mlsanityData to 7 Oct 2026

Anatomy-aware Self-supervised Learning for Anomaly Detection in Chest Radiographs

arXiv 2205.04282 ↗First posted 9 May 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Large numbers of labeled medical images are essential for the accurate detection of anomalies, but manual annotation is labor-intensive and time-consuming. Self-supervised learning (SSL) is a training method to learn data-specific features without manual annotation. Several SSL-based models have been employed in medical image anomaly detection. These SSL methods effectively learn representations in several field-specific images, such as natural and industrial product images. However, owing to the requirement of medical expertise, typical SSL-based models are inefficient in medical image anomaly detection. We present an SSL-based model that enables anatomical structure-based unsupervised anomaly detection (UAD). The model employs the anatomy-aware pasting (AnatPaste) augmentation tool. AnatPaste employs a threshold-based lung segmentation pretext task to create anomalies in normal chest radiographs, which are used for model pretraining. These anomalies are similar to real anomalies and help the model recognize them. We evaluate our model on three opensource chest radiograph datasets. Our model exhibit area under curves (AUC) of 92.1%, 78.7%, and 81.9%, which are the highest among existing UAD models. This is the first SSL model to employ anatomical information as a pretext task. AnatPaste can be applied in various deep learning models and downstream tasks. It can be employed for other modalities by fixing appropriate segmentation. Our code is publicly available at: https://github.com/jun-sato/AnatPaste.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 33 of its 73 references that are in the map. First posted on arXiv 9 May 2022.

Builds on

33 of 73 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  9. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  10. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  11. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  12. 2020Contrastive Learning of Medical Visual Representations from Paired Images and Textcited by 636
21 more
  1. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  2. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  3. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  4. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  5. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  6. 2020Deep Learning for Anomaly Detection: A Reviewcited by 159
  7. 2020Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Studycited by 146
  8. 2020Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotationscited by 89
  9. 2021SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentationcited by 86
  10. 2021Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reportscited by 80
  11. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  12. 2020MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Modelscited by 61
  13. 2021Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contextscited by 59
  14. 2021MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretationcited by 52
  15. 2020Self-supervised Feature Learning via Exploiting Multi-modal Data for Retinal Disease Diagnosiscited by 47
  16. 2015How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?cited by 45
  17. 2021Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Imagescited by 45
  18. 2021COVID-19 Prognosis via Self-Supervised Representation Learning and Multi-Image Predictioncited by 36
  19. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  20. 2021Unsupervised Detection of Lung Nodules in Chest Radiography Using Generative Adversarial Networkscited by 4
  21. 2018Pneumonia Detection in Chest Radiographscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 5; 2025: 3; 2026: 2.

12 papers.

  1. 2022Robust and Efficient Medical Imaging with Self-Supervisioncited by 40
  2. 2024MedIAnomaly: A comparative study of anomaly detection in medical imagescited by 25
  3. 2024Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Imagescited by 13
  4. 2023AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rayscited by 8
  5. 2024Position-Guided Prompt Learning for Anomaly Detection in Chest X-Rayscited by 3
  6. 2025AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Imagescited by 3
  7. 2024DINO-LG: Enhancing Vision Transformers with Label Guidance for Coronary Artery Calcium Detectioncited by 1
  8. 2025ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rayscited by 1
  9. 2024Training Better Deep Learning Models Using Human Saliencycited by 0
  10. 2025DiSSECT: Structuring Transfer-Ready Medical Image Representations through Discrete Self-Supervisioncited by 0
  11. 2026Towards Modality-Agnostic Medical Image Anomaly Detection: A Training-Free Manifold Refinement Approachcited by 0
  12. 2026AUCp: Pseudo-AUC for Inference Model Selection with Unlabeled Validation Data in Abnormality Detectioncited by 0