mlsanityData to 14 Oct 2026

Proxy-bridged Image Reconstruction Network for Anomaly Detection in Medical Images

arXiv 2110.01761 ↗First posted 5 Oct 2021eess.IV cs.CV cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. Most existing methods solve this problem with a self-reconstruction framework, which tends to learn an identity mapping and reduces the sensitivity to anomalies. To mitigate this problem, in this paper, we propose a novel Proxy-bridged Image Reconstruction Network (ProxyAno) for anomaly detection in medical images. Specifically, we use an intermediate proxy to bridge the input image and the reconstructed image. We study different proxy types, and we find that the superpixel-image (SI) is the best one. We set all pixels' intensities within each superpixel as their average intensity, and denote this image as SI. The proposed ProxyAno consists of two modules, a Proxy Extraction Module and an Image Reconstruction Module. In the Proxy Extraction Module, a memory is introduced to memorize the feature correspondence for normal image to its corresponding SI, while the memorized correspondence does not apply to the abnormal images, which leads to the information loss for abnormal image and facilitates the anomaly detection. In the Image Reconstruction Module, we map an SI to its reconstructed image. Further, we crop a patch from the image and paste it on the normal SI to mimic the anomalies, and enforce the network to reconstruct the normal image even with the pseudo abnormal SI. In this way, our network enlarges the reconstruction error for anomalies. Extensive experiments on brain MR images, retinal OCT images and retinal fundus images verify the effectiveness of our method for both image-level and pixel-level anomaly detection.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 23 of its 57 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

23 of 57 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  5. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  6. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  7. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  8. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  9. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  10. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  11. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  12. 2019Unsupervised Anomaly Localization using Variational Auto-Encoderscited by 73
11 more
  1. 2020Unsupervised Lesion Detection via Image Restoration with a Normative Priorcited by 65
  2. 2018Context-encoding Variational Autoencoder for Unsupervised Anomaly Detectioncited by 64
  3. 2020Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Imagescited by 52
  4. 2020MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstructioncited by 50
  5. 2019Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCTcited by 42
  6. 2019CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Gradingcited by 35
  7. 2020Deep Mining External Imperfect Data for Chest X-ray Disease Screeningcited by 27
  8. 2019Sparse-GAN: Sparsity-constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Imagecited by 14
  9. 2020DeScarGAN: Disease-Specific Anomaly Detection with Weak Supervisioncited by 13
  10. 2018Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Gradingcited by 8
  11. 2019Abnormal Chest X-ray Identification With Generative Adversarial One-Class Classifiercited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 7; 2025: 4; 2026: 2.

18 papers.

Sort:

By area:

  1. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  2. 2023Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detectioncited by 21
  3. 2024Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detectioncited by 17
  4. 2022Siamese Transition Masked Autoencoders as Uniform Unsupervised Visual Anomaly Detectorcited by 9
  5. 2022Robust Vector Quantized-Variational Autoencodercited by 4
  6. 2024Position-Guided Prompt Learning for Anomaly Detection in Chest X-Rayscited by 3
  7. 2024SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applicationscited by 2
  8. 2023Region and Spatial Aware Anomaly Detection for Fundus Imagescited by 1
  9. 2023Image Reconstruction using Superpixel Clustering and Tensor Completioncited by 1
  10. 2024Diff-CXR: Report-to-CXR generation through a disease-knowledge enhanced diffusion modelcited by 1
  11. 2026URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detectioncited by 1
  12. 2024Harnessing Intra-group Variations Via a Population-Level Context for Pathology Detectioncited by 0
6 more
  1. 2024An AI System for Continuous Knee Osteoarthritis Severity Grading Using Self-Supervised Anomaly Detection with Limited Datacited by 0
  2. 2025SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Imagescited by 0
  3. 2025A Closer Look at Edema Area Segmentation in SD-OCT Images Using Adversarial Frameworkcited by 0
  4. 2025Cross-Task Generalization in Handwriting-Based Alzheimer's Screening via Vision Language Adaptationcited by 0
  5. 2025Unsupervised Anomaly Detection in Brain MRI via Disentangled Anatomy Learningcited by 0
  6. 2026MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectorscited by 0