发表机构
University of Augsburg（奥格斯堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出多源超声基准SADUSI，评估自监督异常检测方法，发现现有方法在跨解剖部位泛化上表现有限，揭示该领域开放挑战。
AI 中文摘要
自监督异常检测是医学超声领域中一种有前景的范式，因为正常图像通常比所有可能病理的详尽标注更容易获取。然而，大多数现有评估仅限于单一解剖部位或任务，这使得模型是学习了正常超声外观的稳健概念，还是仅学习了特定来源的表征，尚不明确。我们引入了SADUSI基准，这是一个多源超声数据集，旨在跨广泛的解剖区域、视图和采集协议训练和评估异常检测方法。SADUSI的目标是提供多样化的正常超声分布，以及一个可从单张图像评估的可见结构异常基准。我们评估了代表性的自监督异常检测方法，发现当前方法在此设置中表现不佳。特别是，基于重建的扩散方法（如AnoDDPM和DeCo-Diff）实现了像素级AUROC值0.56-0.72，最大F1分数0.10-0.26，表明病理与正常图像区域的分离有限。基于特征的PatchCore变体表现更好，达到像素级AUROC值0.76-0.83，但最大F1分数仍限于0.14-0.40。这些发现表明，广泛的多源超声异常检测仍是一个开放挑战，SADUSI可作为开发超越解剖特定设置泛化方法的资源。
英文摘要
Self-supervised anomaly detection is a promising paradigm for medical ultrasound, as normal images are often easier to obtain than exhaustive annotations of all possible pathologies. However, most existing evaluations are limited to a single anatomy or task, making it unclear whether models learn a robust notion of normal ultrasound appearance or only a source-specific representation. We introduce the SADUSI benchmark, a multi-source ultrasound dataset designed to train and evaluate anomaly detection methods across a broad range of anatomical regions, views, and acquisition protocols. The goal of SADUSI is to provide a diverse normal ultrasound distribution and a benchmark for visible structural anomalies that can be assessed from single images. We evaluate representative self-supervised anomaly detection methods and find that current approaches struggle in this setting. In particular, reconstruction-based diffusion methods such as AnoDDPM and DeCo-Diff achieve pixel-level AUROC values of 0.56-0.72 and maximum F1 scores of 0.10-0.26, indicating limited separation of pathology from normal image regions. Feature-based PatchCore variants perform better, reaching pixel-level AUROC values of 0.76-0.83, but remain limited with maximum F1 scores of 0.14-0.40. These findings suggest that broad multi-source ultrasound anomaly detection remains an open challenge and that SADUSI can serve as a resource for developing methods that generalize beyond anatomy-specific settings.
Comments7 pages, 3 figures
Journal ref2026 IEEE 9th International Conference on Multimedia Information Processing and Retrieval (MIPR), Bangkok, Thailand, 2026, pp. 340-346
DOI：10.1109/MIPR70517.2026.00061
