mlsanityData to 14 Oct 2026

GANs for Medical Image Synthesis: An Empirical Study

arXiv 2105.05318 ↗First posted 11 May 2021eess.IV cs.CV cs.LGcited by 65

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) have become increasingly powerful, generating mind-blowing photorealistic images that mimic the content of datasets they were trained to replicate. One recurrent theme in medical imaging is whether GANs can also be effective at generating workable medical data as they are for generating realistic RGB images. In this paper, we perform a multi-GAN and multi-application study to gauge the benefits of GANs in medical imaging. We tested various GAN architectures from basic DCGAN to more sophisticated style-based GANs on three medical imaging modalities and organs namely : cardiac cine-MRI, liver CT and RGB retina images. GANs were trained on well-known and widely utilized datasets from which their FID score were computed to measure the visual acuity of their generated images. We further tested their usefulness by measuring the segmentation accuracy of a U-Net trained on these generated images. Results reveal that GANs are far from being equal as some are ill-suited for medical imaging applications while others are much better off. The top-performing GANs are capable of generating realistic-looking medical images by FID standards that can fool trained experts in a visual Turing test and comply to some metrics. However, segmentation results suggests that no GAN is capable of reproducing the full richness of a medical datasets.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 11 May 2021.

Builds on

30 of 45 references.

References · 30

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2016Improved Techniques for Training GANscited by 2,970
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  12. 2018Demystifying MMD GANscited by 1,293
18 more
  1. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  2. 2016Least Squares Generative Adversarial Networkscited by 1,001
  3. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  4. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  5. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  6. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  7. 2017Geometric GANcited by 233
  8. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  9. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  10. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 147
  11. 2019Classification Accuracy Score for Conditional Generative Modelscited by 136
  12. 2018GANs for Medical Image Analysiscited by 81
  13. 2018How good is my GAN?cited by 74
  14. 2018Cross-View Image Synthesis using Conditional GANscited by 69
  15. 2017How to Fool Radiologists with Generative Adversarial Networks? A Visual Turing Test for Lung Cancer Diagnosiscited by 35
  16. 2018Learning Implicit Brain MRI Manifolds with Deep Learningcited by 20
  17. 2018Generating Highly Realistic Images of Skin Lesions with GANscited by 16
  18. 2020On the effectiveness of GAN generated cardiac MRIs for segmentationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 18; 2024: 14; 2025: 17; 2026: 7.

65 papers.

Sort:

By area:

  1. 2024MAISI: Medical AI for Synthetic Imagingcited by 87
  2. 2023Conditional Diffusion Models for Semantic 3D Brain MRI Synthesiscited by 86
  3. 2025Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Qualitycited by 25
  4. 2024Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challengescited by 24
  5. 2023Medical diffusion on a budget: Textual Inversion for medical image generationcited by 20
  6. 2024A study of why we need to reassess full reference image quality assessment with medical imagescited by 17
  7. 2024Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNNcited by 15
  8. 2022Conditional Generation of Medical Time Series for Extrapolation to Underrepresented Populationscited by 14
  9. 2025MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairscited by 13
  10. 2022Evaluating the Performance of StyleGAN2-ADA on Medical Imagescited by 11
  11. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  12. 2023Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and dosescited by 8
38 more
  1. 2024TimEHR: Image-based Time Series Generation for Electronic Health Recordscited by 8
  2. 2023Evaluating clinical diversity and plausibility of synthetic capsule endoscopic imagescited by 7
  3. 2023Bi-parametric prostate MR image synthesis using pathology and sequence-conditioned stable diffusioncited by 7
  4. 2023Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and Privacycited by 7
  5. 2023Ideal Observer Computation by Use of Markov-Chain Monte Carlo with Generative Adversarial Networkscited by 6
  6. 2024Vision-Language Synthetic Data Enhances Echocardiography Downstream Taskscited by 6
  7. 2022Leveraging Statistical Shape Priors in GAN-based ECG Synthesiscited by 4
  8. 2023DermSynth3D: Synthesis of in-the-wild Annotated Dermatology Imagescited by 4
  9. 2023Generative Adversarial Networks for Brain Images Synthesis: A Reviewcited by 4
  10. 2024A Domain Translation Framework with an Adversarial Denoising Diffusion Model to Generate Synthetic Datasets of Echocardiography Imagescited by 4
  11. 2024Neurovascular Segmentation in sOCT with Deep Learning and Synthetic Training Datacited by 4
  12. 2024Multi-resolution Guided 3D GANs for Medical Image Translationcited by 4
  13. 2022Mining the manifolds of deep generative models for multiple data-consistent solutions of ill-posed tomographic imaging problemscited by 3
  14. 2022Nuclei & Glands Instance Segmentation in Histology Images: A Narrative Reviewcited by 3
  15. 2023Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executablescited by 3
  16. 2023Learning Expected Appearances for Intraoperative Registration during Neurosurgerycited by 3
  17. 2022A Novel Transparency Strategy-based Data Augmentation Approach for BI-RADS Classification of Mammogramscited by 2
  18. 2022A Note on the Regularity of Images Generated by Convolutional Neural Networkscited by 2
  19. 2023M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Taskscited by 2
  20. 2023LatentAugment: Data Augmentation via Guided Manipulation of GAN's Latent Spacecited by 2
  21. 2023RadImageGAN -- A Multi-modal Dataset-Scale Generative AI for Medical Imagingcited by 2
  22. 2025Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Mapcited by 2
  23. 2025Towards Better Cephalometric Landmark Detection with Diffusion Data Generationcited by 2
  24. 2026MRI-to-CT synthesis using drifting modelscited by 2
  25. 2022Empirical Study of Quality Image Assessment for Synthesis of Fetal Head Ultrasound Imaging with DCGANscited by 1
  26. 2024Pancreatic Tumor Segmentation as Anomaly Detection in CT Images Using Denoising Diffusion Modelscited by 1
  27. 2024Taming the Tail: Leveraging Asymmetric Loss and Pade Approximation to Overcome Medical Image Long-Tailed Class Imbalancecited by 1
  28. 2024Medical Imaging Complexity and its Effects on GAN Performancecited by 1
  29. 2024DiffuPT: Class Imbalance Mitigation for Glaucoma Detection via Diffusion Based Generation and Model Pretrainingcited by 1
  30. 2025PhotoGAN: Generative Adversarial Neural Network Acceleration with Silicon Photonicscited by 1
  31. 2025Pathological MRI Segmentation by Synthetic Pathological Data Generation in Fetuses and Neonatescited by 1
  32. 2025Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentationcited by 1
  33. 2025Generative Adversarial Synthesis and Deep Feature Discrimination of Brain Tumor MRI Imagescited by 1
  34. 2022MIPR:Automatic Annotation of Medical Images with Pixel Rearrangementcited by 0
  35. 2023From Private to Public: Benchmarking GANs in the Context of Private Time Series Classificationcited by 0
  36. 2023Synthetic Skull CT Generation with Generative Adversarial Networks to Train Deep Learning Models for Clinical Transcranial Ultrasoundcited by 0
  37. 2023MVC: A Multi-Task Vision Transformer Network for COVID-19 Diagnosis from Chest X-ray Imagescited by 0
  38. 2024Leveraging Multimodal CycleGAN for the Generation of Anatomically Accurate Synthetic CT Scans from MRIscited by 0

50 most cited of 65 All 65 (JSON)