基于范例的、使用最少标注的鲁棒异常检测：Exemplar Med-DETR

中文摘要 AI 辅助

减少标注需求仍是开发鲁棒医学目标检测器的关键挑战。为解决该问题，视觉-语言（VL）目标检测方法利用 grounding 文本信息，在自然图像领域实现了强大的零样本和少样本目标检测器[1,2,3,4]。然而，将这些方法迁移至医学领域颇具挑战性，因为医学领域缺乏质量与数量相当的 grounding 数据；尽管如此，医学图像中存在大量未被充分利用的上下文及非成像信息。少样本学习（FSL）技术可部分缓解这一局限，但难以泛化至未见的医学发现，且引入新发现时需大量重新训练[5,6]。为克服这些挑战，我们扩展了先前的 EM-DETR 框架[7]，提出一种可扩展的少样本（FS）检测方法，旨在在极少监督下高效完成胸部 X 射线（CXR）图像的异常检测。所提架构融合了基于范例的特征生成与领域感知对比优化，无需 exhaustive 重新训练即可有效适配新疾病发现。我们的方法使用不足 10% 的标注数据即可达到接近当前最优（SOTA）的检测性能，展现出其在专有及公开 CXR 数据集上实现实用、标注高效的临床部署的潜力。

英文摘要

Reducing annotation requirements remains a key challenge in developing robust medical object detectors. To address this, Vision-Language (VL) object detection methods leverage grounding text information to enable powerful zero-shot and few-shot object detectors in the natural image domain [1, 2, 3, 4]. However, transferring these methods to the medical domain is challenging due to the absence of comparable quality and quantity of the grounding data. Regardless, significant contextual and non-imaging information exists in medical images that remains underutilized. Few-shot learning (FSL) techniques partially address this limitation but struggle to general ize to unseen medical findings and require extensive retraining when new findings are introduced [5, 6]. To overcome these challenges, we extend our prior EM-DETR framework [7] and introduce a scalable FS detection approach designed for efficient abnormality detection in Chest X-Ray (CXR) images under minimal supervision. The proposed architecture incorporates exemplar-based feature generation and domain-aware contrastive optimization, enabling effective adaptation to novel disease findings without exhaustive retraining. Our method achieves near state-of-the-art (SOTA) detection performance using less than 10% of the annotated data, demonstrating its potential for practical, annotation-efficient clinical deployment across both proprietary and public CXR datasets.

发表机构

• Friedrich-Alexander-Universität（弗里德里希-亚历山大大学）
• Siemens Healthineers（西门子医疗）
• Siemens Medical Solutions（西门子医疗解决方案）

机构由 AI 辅助整理，请以论文原文为准。