mlsanityData to 7 Oct 2026

Assessing the ability of generative adversarial networks to learn canonical medical image statistics

arXiv 2204.12007 ↗First posted 26 Apr 2022eess.IV cs.CV physics.med-phcited by 11

Not on the map. Why?

Abstract (arXiv)

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image quality assessment. Despite the impressive progress in generating high-resolution, perceptually realistic images, it is not clear if modern GANs reliably learn the statistics that are meaningful to a downstream medical imaging application. In this work, the ability of a state-of-the-art GAN to learn the statistics of canonical stochastic image models (SIMs) that are relevant to objective assessment of image quality is investigated. It is shown that although the employed GAN successfully learned several basic first- and second-order statistics of the specific medical SIMs under consideration and generated images with high perceptual quality, it failed to correctly learn several per-image statistics pertinent to the these SIMs, highlighting the urgent need to assess medical image GANs in terms of objective measures of image quality.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 32 of its 71 references that are in the map. First posted on arXiv 26 Apr 2022.

Builds on

32 of 71 references.

References · 32

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  8. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  9. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  10. 2018A Note on the Inception Scorecited by 225
  11. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  12. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
20 more
  1. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  2. 2018Distribution Matching Losses Can Hallucinate Features in Medical Image Translationcited by 99
  3. 2018CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)cited by 81
  4. 2020On hallucinations in tomographic image reconstructioncited by 66
  5. 2020MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstructioncited by 50
  6. 2019Unsupervised Medical Image Translation Using Cycle-MedGANcited by 44
  7. 2020Overcoming Barriers to Data Sharing with Medical Image Generation: A Comprehensive Evaluationcited by 36
  8. 20213D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Imagescited by 32
  9. 2021Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Taskscited by 20
  10. 2020Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstructioncited by 19
  11. 2021Prior Image-Constrained Reconstruction using Style-Based Generative Modelscited by 19
  12. 2021Objective task-based evaluation of artificial intelligence-based medical imaging methods: Framework, strategies and role of the physiciancited by 15
  13. 2018Deep Generative Models in the Real-World: An Open Challenge from Medical Imagingcited by 12
  14. 2021Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networkscited by 12
  15. 2020Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networkscited by 11
  16. 2021Impact of deep learning-based image super-resolution on binary signal detectioncited by 9
  17. 2020Markov-Chain Monte Carlo Approximation of the Ideal Observer using Generative Adversarial Networkscited by 8
  18. 2020Evaluation of Deep Convolutional Generative Adversarial Networks for data augmentation of chest X-ray imagescited by 5
  19. 2018Learning Implicit Generative Models by Teaching Explicit Onescited by 3
  20. 2022Evaluating Procedures for Establishing Generative Adversarial Network-based Stochastic Image Models in Medical Imagingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

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

11 papers.

  1. 2023AmbientFlow: Invertible generative models from incomplete, noisy measurementscited by 11
  2. 2023Assessing the capacity of a denoising diffusion probabilistic model to reproduce spatial contextcited by 7
  3. 2024Synthetic Data in Radiological Imaging: Current State and Future Outlookcited by 7
  4. 2023Ideal Observer Computation by Use of Markov-Chain Monte Carlo with Generative Adversarial Networkscited by 6
  5. 2024Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statisticscited by 4
  6. 2025Shifts in Doctors' Eye Movements Between Real and AI-Generated Medical Imagescited by 1
  7. 2025T-SYNTH: A Knowledge-Based Dataset of Synthetic Breast Imagescited by 1
  8. 2025Hallucinations in medical devicescited by 0
  9. 2025Knowledge-based anomaly detection for identifying network-induced shape artifactscited by 0
  10. 2026Not all Jensen-Shannon Divergence Estimators are Equalcited by 0
  11. 2026M3-Score: Fidelity, Memorization and Coverage as Separate Axes for Evaluating Generative Radiology Image Modelscited by 0