mlsanityData to 14 Oct 2026

PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings

arXiv 2505.17614 ↗First posted 23 May 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised pathology detection trains models on non-pathological data to flag deviations as pathologies, offering strong generalizability for identifying novel diseases and avoiding costly annotations. However, building reliable normality models requires vast healthy datasets, as hospitals' data is inherently biased toward symptomatic populations, while privacy regulations hinder the assembly of representative healthy cohorts. To address this limitation, we propose PathoSCOPE, a few-shot unsupervised pathology detection framework that requires only a small set of non-pathological samples (minimum 2 shots), significantly improving data efficiency. We introduce Global-Local Contrastive Loss (GLCL), comprised of a Local Contrastive Loss to reduce the variability of non-pathological embeddings and a Global Contrastive Loss to enhance the discrimination of pathological regions. We also propose a Pathology-informed Embedding Generation (PiEG) module that synthesizes pathological embeddings guided by the global loss, better exploiting the limited non-pathological samples. Evaluated on the BraTS2020 and ChestXray8 datasets, PathoSCOPE achieves state-of-the-art performance among unsupervised methods while maintaining computational efficiency (2.48 GFLOPs, 166 FPS).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 31 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

20 of 31 references.

References · 20

  1. 2013Describing Textures in the Wildcited by 2,125
  2. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  3. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  4. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  5. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
  6. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  7. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  8. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  9. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  10. 2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
  11. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  12. 2019Towards Visually Explaining Variational Autoencoderscited by 113
8 more
  1. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  2. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
  3. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  4. 2020MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstructioncited by 50
  5. 2023Unsupervised Pathology Detection: A Deep Dive Into the State of the Artcited by 24
  6. 2022Unsupervised Anomaly Localization with Structural Feature-Autoencoderscited by 23
  7. 2022Constrained unsupervised anomaly segmentationcited by 19
  8. 2020Improving unsupervised anomaly localization by applying multi-scale memories to autoencoderscited by 5

Built on by

Not cited yet.