A Multi-Source Ultrasound Benchmark Revealing the Limits of Contemporary Self-Supervised Anomaly Detection Methods

2026-10-07

AI Summary

This study addresses the limitation of existing ultrasound anomaly detection evaluations, which are typically confined to single anatomical structures and hinder robustness validation. To this end, we introduce SADUSI, a multi-source ultrasound benchmark dataset encompassing diverse anatomical regions and acquisition protocols, providing varied normal distributions alongside single-image visible anomalies. Leveraging self-supervised learning paradigms, we systematically compare diffusion-based reconstruction models, such as AnoDDPM, against feature-matching approaches, specifically PatchCore variants. Experimental results reveal that diffusion models yield suboptimal performance, while PatchCore achieves comparatively better yet still limited F1 scores. These findings expose significant deficiencies in current methodologies when applied to multi-source scenarios, confirming that multi-source ultrasound anomaly detection remains an open and pressing challenge requiring further investigation.

Abstract

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.

Problem

• self-supervised anomaly detection
• medical ultrasound
• multi-source benchmark
• generalization
• structural anomalies

Innovation

• Self-supervised anomaly detection
• Multi-source ultrasound benchmark
• Diffusion models
• Feature-based methods
• Generalization