{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T02:18:27Z","timestamp":1783649907224,"version":"3.55.0"},"reference-count":47,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T00:00:00Z","timestamp":1647993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Artificial intelligence (AI) is expected to have a major effect on radiology as it demonstrated remarkable progress in many clinical tasks, mostly regarding the detection, segmentation, classification, monitoring, and prediction of diseases. Generative Adversarial Networks have been proposed as one of the most exciting applications of deep learning in radiology. GANs are a new approach to deep learning that leverages adversarial learning to tackle a wide array of computer vision challenges. Brain radiology was one of the first fields where GANs found their application. In neuroradiology, indeed, GANs open unexplored scenarios, allowing new processes such as image-to-image and cross-modality synthesis, image reconstruction, image segmentation, image synthesis, data augmentation, disease progression models, and brain decoding. In this narrative review, we will provide an introduction to GANs in brain imaging, discussing the clinical potential of GANs, future clinical applications, as well as pitfalls that radiologists should be aware of.<\/jats:p>","DOI":"10.3390\/jimaging8040083","type":"journal-article","created":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T23:30:23Z","timestamp":1647991823000},"page":"83","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Generative Adversarial Networks in Brain Imaging: A Narrative Review"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7964-8798","authenticated-orcid":false,"given":"Maria Elena","family":"Laino","sequence":"first","affiliation":[{"name":"Artificial Intelligence Center, Humanitas Clinical and Research Center\u2014IRCCS, Via Manzoni 56, 20089 Rozzano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierandrea","family":"Cancian","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Center, Humanitas Clinical and Research Center\u2014IRCCS, Via Manzoni 56, 20089 Rozzano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6190-6688","authenticated-orcid":false,"given":"Letterio Salvatore","family":"Politi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Humanitas Clinical and Research Center\u2014IRCCS, Via Manzoni 56, 20089 Rozzano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo Giovanni","family":"Della Porta","sequence":"additional","affiliation":[{"name":"Department of Hematology, Humanitas Clinical and Research Center\u2014IRCCS, Via Manzoni 56, 20089 Rozzano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Saba","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Cagliari, 09124 Cagliari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3376-8740","authenticated-orcid":false,"given":"Victor","family":"Savevski","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Center, Humanitas Clinical and Research Center\u2014IRCCS, Via Manzoni 56, 20089 Rozzano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1016\/j.acra.2019.12.024","article-title":"Creating Artificial Images for Radiology Applications Using Generative Adversarial Networks (GANs)\u2014A Systematic Review","volume":"27","author":"Sorin","year":"2020","journal-title":"Acad. Radiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/978-3-030-33128-3_2","article-title":"Medical Image Synthesis via Deep Learning","volume":"1213","author":"Yu","year":"2020","journal-title":"Adv. Exp. Med. Biol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1148\/rg.2021200151","article-title":"Generative adversarial networks: A primer for radiologists","volume":"41","author":"Wolterink","year":"2021","journal-title":"Radiographics"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.neuroscience.2020.07.040","article-title":"BigGAN-based Bayesian Reconstruction of Natural Images from Human Brain Activity","volume":"444","author":"Qiao","year":"2020","journal-title":"Neuroscience"},{"key":"ref_5","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.neunet.2020.09.004","article-title":"GP-GAN: Brain tumor growth prediction using stacked 3D generative adversarial networks from longitudinal MR Images","volume":"132","author":"Elazab","year":"2020","journal-title":"Neural Netw."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"159","DOI":"10.18383\/j.tom.2018.00042","article-title":"Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images","volume":"4","author":"Kazuhiro","year":"2018","journal-title":"Tomography"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cviu.2018.10.009","article-title":"Pros and Cons of GAN Evaluation Measures","volume":"179","author":"Borji","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_9","first-page":"6627","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101731","DOI":"10.1016\/j.media.2020.101731","article-title":"Unified generative adversarial networks for multimodal segmentation from unpaired 3D medical images","volume":"64","author":"Yuan","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1007\/s10278-020-00321-5","article-title":"Semantic Segmentation of White Matter in FDG-PET Using Generative Adversarial Network","volume":"33","author":"Oh","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s13195-021-00797-5","article-title":"Enhancing magnetic resonance imaging-driven Alzheimer\u2019s disease classification performance using generative adversarial learning","volume":"13","author":"Zhou","year":"2021","journal-title":"Alzheimer\u2019s Res. Ther."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s13550-020-00644-y","article-title":"Independent attenuation correction of whole body [18F]FDG-PET using a deep learning approach with Generative Adversarial Networks","volume":"10","author":"Armanious","year":"2020","journal-title":"EJNMMI Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"655019","DOI":"10.3389\/fnins.2021.655019","article-title":"Research on the Modality Transfer Method of Brain Imaging Based on Generative Adversarial Network","volume":"15","author":"Cheng","year":"2021","journal-title":"Front. Neurosci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"101944","DOI":"10.1016\/j.media.2020.101944","article-title":"Mustgan: Multi-stream generative adversarial networks for MR image synthesis","volume":"70","author":"Yurt","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jin, C.-B., Kim, H., Liu, M., Jung, W., Joo, S., Park, E., Ahn, Y.S., Han, I.H., Lee, J.I., and Cui, X. (2019). Deep CT to MR Synthesis Using Paired and Unpaired Data. Sensors, 19.","DOI":"10.3390\/s19102361"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1002\/acm2.12856","article-title":"Dosimetric evaluation of synthetic CT generated with GANs for MRI-only proton therapy treatment planning of brain tumors","volume":"21","author":"Kazemifar","year":"2020","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.radonc.2020.09.029","article-title":"Deep learning-based synthetic CT generation for paediatric brain MR-only photon and proton radiotherapy","volume":"153","author":"Maspero","year":"2020","journal-title":"Radiother. Oncol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"260","DOI":"10.3389\/fnins.2020.00260","article-title":"A 3D Fully Convolutional Neural Network With Top-Down Attention-Guided Refinement for Accurate and Robust Automatic Segmentation of Amygdala and Its Subnuclei","volume":"14","author":"Liu","year":"2020","journal-title":"Front. Neurosci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2684851","DOI":"10.1155\/2020\/2684851","article-title":"An Indirect Multimodal Image Registration and Completion Method Guided by Image Synthesis","volume":"2020","author":"Yang","year":"2020","journal-title":"Comput. Math. Methods Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1718","DOI":"10.1002\/mrm.28819","article-title":"Three-dimensional self-attention conditional GAN with spectral normalization for multimodal neuroimaging synthesis","volume":"86","author":"Lan","year":"2021","journal-title":"Magn. Reson. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.neunet.2020.01.029","article-title":"PET image super-resolution using generative adversarial networks","volume":"125","author":"Song","year":"2020","journal-title":"Neural Netw."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TRPMS.2020.3006844","article-title":"MR-Based Attenuation Correction for Brain PET Using 3-D Cycle-Consistent Adversarial Network","volume":"5","author":"Gong","year":"2020","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1002\/jmri.24850","article-title":"Motion artifacts in MRI: A complex problem with many partial solutions","volume":"42","author":"Zaitsev","year":"2015","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3555","DOI":"10.1002\/mp.13626","article-title":"Ultra-low-dose PET reconstruction using generative adversarial network with feature matching and task-specific perceptual loss","volume":"46","author":"Ouyang","year":"2019","journal-title":"Med. Phys."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1148\/radiol.2018180940","article-title":"Ultra\u2013Low-Dose 18F-Florbetaben Amyloid PET Imaging Using Deep Learning with Multi-Contrast MRI Inputs","volume":"290","author":"Chen","year":"2018","journal-title":"Radiology"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e0238455","DOI":"10.1371\/journal.pone.0238455","article-title":"Study of low-dose PET image recovery using supervised learning with CycleGAN","volume":"15","author":"Zhao","year":"2020","journal-title":"PLoS ONE"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"871","DOI":"10.2967\/jnumed.120.248856","article-title":"Conditional Generative Adversarial Networks Aided Motion Correction of Dynamic 18F-FDG PET Brain Studies","volume":"62","author":"Sundar","year":"2021","journal-title":"J. Nucl. Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103755","DOI":"10.1016\/j.compbiomed.2020.103755","article-title":"SegSRGAN: Super-resolution and segmentation using generative adversarial networks\u2014Application to neonatal brain MRI","volume":"120","author":"Delannoy","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"101747","DOI":"10.1016\/j.media.2020.101747","article-title":"Subsampled brain MRI reconstruction by generative adversarial neural networks","volume":"65","author":"Shaul","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhang, H., Shinomiya, Y., and Yoshida, S. (2021). 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution. Sensors, 21.","DOI":"10.3390\/s21092978"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/s40708-020-00104-2","article-title":"GAN-based synthetic brain PET image generation","volume":"7","author":"Islam","year":"2020","journal-title":"Brain Inform."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.mri.2021.06.001","article-title":"Realistic generation of diffusion-weighted magnetic resonance brain images with deep generative models","volume":"81","author":"Hirte","year":"2021","journal-title":"Magn. Reson. Imaging"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"104254","DOI":"10.1016\/j.compbiomed.2021.104254","article-title":"Synthesizing anonymized and labeled TOF-MRA patches for brain vessel segmentation using generative adversarial networks","volume":"131","author":"Kossen","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"106113","DOI":"10.1016\/j.cmpb.2021.106113","article-title":"Data augmentation using generative adversarial neural networks on brain structural connectivity in multiple sclerosis","volume":"206","author":"Barile","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, Q., Yu, Z., Wang, Y., and Zheng, H. (2020). TumorGAN: A Multi-Modal Data Augmentation Framework for Brain Tumor Segmentation. Sensors, 20.","DOI":"10.3390\/s20154203"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1007\/s00259-019-04676-y","article-title":"Slice-selective learning for Alzheimer\u2019s disease classification using a generative adversarial network: A feasibility study of external validation","volume":"47","author":"Kim","year":"2020","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"117602","DOI":"10.1016\/j.neuroimage.2020.117602","article-title":"Reconstructing seen image from brain activity by visually-guided cognitive representation and adversarial learning","volume":"228","author":"Ren","year":"2021","journal-title":"NeuroImage"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/s12264-020-00613-4","article-title":"Deep Natural Image Reconstruction from Human Brain Activity Based on Conditional Progressively Growing Generative Adversarial Networks","volume":"37","author":"Huang","year":"2021","journal-title":"Neurosci. Bull."},{"key":"ref_40","first-page":"1","article-title":"Reconstructing feedback representations in the ventral visual pathway with a generative adversarial autoencoder","volume":"17","author":"Mohsenzadeh","year":"2021","journal-title":"PLoS Comput. Biol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s12859-020-03936-1","article-title":"MADGAN: Unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction","volume":"22","author":"Han","year":"2021","journal-title":"BMC Bioinform."},{"key":"ref_42","unstructured":"Frangi, A., Schnabel, J., Davatzikos, C., Alberola-L\u00f3pez, C., and Fichtinger, G. (2018). Distribution Matching Losses Can Hallucinate Features in Medical Image Translation. Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, Springer. Available online: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-00928-1_60."},{"key":"ref_43","unstructured":"Mirsky, Y., Mahler, T., Shelef, I., and Elovici, Y. (2019). CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning. arXiv, Available online: https:\/\/arxiv.org\/abs\/1901.03597v3."},{"key":"ref_44","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Kingma, D.P., and Welling, M. (2019). An introduction to variational autoencoders. arXiv.","DOI":"10.1561\/9781680836233"},{"key":"ref_46","unstructured":"Bank, D., Koenigstein, N., and Giryes, R. (2020). Autoencoders. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational inference: A review for statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"J. Am. Stat. Assoc."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/8\/4\/83\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:41:15Z","timestamp":1760136075000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/8\/4\/83"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,23]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["jimaging8040083"],"URL":"https:\/\/doi.org\/10.3390\/jimaging8040083","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,23]]}}}