[
    {
        "id": "osp-16685",
        "type": "article-journal",
        "title": "A Multi-Source Ultrasound Benchmark Revealing the Limits of Contemporary Self-Supervised Anomaly Detection Methods",
        "author": [
            {
                "family": "Riedenauer",
                "given": "Marco"
            },
            {
                "family": "Kienzle",
                "given": "Daniel"
            },
            {
                "family": "Mayekar",
                "given": "Pratik"
            },
            {
                "family": "Lienhart",
                "given": "Rainer"
            }
        ],
        "URL": "https://omanscience.com/en/articles/a-multi-source-ultrasound-benchmark-revealing-the-limits-of-contemporary-self-supervised-anomaly-detection-methods",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "DOI": "10.1109/mipr70517.2026.00061",
        "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."
    }
]