mlsanityData to 14 Oct 2026

Distribution Matching Losses Can Hallucinate Features in Medical Image Translation

arXiv 1805.08841 ↗First posted 22 May 2018cs.CV cs.LGcited by 99

Not on the map. Why?

Abstract (arXiv)

This paper discusses how distribution matching losses, such as those used in CycleGAN, when used to synthesize medical images can lead to mis-diagnosis of medical conditions. It seems appealing to use these new image synthesis methods for translating images from a source to a target domain because they can produce high quality images and some even do not require paired data. However, the basis of how these image translation models work is through matching the translation output to the distribution of the target domain. This can cause an issue when the data provided in the target domain has an over or under representation of some classes (e.g. healthy or sick). When the output of an algorithm is a transformed image there are uncertainties whether all known and unknown class labels have been preserved or changed. Therefore, we recommend that these translated images should not be used for direct interpretation (e.g. by doctors) because they may lead to misdiagnosis of patients based on hallucinated image features by an algorithm that matches a distribution. However there are many recent papers that seem as though this is the goal.

Key facts. Cited by 99 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 10; 2023: 19; 2024: 16; 2025: 13; 2026: 22.

99 papers.

Sort:

By area:

  1. 2021Deblurring via Stochastic Refinementcited by 249
  2. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 165
  3. 2021Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representationscited by 31
  4. 2024Hallucination Index: An Image Quality Metric for Generative Reconstruction Modelscited by 26
  5. 2021Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonizationcited by 24
  6. 2022A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysiscited by 24
  7. 2022BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networkscited by 23
  8. 2021A Structural Causal Model for MR Images of Multiple Sclerosiscited by 21
  9. 2022COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Trainingcited by 20
  10. 2024Similarity and Quality Metrics for MR Image-To-Image Translationcited by 20
  11. 2023Low-field magnetic resonance image enhancement via stochastic image quality transfercited by 19
  12. 2021Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Futurecited by 18
38 more
  1. 2024StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translationcited by 18
  2. 2021Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translationcited by 15
  3. 2021Data synthesis and adversarial networks: A review and meta-analysis in cancer imagingcited by 15
  4. 2023Denoising diffusion-based MRI to CT image translation enables automated spinal segmentationcited by 15
  5. 2022Assessing the ability of generative adversarial networks to learn canonical medical image statisticscited by 11
  6. 2022High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detectioncited by 11
  7. 2024StainDiffuser: MultiTask Dual Diffusion Model for Virtual Stainingcited by 11
  8. 2021MR-Contrast-Aware Image-to-Image Translations with Generative Adversarial Networkscited by 10
  9. 2021METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopycited by 9
  10. 2021Appearance Based Deep Domain Adaptation for the Classification of Aerial Imagescited by 9
  11. 2023Digital staining in optical microscopy using deep learning -- a reviewcited by 7
  12. 2021Multitask 3D CBCT-to-CT Translation and Organs-at-Risk Segmentation Using Physics-Based Data Augmentationcited by 6
  13. 2021High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Losscited by 6
  14. 2021Bridging the gap between paired and unpaired medical image translationcited by 6
  15. 2023Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labelscited by 6
  16. 2023Cross-modal tumor segmentation using generative blending augmentation and self trainingcited by 6
  17. 2024Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networkscited by 6
  18. 2022Data Models for Dataset Drift Controls in Machine Learning With Optical Imagescited by 5
  19. 2021Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired imagescited by 4
  20. 2023Physical Color Calibration of Digital Pathology Scanners for Robust Artificial Intelligence Assisted Cancer Diagnosiscited by 4
  21. 2023SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-spacecited by 4
  22. 2024IGUANe: a 3D generalizable CycleGAN for multicenter harmonization of brain MR imagescited by 4
  23. 2024Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statisticscited by 4
  24. 2024Position: Cracking the Code of Cascading Disparity Towards Marginalized Communitiescited by 4
  25. 2024Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonizationcited by 4
  26. 2023Generalizable synthetic MRI with physics-informed convolutional networkscited by 3
  27. 2025Systematic Review and Meta-analysis of AI-driven MRI Motion Artifact Detection and Correctioncited by 3
  28. 2021Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rayscited by 2
  29. 2021Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptationcited by 2
  30. 2023A Practical Framework for Unsupervised Structure Preservation Medical Image Enhancementcited by 2
  31. 2023ProtoKD: Learning from Extremely Scarce Data for Parasite Ova Recognitioncited by 2
  32. 2023Uncertainty Estimation in Contrast-Enhanced MR Image Translation with Multi-Axis Fusioncited by 2
  33. 2023Ultrasound Image Enhancement using CycleGAN and Perceptual Losscited by 2
  34. 2024Anatomical Conditioning for Contrastive Unpaired Image-to-Image Translation of Optical Coherence Tomography Imagescited by 2
  35. 2024Improve Cross-Modality Segmentation by Treating T1-Weighted MRI Images as Inverted CT Scanscited by 2
  36. 2024A Modular Conditional Diffusion Framework for Image Reconstructioncited by 2
  37. 2025TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reductioncited by 2
  38. 2025Digital Staining with Knowledge Distillation: A Unified Framework for Unpaired and Paired-But-Misaligned Datacited by 2

50 most cited of 99 All 99 (JSON)