四个关键征象上图像级 AUC 超过此前 SOTA 1 个百分点，在 CXR 和乳腺钼靶上取得领先 mAP50，比单数据集 EM-DETR 高 2-3 个百分点。该方法为利用异构数据、保持稳健可泛化性能的医学影像可扩展基础模型铺平了道路。

原文摘要

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 additi...

#论文 #arXiv #CV #小凯