Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathology

2025/06/24 by Can Cui, Cui, Can, Xindong Zheng +19
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.19234

openalex publication_date 2025/06/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Normal and Abnormal Pathology Knowledge-Augmented Vision-Language Model for Anomaly Detection in Pathology Images
• MedIAnomaly: A comparative study of anomaly detection in medical images
• A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect
• Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Images
• BMAD: Benchmarks for Medical Anomaly Detection
• ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction
• Transformer based Models for Unsupervised Anomaly Segmentation in Brain MR Images
• CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization
• A Unified Model for Multi-class Anomaly Detection
• Glo-In-One: Holistic Glomerular Detection, Segmentation, and Lesion Characterization with Large-scale Web Image Mining
• FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
• Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection
• DRAEM -- A discriminatively trained reconstruction embedding for surface\n anomaly detection
• CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows
• Towards Total Recall in Industrial Anomaly Detection
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
• Unsupervised anomaly detection in digital pathology using GANs
• Student-Teacher Feature Pyramid Matching for Anomaly Detection
• Deep One-Class Classification via Interpolated Gaussian Descriptor
• PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and\n Localization
• PANDA: Adapting Pretrained Features for Anomaly Detection and\n Segmentation
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
• Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder\n Anomaly Detection
• GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution

Related

• Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Images
• On Pixel-level Performance Assessment in Anomaly Detection
• MedIAnomaly: A comparative study of anomaly detection in medical images
• A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect
• LesionPaste: One-Shot Anomaly Detection for Medical Images