mlsanityData to 14 Oct 2026

Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges

arXiv 2407.00116 ↗First posted 27 Jun 2024cs.LG cs.AIcited by 24

On the map: Synthetic data and self-improvement for LLMs → Medical synthetic data and agents

Abstract (arXiv)

This paper presents a comprehensive systematic review of generative models (GANs, VAEs, DMs, and LLMs) used to synthesize various medical data types, including imaging (dermoscopic, mammographic, ultrasound, CT, MRI, and X-ray), text, time-series, and tabular data (EHR). Unlike previous narrowly focused reviews, our study encompasses a broad array of medical data modalities and explores various generative models. Our search strategy queries databases such as Scopus, PubMed, and ArXiv, focusing on recent works from January 2021 to November 2023, excluding reviews and perspectives. This period emphasizes recent advancements beyond GANs, which have been extensively covered previously. The survey reveals insights from three key aspects: (1) Synthesis applications and purpose of synthesis, (2) generation techniques, and (3) evaluation methods. It highlights clinically valid synthesis applications, demonstrating the potential of synthetic data to tackle diverse clinical requirements. While conditional models incorporating class labels, segmentation masks and image translations are prevalent, there is a gap in utilizing prior clinical knowledge and patient-specific context, suggesting a need for more personalized synthesis approaches and emphasizing the importance of tailoring generative approaches to the unique characteristics of medical data. Additionally, there is a significant gap in using synthetic data beyond augmentation, such as for validation and evaluation of downstream medical AI models. The survey uncovers that the lack of standardized evaluation methodologies tailored to medical images is a barrier to clinical application, underscoring the need for in-depth evaluation approaches, benchmarking, and comparative studies to promote openness and collaboration.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Placed in Medical synthetic data and agents, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 62 of its 261 references that are in the map. First posted on arXiv 27 Jun 2024.

Builds on

62 of 261 references.

References · 62

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2015Variational Inference with Normalizing Flowscited by 2,170
  4. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  5. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  7. 2017Renyi Differential Privacycited by 650
  8. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 273
  9. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  10. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  11. 2022Metrics reloaded: Recommendations for image analysis validationcited by 195
  12. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Modelscited by 192
38 more
  1. 2022Diffusion Probabilistic Models beat GANs on Medical Imagescited by 77
  2. 2021GANs for Medical Image Synthesis: An Empirical Studycited by 65
  3. 2020Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANcited by 60
  4. 2020Differentially Private Synthetic Medical Data Generation using Convolutional GANscited by 52
  5. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  6. 2021Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applicationscited by 47
  7. 2023Causal Recurrent Variational Autoencoder for Medical Time Series Generationcited by 45
  8. 2022Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesiscited by 42
  9. 2022TTS-GAN: A Transformer-based Time-Series Generative Adversarial Networkcited by 41
  10. 2020Overcoming Barriers to Data Sharing with Medical Image Generation: A Comprehensive Evaluationcited by 36
  11. 2023Diffusion-based Conditional ECG Generation with Structured State Space Modelscited by 36
  12. 2019mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesiscited by 34
  13. 2023MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generationcited by 34
  14. 2023Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentationcited by 34
  15. 2023Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesiscited by 32
  16. 2023Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Modelcited by 29
  17. 2020EVA: Generating Longitudinal Electronic Health Records Using Conditional Variational Autoencoderscited by 28
  18. 2018Natural Language Generation for Electronic Health Recordscited by 27
  19. 2021Segmentation-Renormalized Deep Feature Modulation for Unpaired Image Harmonizationcited by 24
  20. 2020Generating Electronic Health Records with Multiple Data Types and Constraintscited by 21
  21. 2020Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANscited by 17
  22. 2022Multi-Label Clinical Time-Series Generation via Conditional GANcited by 16
  23. 2020Learning Two-Stream CNN for Multi-Modal Age-related Macular Degeneration Categorizationcited by 15
  24. 2022Conditional Generation of Medical Time Series for Extrapolation to Underrepresented Populationscited by 14
  25. 2023Correlated and Multi-frequency Diffusion Modeling for Highly Under-sampled MRI Reconstructioncited by 14
  26. 2023Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representationscited by 13
  27. 2022Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detectioncited by 11
  28. 2022High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detectioncited by 11
  29. 2021Controllable cardiac synthesis via disentangled anatomy arithmeticcited by 9
  30. 2022The (de)biasing effect of GAN-based augmentation methods on skin lesion imagescited by 9
  31. 2021A multi-stage GAN for multi-organ chest X-ray image generation and segmentationcited by 8
  32. 2022Brain Lesion Synthesis via Progressive Adversarial Variational Auto-Encodercited by 8
  33. 2022Sharing Generative Models Instead of Private Data: A Simulation Study on Mammography Patch Classificationcited by 7
  34. 2022Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANscited by 7
  35. 2021Deep Learning based Multi-modal Computing with Feature Disentanglement for MRI Image Synthesiscited by 6
  36. 2021Synthesis of standard 12-lead electrocardiograms using two dimensional generative adversarial networkcited by 6
  37. 2023Denoising Diffusion Medical Modelscited by 6
  38. 2024A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GANcited by 6

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 13.

24 papers.

Sort:

By area:

  1. 2025Beyond Generative AI: World Models for Clinical Prediction, Counterfactuals, and Planningcited by 9
  2. 2025Longitudinal Flow Matching for Trajectory Modelingcited by 7
  3. 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Recordscited by 6
  4. 2025Towards Virtual Clinical Trials of Radiology AI with Conditional Generative Modelingcited by 4
  5. 2025Radiology Report Conditional 3D CT Generation with Multi Encoder Latent diffusion Modelcited by 3
  6. 2026SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendationscited by 3
  7. 2024High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASRcited by 2
  8. 2025FundusGAN: A Hierarchical Feature-Aware Generative Framework for High-Fidelity Fundus Image Generationcited by 2
  9. 2025Interpretable Similarity of Synthetic Image Utilitycited by 2
  10. 2026MRI-to-CT synthesis using drifting modelscited by 2
  11. 2026SRA-Seg: Synthetic to Real Alignment for Semi-Supervised Medical Image Segmentationcited by 1
  12. 2026MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysiscited by 1
12 more
  1. 2026Exploiting Completeness Perception with Diffusion Transformer for Unified 3D MRI Synthesiscited by 1
  2. 2025Improving Diagnostic Accuracy for Oral Cancer with inpainting Synthesis Lesions Generated Using Diffusion Modelscited by 0
  3. 2025Enabling Granular Subgroup Level Model Evaluations by Generating Synthetic Medical Time Seriescited by 0
  4. 2025Generative Artificial Intelligence in Bioinformatics: A Systematic Review of Models, Applications, and Methodological Advancescited by 0
  5. 2026Interpretability and Individuality in Knee MRI: Patient-Specific Radiomic Fingerprint with Reconstructed Healthy Personascited by 0
  6. 2026Evaluation metrics for temporal preservation in synthetic longitudinal patient datacited by 0
  7. 2026Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstructioncited by 0
  8. 2026LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generatorscited by 0
  9. 2026Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Maskscited by 0
  10. 2026Feature-Space Guided Diffusion for Realistic Ultrasound Image Synthesiscited by 0
  11. 2026A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasetscited by 0
  12. 2026Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation
  2. 2024Deep Generative Models for 3D Medical Image Synthesis
  3. 2023Generative AI for Medical Imaging: extending the MONAI Framework
  4. 2024Deep Generative Models Unveil Patterns in Medical Images Through Vision-Language Conditioning
  5. 2023Recent Advances in Generative AI for Healthcare Applications
  6. 2026Cross Modality Image Translation In Medical Imaging Using Generative Frameworks
  7. 2024A Generalist Model for Diverse Text-Guided Medical Image Synthesis
  8. 2023Augmenting medical image classifiers with synthetic data from latent diffusion models