对比20多种异常检测方法，为病理图像分析提供可靠评估基准。
Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathology
- 构建5个真实与合成病理数据集，系统测试不同算法性能。
- 发现图像尺度和训练周期显著影响检测效果，部分方法在小异常上表现差。
- 为罕见病识别、生物标志物发现等应用提供可复用的评估参考。
异常检测在工业缺陷检测中已广泛研究，发展出众多方法应对各类挑战。在数字病理学领域，其在罕见病识别、伪影检测和生物标志物发现等方面具有重要潜力。然而，病理图像特有的大尺寸、多尺度结构、染色变异和重复模式等特点，给现有算法带来新挑战。本研究通过大规模实验，对超过20种经典与主流异常检测方法进行定量评估。我们整理了五个数字病理数据集（包括真实与合成数据），系统考察了图像尺度、异常模式类型及训练周期选择策略对检测性能的影响。结果揭示了各方法的优劣，建立了全面的基准，为未来数字病理图像异常检测研究提供指导。
原文摘要 · Abstract (English)
Anomaly detection has been widely studied in the context of industrial defect inspection, with numerous methods developed to tackle a range of challenges. In digital pathology, anomaly detection holds significant potential for applications such as rare disease identification, artifact detection, and biomarker discovery. However, the unique characteristics of pathology images, such as their large size, multi-scale structures, stain variability, and repetitive patterns, introduce new challenges that current anomaly detection algorithms struggle to address. In this quantitative study, we benchmark over 20 classical and prevalent anomaly detection methods through extensive experiments. We curated five digital pathology datasets, both real and synthetic, to systematically evaluate these approaches. Our experiments investigate the influence of image scale, anomaly pattern types, and training epoch selection strategies on detection performance. The results provide a detailed comparison of each method's strengths and limitations, establishing a comprehensive benchmark to guide future research in anomaly detection for digital pathology images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。