Skip to content
2000
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format text download EPUB
file format pdf download PDF
side by side viewer icon HTML

Abstract

This review provides a comprehensive analysis of recent advancements in generative deep learning (DL) models applied to diagnostic medical imaging, emphasizing their transformative potential in enhancing diagnostic accuracy, reducing radiation exposure, and improving data handling. We explore the architectures, applications, and unique contributions of generative adversarial networks (GANs), autoencoders (AEs), diffusion models, and transformer-based models. The key areas include synthetic data generation for training, text-to-image and image-to-text translation for interpretability, and image-to-image enhancement across imaging modalities. We designed different pipeline architectures presenting basic and advanced generative models specifically designed for medical imaging applications. These include enhanced GAN configurations, such as the multi-layer ML-C-GAN and Temporal-GAN for time-sequenced medical images, and specialized AE-GAN hybrids such as Atten-AE and M3AE, which combine attention modules and language encoding for text-to-image and image-to-text translation. Each pipeline uniquely addresses challenges in synthetic image quality, temporal progression, and accurate caption generation, showcasing their capacity to produce clinically relevant, high-fidelity images across modalities. The discussion highlights these architectural innovations, emphasizing their role in enhancing image synthesis, diagnostic reporting, and patient-specific image interpretation within medical imaging. The review concludes by identifying future directions to refine generative models for clinical applications, ultimately aiming to facilitate more accurate, accessible, and personalized patient care.

© 2025 The Author(s).
© 2025 The Author(s). Published by Bentham Science Publishers. This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056369157250212095252
2025-01-01
2025-09-06

  • From This Site

    /content/journals/cmir/10.2174/0115734056369157250212095252
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056369157.html?itemId=/content/journals/cmir/10.2174/0115734056369157250212095252&mimeType=html&fmt=ahah

References

  1. BarretoA. G. Oliveirad.J. M. GoisF. N. B. CortezP. C. Albuquerqued.V. H. C. A new generative model for textual descriptions of medical images using transformers enhanced with convolutional neural networks.Bioengineering2023109109810.3390/bioengineering10091098
     [Google Scholar]
  2. HeK. GanC. LiZ. RekikI. YinZ. JiW. GaoY. WangQ. ZhangJ. ShenD. Transformers in medical image analysis.Intell. Medic.202331597810.1016/j.imed.2022.07.002
     [Google Scholar]
  3. CelardP. IglesiasE. L. FdezS.J. M. RomeroR. VieiraA. S. BorrajoL. A survey on deep learning applied to medical images: From simple artificial neural networks to generative models.Neural Comp. App.20233532291232310.1007/s00521‑022‑07953‑4
     [Google Scholar]
  4. DayarathnaS. IslamK.T. UribeS. YangG. HayatM. ChenZ. Deep learning based synthesis of MRI, CT and PET: Review and analysis.Med. Image Anal.2024922023120110304610.1016/j.media.2023.10304638052145
     [Google Scholar]
  5. SkandaraniY. JodoinP.M. LalandeA. GANs for medical image synthesis: An empirical study.J. Imaging2023936910.3390/jimaging903006936976120
     [Google Scholar]
  6. CaoH. TanC. GaoZ. XuY. ChenG. HengP.A. LiS.Z. A survey on generative diffusion models.IEEE Trans. Knowl. Data Eng.20243672814283010.1109/TKDE.2024.3361474
     [Google Scholar]
  7. SenerB. Deep generative models in medical imaging: A literature review.Applications of Machine Intelligence in Engineering1st Ed.LondonCRC Press202413114410.1201/9781003269793‑15
     [Google Scholar]
  8. UzunovaH. WilmsM. ForkertN.D. HandelsH. EhrhardtJ. A systematic comparison of generative models for medical images.Int. J. CARS20221771213122410.1007/s11548‑022‑02567‑635128605
     [Google Scholar]
  9. KimK. ChoK. JangR. KyungS. LeeS. HamS. ChoiE. HongG.S. KimN. Updated primer on generative artificial intelligence and large language models in medical imaging for medical professionals.Korean J. Radiol.202425322424210.3348/kjr.2023.081838413108
     [Google Scholar]
  10. KimK. NaY. YeS.J. LeeJ. AhnS.S. ParkE.J. KimH. Controllable Text-to-Image Synthesis for Multi-Modality MR Images.Proceedings of the IEEE/CVF Winter Conference on Applications of Computer VisionWaikoloa, HI, USA, 03-08 Jan 2024, pp. 7921-7930.10.1109/WACV57701.2024.00775
     [Google Scholar]
  11. LiuY. DwivediG. BoussaidF. BennamounM. 3D brain and heart volume generative models: A survey.ACM Comput. Surv.202456613710.1145/3638044
     [Google Scholar]
  12. AzuajeG. LiewK. BueningR. SheW.J. SiriarayaP. WakamiyaS. AramakiE. Exploring the use of AI text-to-image generation to downregulate negative emotions in an expressive writing application.R. Soc. Open Sci.202310122023810.1098/rsos.22023836636309
     [Google Scholar]
  13. JiaoJ. XiaoX. LiZ. dm-GAN: Distributed multi-latent code inversion enhanced GAN for fast and accurate breast X-ray image automatic generation.Math. Biosci. Eng.20232011194851950310.3934/mbe.202386338052611
     [Google Scholar]
  14. KhanZakir ShiraziSyed Hamad ShahzadMuhammad MunirArslan RasheedAssad XieYong GulSarah A Framework for Segmentation and Classification of Blood Cells Using Generative Adversarial Networks.IEEE Access.202412519955201510.1109/ACCESS.2024.3378575
     [Google Scholar]
  15. EndoYuki Masked-attention diffusion guidance for spatially controlling text-to-image generation.Visual Comp.20234096033604510.1007/s00371‑023‑03151‑y
     [Google Scholar]
  16. AssogbaYannick PearceAdam ElliottMadison Large scale qualitative evaluation of generative image model outputs.ArXiv abs/2301.04518202316
     [Google Scholar]
  17. BerahmandK. DaneshfarF. SalehiE.S. LiY. XuY. Autoencoders and their applications in machine learning: A survey.Artif. Intell. Rev.20245722810.1007/s10462‑023‑10662‑6
     [Google Scholar]
  18. DashAnkan YeJunyi WangGuiling A Review of Generative Adversarial Networks (GANs) and Its Applications in a Wide Variety of Disciplines: From Medical to Remote Sensing.IEEE Access202412183301835710.1109/ACCESS.2023.3346273
     [Google Scholar]
  19. YiX. WaliaE. BabynP. Generative adversarial network in medical imaging: A review.Med. Image Anal.20195810155210.1016/j.media.2019.101552
     [Google Scholar]
  20. LvT. XieC. ZhangY. LiuY. ZhangG. QuB. ZhaoW. XuS. A qualitative study of improving megavoltage computed tomography image quality and maintaining dose accuracy using cycleGAN‐based image synthesis.Med. Phys.202451139440610.1002/mp.1663337475544
     [Google Scholar]
  21. ChenZ. DuY. HuJ. LiuY. LiG. WanX. ChangT-H. Multi-modal Masked Autoencoders for Medical Vision-and-Language Pre-training.International Conference on Medical Image Computing and Computer-Assisted InterventionSwitzerlandSpringer Nature Switzerland, City202296510.1007/978‑3‑031‑16443‑9_65
     [Google Scholar]
  22. FranzesM.G. NiehuesJ. M. KhaderF. ArastehS. T. HaarburgerC. KuhlC. WangT. HanT. NolteT. NebelungS. KatherJ. N. TruhnD. 2023A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis.Scient. Rep.1311209810.1038/s41598‑023‑39278‑0
     [Google Scholar]
  23. ZhuM. PanP. ChenW. YangY. DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis.2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Long Beach, CA, USA, 15-20 June 2019, pp. 5795-5803.10.1109/CVPR.2019.00595
     [Google Scholar]
  24. DevasanaG.M.S. KumarK.V. SelvarajR. SatheeshT. Automatic Creation of Quality Images from Text using Multiple Generative Adversial Network.Procedia Comp. Sci.202323095596310.1016/j.procs.2023.12.135
     [Google Scholar]
  25. ParkHyun-Cheol PyoI.Hong Data Augmentation Based on Generative Adversarial Networks for Endoscopic Image Classification.IEEE Access202311492164922510.1109/ACCESS.2023.3275173
     [Google Scholar]
  26. FanL.Y. BangA. BonomiL. ComputerI.S.O.C. Evaluating Generative Models in Medical Imaging.2024 IEEE 12th International Conference on Healthcare Informatics (ICHI)20245535510.1109/ICHI61247.2024.00084
     [Google Scholar]
  27. SchönJ. SelvanR. NygaardL. VogeliusI. PetersenJ. Explicit temporal embedding in deep generative latent models for longitudinal medical image synthesis.Comput. Visi. Patt. Recogni.202310546510.48550/arXiv.2301.05465
     [Google Scholar]
  28. GulakalaRutwik MarkertBernd StoffelMarcus Rapid diagnosis of Covid-19 infections by a progressively growing GAN and CNN optimisation.Comp. Methods Prog. Biomed.202322910726210.1016/j.cmpb.2022.107262
     [Google Scholar]
  29. GolfeAlejandro Amord.Rocío ColomerAdrián SalesMaría A. TerradezLiria NaranjoValery ProGleason-GAN: Conditional progressive growing GAN for prostatic cancer Gleason grade patch synthesis.Comp. Methods Prog. Biomed.202324010769510.1016/j.cmpb.2023.107695
     [Google Scholar]
  30. WangJ. LeiB. DingL. XuX. GuX. ZhangM. Autoencoder-based conditional optimal transport generative adversarial network for medical image generation.Visual Informatics202481152510.1016/j.visinf.2023.11.001
     [Google Scholar]
  31. WeiY. ZhangY. JiZ. BaiJ. ZhangL. ZuoW. ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation.arXiv:2302.13848202316
     [Google Scholar]
  32. BeddiarD.R. OussalahM. SeppanenT. Retrieved Generative Captioning for Medical Images.Proceedings of the 20th International Conference on Content-based Multimedia IndexingNew York, NY, USA, 30 Dec 2023 pp. 48–54.10.1145/3617233.3617246
     [Google Scholar]
  33. SchönJ. SelvanR. PetersenJ. Interpreting Latent Spaces of Generative Models for Medical Images Using Unsupervised Methods.MICCAI Workshop on Deep Generative ModelsChamSpringer Nature Switzerland.2022243310.1007/978‑3‑031‑18576‑2_3
     [Google Scholar]
  34. ShaheerU. Bi-parametric prostate MR image synthesis using pathology and sequence-conditioned stable diffusion.Image Video Process.202310209410.48550/arXiv.2303.02094
     [Google Scholar]
  35. ShavlokhovaV. VollmerA. ZouboulisC.C. VollmerM. WollbornJ. LangG. KüblerA. HartmannS. StollC. RoiderE. SaraviB. Finetuning of GLIDE stable diffusion model for AI-based text-conditional image synthesis of dermoscopic images.Front. Med.20231020123143610.3389/fmed.2023.123143637928464
     [Google Scholar]
  36. LanhongY.Z.Z. WangB. JhaD. KelesE. MedetalibeyogluA. BagciU. EMIT-diff: Enhancing medical image segmentation via text-guided diffusion model.arXiv:2310.12868202316
     [Google Scholar]
  37. LiR. LiW. YangY. WeiH. JiangJ. BaiQ. Swinv2-Imagen: Hierarchical vision transformer diffusion models for text-to-image generation.Neural Comput. Appl.20243628172451726010.1007/s00521‑023‑09021‑x
     [Google Scholar]
  38. XuY. LiangJ. ZhuoY. LiuL. XiaoY. ZhouL. TDASD: Generating medically significant fine-grained lung adenocarcinoma nodule CT images based on stable diffusion models with limited sample size.Comput. Methods Programs Biomed.20242482024030510810310.1016/j.cmpb.2024.10810338484410
     [Google Scholar]
  39. KatherJ. N. LalehG.N. FoerschS. TruhnD. Medical domain knowledge in domain-agnostic generative AI.NPJ Dig. Med.2022519010.1038/s41746‑022‑00634‑5
     [Google Scholar]
  40. StruppekL. HintersdorfD. KerstingK. Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis.Proceedings of the IEEE/CVF International Conference on Computer VisionParis, France, 01-06 Oct 2023, pp. 4561-4573.10.1109/ICCV51070.2023.00423
     [Google Scholar]
  41. AksoyN. RavikumarN. FrangiA.F. Radiology report generation using transformers conditioned with non-imaging data.Medical Imaging 2023: Imaging Informatics for Healthcare, Research, and ApplicationsSPIE.20231246914615310.1117/12.2653672
     [Google Scholar]
  42. WangC. J. RostN. S. GollandP. Spatial-intensity transforms for medical image-to-image translation.IEEE Trans. Med. Imaging.202342113362337310.1109/TMI.2023.3283948
     [Google Scholar]
  43. OsualaR. KushibarK. GarruchoL. LinardosA. SzafranowskaZ. KleinS. GlockerB. DiazO. LekadirK. Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging.Med. Image Anal.2023842022112410270410.1016/j.media.2022.10270436473414
     [Google Scholar]
  44. MulitaF. VerrasG. I. AnagnostopoulosC. N. KotisK. A smarter health through the internet of surgical things.Sensors20222212457710.3390/s22124577
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056369157250212095252
Loading
Generative AI for Diagnostic Medical Imaging: A Review
Curr. Med. Imaging 21, E15734056369157 (2025); https://doi.org/10.2174/0115734056369157250212095252
/content/journals/cmir/10.2174/0115734056369157250212095252
/content/journals/cmir/10.2174/0115734056369157250212095252
Loading

Data & Media loading...


  • Article Type:     Review Article
Keyword(s): Autoencoders; Diffusion models; Generative adversarial networks; Image-to-image; Image-to-text; Medical imaging; Text-to-image; Transformers

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test