mlsanityData to 14 Oct 2026

medigan: a Python library of pretrained generative models for medical image synthesis

arXiv 2209.14472 ↗First posted 28 Sep 2022eess.IV cs.CV cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Synthetic data generated by generative models can enhance the performance and capabilities of data-hungry deep learning models in medical imaging. However, there is (1) limited availability of (synthetic) datasets and (2) generative models are complex to train, which hinders their adoption in research and clinical applications. To reduce this entry barrier, we propose medigan, a one-stop shop for pretrained generative models implemented as an open-source framework-agnostic Python library. medigan allows researchers and developers to create, increase, and domain-adapt their training data in just a few lines of code. Guided by design decisions based on gathered end-user requirements, we implement medigan based on modular components for generative model (i) execution, (ii) visualisation, (iii) search & ranking, and (iv) contribution. The library's scalability and design is demonstrated by its growing number of integrated and readily-usable pretrained generative models consisting of 21 models utilising 9 different Generative Adversarial Network architectures trained on 11 datasets from 4 domains, namely, mammography, endoscopy, x-ray, and MRI. Furthermore, 3 applications of medigan are analysed in this work, which include (a) enabling community-wide sharing of restricted data, (b) investigating generative model evaluation metrics, and (c) improving clinical downstream tasks. In (b), extending on common medical image synthesis assessment and reporting standards, we show Fr'echet Inception Distance variability based on image normalisation and radiology-specific feature extraction.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 55 of its 118 references that are in the map. First posted on arXiv 28 Sep 2022.

Builds on

55 of 118 references.

References · 55

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2014Going Deeper with Convolutionscited by 4,241
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  9. 2016Improved Techniques for Training GANscited by 2,970
  10. 2017Improved Training of Wasserstein GANscited by 2,235
  11. 2015Variational Inference with Normalizing Flowscited by 2,170
  12. 2014Conditional Generative Adversarial Netscited by 2,162
38 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  2. 2016Density estimation using Real NVPcited by 2,042
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  5. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  6. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  7. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  8. 2018Which Training Methods for GANs do actually Converge?cited by 679
  9. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  10. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  11. 2022Brain Imaging Generation with Latent Diffusion Modelscited by 268
  12. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 260
  13. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  14. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  15. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 211
  16. 2020TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningcited by 177
  17. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  18. 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
  19. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  20. 2020Synthetic Data -- Anonymisation Groundhog Daycited by 108
  21. 2021An Introduction to Deep Generative Modelingcited by 104
  22. 2017Deep MR to CT Synthesis using Unpaired Datacited by 86
  23. 2017A Deep Cascade of Convolutional Neural Networks for MR Image Reconstructioncited by 74
  24. 2021nnDetection: A Self-configuring Method for Medical Object Detectioncited by 60
  25. 2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
  26. 2017NiftyNet: a deep-learning platform for medical imagingcited by 45
  27. 2021SinGAN-Seg: Synthetic training data generation for medical image segmentationcited by 43
  28. 2018GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentationcited by 41
  29. 2020OPTIMAM Mammography Image Database: a large scale resource of mammography images and clinical datacited by 38
  30. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  31. 2021Unsupervised Brain Anomaly Detection and Segmentation with Transformerscited by 34
  32. 2022Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysiscited by 18
  33. 2020Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANscited by 17
  34. 2021Data synthesis and adversarial networks: A review and meta-analysis in cancer imagingcited by 15
  35. 2020Secondary Use of Electronic Health Record: Opportunities and Challengescited by 14
  36. 2020Mimicry: Towards the Reproducibility of GAN Researchcited by 14
  37. 2021FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imagingcited by 13
  38. 2017DLTK: State of the Art Reference Implementations for Deep Learning on Medical Imagescited by 11

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 4; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trendcited by 24
  2. 2024Fr'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasetscited by 19
  3. 2025Metrics that matter: Evaluating image quality metrics for medical image generationcited by 12
  4. 2024Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Modelscited by 11
  5. 2023Single-Model Attribution of Generative Models Through Final-Layer Inversioncited by 10
  6. 2023Pre- to Post-Contrast Breast MRI Synthesis for Enhanced Tumour Segmentationcited by 9
  7. 2024Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networkscited by 6
  8. 2024Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Datacited by 3
  9. 2023RadImageGAN -- A Multi-modal Dataset-Scale Generative AI for Medical Imagingcited by 2
  10. 2025Assessing the Distributional Fidelity of Synthetic Chest X-rays using the Embedded Characteristic Scorecited by 1
  11. 2025Enhanced Generative Model Evaluation with Clipped Density and Coveragecited by 1
  12. 2024Mitigating annotation shift in cancer classification using single image generative modelscited by 0
2 more
  1. 2025Clinically-guided Data Synthesis for Laryngeal Lesion Detectioncited by 0
  2. 2026Repurposing Image Diffusion Models for Adversarial Synthetic Structured Data: A Case Study of Ground Truth Driftcited by 0