mlsanityData to 14 Oct 2026

Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classification

arXiv 2206.13123 ↗First posted 27 Jun 2022eess.IV cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

The success of deep learning has set new benchmarks for many medical image analysis tasks. However, deep models often fail to generalize in the presence of distribution shifts between training (source) data and test (target) data. One method commonly employed to counter distribution shifts is domain adaptation: using samples from the target domain to learn to account for shifted distributions. In this work we propose an unsupervised domain adaptation approach that uses graph neural networks and, disentangled semantic and domain invariant structural features, allowing for better performance across distribution shifts. We propose an extension to swapped autoencoders to obtain more discriminative features. We test the proposed method for classification on two challenging medical image datasets with distribution shifts - multi center chest Xray images and histopathology images. Experiments show our method achieves state-of-the-art results compared to other domain adaptation methods.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 45 of its 162 references that are in the map. First posted on arXiv 27 Jun 2022.

Builds on

45 of 162 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  4. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  5. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 461
  6. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  7. 2020Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentationcited by 134
  8. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  9. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  10. 2018Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Networkcited by 74
  11. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  12. 2018A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulationcited by 62
33 more
  1. 2017Detecting Cancer Metastases on Gigapixel Pathology Imagescited by 52
  2. 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
  3. 2020Cardiac Segmentation with Strong Anatomical Guaranteescited by 44
  4. 2019Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentationcited by 33
  5. 2018Chest X-rays Classification: A Multi-Label and Fine-Grained Problemcited by 31
  6. 2021Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognitioncited by 27
  7. 2020Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidancecited by 22
  8. 2021Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentationcited by 22
  9. 2018Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learningcited by 19
  10. 2020Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentationcited by 14
  11. 2021Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimationcited by 13
  12. 2018Deep multiscale convolutional feature learning for weakly supervised localization of chest pathologies in X-ray imagescited by 12
  13. 2019Night Time Haze and Glow Removal using Deep Dilated Convolutional Networkcited by 11
  14. 2019Progressive Generative Adversarial Networks for Medical Image Super resolutioncited by 11
  15. 2019Adversarial Pulmonary Pathology Translation for Pairwise Chest X-ray Data Augmentationcited by 11
  16. 2020Registration of Histopathogy Images Using Structural Information From Fine Grained Feature Mapscited by 11
  17. 2019Informative sample generation using class aware generative adversarial networks for classification of chest Xrayscited by 10
  18. 2017Retinal Vasculature Segmentation Using Local Saliency Maps and Generative Adversarial Networks For Image Super Resolutioncited by 9
  19. 2018GAN Based Medical Image Registrationcited by 9
  20. 2020Anomaly Detection on X-Rays Using Self-Supervised Aggregation Learningcited by 9
  21. 2016Consensus Based Medical Image Segmentation Using Semi-Supervised Learning And Graph Cutscited by 8
  22. 2019Training Data Independent Image Registration With GANs Using Transfer Learning And Segmentation Informationcited by 8
  23. 2019AMD Severity Prediction And Explainability Using Image Registration And Deep Embedded Clusteringcited by 8
  24. 2019sZoom: A Framework for Automatic Zoom into High Resolution Surveillance Videoscited by 8
  25. 2021CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysiscited by 8
  26. 2019Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registrationcited by 7
  27. 2020Graph Domain Adaptation for Alignment-Invariant Brain Surface Segmentationcited by 7
  28. 2021Multi-scale Deep Learning Architecture for Nucleus Detection in Renal Cell Carcinoma Microscopy Imagecited by 7
  29. 2021Gated Fusion Network for SAO Filter and Inter Frame Prediction in Versatile Video Codingcited by 6
  30. 2022Anomaly Detection in Retinal Images using Multi-Scale Deep Feature Sparse Codingcited by 6
  31. 2021Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentationcited by 5
  32. 2022Outlier-based Autism Detection using Longitudinal Structural MRIcited by 5
  33. 2021Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 2.

5 papers.

  1. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  2. 2023Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detectioncited by 4
  3. 2024Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Datacited by 2
  4. 2022Improved Super Resolution of MR Images Using CNNs and Vision Transformerscited by 1
  5. 2022Cyclic Generative Adversarial Networks With Congruent Image-Report Generation For Explainable Medical Image Analysiscited by 0