{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T02:58:21Z","timestamp":1787885901724,"version":"build-2784847793"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":179,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006601","name":"Ministero degli Affari Esteri e della Cooperazione Internazionale","doi-asserted-by":"publisher","award":["PGR01156"],"award-info":[{"award-number":["PGR01156"]}],"id":[{"id":"10.13039\/501100006601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014031","name":"Cancerforskningsfonden i Norrland","doi-asserted-by":"publisher","award":["MP23-1122"],"award-info":[{"award-number":["MP23-1122"]}],"id":[{"id":"10.13039\/501100014031","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016756","name":"Kempe Foundation","doi-asserted-by":"publisher","award":["JCSMK24-0094"],"award-info":[{"award-number":["JCSMK24-0094"]}],"id":[{"id":"10.13039\/100016756","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003765","name":"Universit\u00e0 Campus Bio-Medico di Roma","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003765","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["PE0000013-FAIR"],"award-info":[{"award-number":["PE0000013-FAIR"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computerized Medical Imaging and Graphics"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.compmedimag.2026.102718","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T17:07:45Z","timestamp":1769792865000},"page":"102718","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["XGeM: A multi-prompt foundation model for multimodal medical data generation"],"prefix":"10.1016","volume":"128","author":[{"given":"Daniele","family":"Molino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Di Feola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eliodoro","family":"Faiella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deborah","family":"Fazzini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Domiziana","family":"Santucci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linlin","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valerio","family":"Guarrasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2621-072X","authenticated-orcid":false,"given":"Paolo","family":"Soda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compmedimag.2026.102718_b1","first-page":"191","article-title":"Health insurance portability and accountability act of 1996","volume":"104","author":"Accountability Act","year":"1996","journal-title":"Public Law"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102718_b2","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1186\/s12909-023-04698-z","article-title":"Revolutionizing healthcare: the role of artificial intelligence in clinical practice","volume":"23","author":"Alowais","year":"2023","journal-title":"BMC Med. Educ."},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102718_b3","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/s40537-023-00727-2","article-title":"A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications","volume":"10","author":"Alzubaidi","year":"2023","journal-title":"J. Big Data"},{"issue":"3","key":"10.1016\/j.compmedimag.2026.102718_b4","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1136\/jamia.1997.0040199","article-title":"Understanding and using DICOM, the data interchange standard for biomedical imaging","volume":"4","author":"Bidgood","year":"1997","journal-title":"J. Am. Med. Informatics Assoc."},{"key":"10.1016\/j.compmedimag.2026.102718_b5","first-page":"1","article-title":"A vision\u2013language foundation model for the generation of realistic chest x-ray images","author":"Bluethgen","year":"2024","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.compmedimag.2026.102718_b6","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Making the most of text semantics to improve biomedical vision\u2013language processing","author":"Boecking","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102718_b7","doi-asserted-by":"crossref","first-page":"110843","DOI":"10.1016\/j.compbiomed.2025.110843","article-title":"MARIA: a multimodal transformer model for incomplete healthcare data","volume":"196","author":"Caruso","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.compmedimag.2026.102718_b8","series-title":"Adapting pretrained vision-language foundational models to medical imaging domains","author":"Chambon","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102718_b9","series-title":"Generating radiology reports via memory-driven transformer","author":"Chen","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102718_b10","series-title":"Rethinking attention with performers","author":"Choromanski","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102718_b11","series-title":"International Conference on Medical Imaging with Deep Learning","first-page":"231","article-title":"TorchXRayVision: A library of chest X-ray datasets and models","author":"Cohen","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102718_b12","series-title":"Improving the factual correctness of radiology report generation with semantic rewards","author":"Delbrouck","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102718_b13","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","article-title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning","volume":"107","author":"Elfwing","year":"2018","journal-title":"Neural Netw."},{"key":"10.1016\/j.compmedimag.2026.102718_b14","doi-asserted-by":"crossref","unstructured":"Esser, Patrick, Rombach, Robin, Ommer, Bjorn, 2021. Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12873\u201312883.","DOI":"10.1109\/CVPR46437.2021.01268"},{"issue":"5","key":"10.1016\/j.compmedimag.2026.102718_b15","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1037\/h0031619","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","year":"1971","journal-title":"Psychol. Bull."},{"key":"10.1016\/j.compmedimag.2026.102718_b16","series-title":"General data protection regulation","author":"General Data Protection Regulation GDPR","year":"2016"},{"issue":"11","key":"10.1016\/j.compmedimag.2026.102718_b17","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"10.1016\/j.compmedimag.2026.102718_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105509","article-title":"A systematic review of intermediate fusion in multimodal deep learning for biomedical applications","author":"Guarrasi","year":"2025","journal-title":"Image Vis. Comput."},{"issue":"2","key":"10.1016\/j.compmedimag.2026.102718_b19","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1002\/j.1538-7305.1950.tb00463.x","article-title":"Error detecting and error correcting codes","volume":"29","author":"Hamming","year":"1950","journal-title":"Bell Syst. Tech. J."},{"key":"10.1016\/j.compmedimag.2026.102718_b20","series-title":"Medical Imaging with Deep Learning","first-page":"288","article-title":"Quantifying the value of lateral views in deep learning for chest x-rays","author":"Hashir","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102718_b21","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":"10.1016\/j.compmedimag.2026.102718_b22","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102718_b23","first-page":"590","article-title":"Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison","volume":"vol. 33","author":"Irvin","year":"2019"},{"issue":"1","key":"10.1016\/j.compmedimag.2026.102718_b24","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"issue":"5","key":"10.1016\/j.compmedimag.2026.102718_b25","doi-asserted-by":"crossref","first-page":"895","DOI":"10.3390\/diagnostics11050895","article-title":"Generation of synthetic chest X-ray images and detection of COVID-19: A deep learning based approach","volume":"11","author":"Karbhari","year":"2021","journal-title":"Diagnostics"},{"key":"10.1016\/j.compmedimag.2026.102718_b26","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"vol. 1","author":"Kenton","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102718_b27","article-title":"Improved precision and recall metric for assessing generative models","volume":"32","author":"Kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102718_b28","series-title":"LLM-CXR: Instruction-finetuned LLM for CXR image understanding and generation","author":"Lee","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102718_b29","series-title":"Unified chest x-ray and radiology report generation model with multi-view chest x-rays","first-page":"8","author":"Lee","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102718_b30","series-title":"Optimus: Organizing sentences via pre-trained modeling of a latent space","author":"Li","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102718_b31","series-title":"On error propagation of diffusion models","author":"Li","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102718_b32","series-title":"Improving factual completeness and consistency of image-to-text radiology report generation","author":"Miura","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102718_b33","series-title":"2025 International Joint Conference on Neural Networks (IJCNN)","first-page":"1","article-title":"Any-to-any vision-language model for multimodal X-ray imaging and radiological report generation","author":"Molino","year":"2025"},{"key":"10.1016\/j.compmedimag.2026.102718_b34","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.patrec.2022.10.026","article-title":"Unsupervised contrastive unpaired image generation approach for improving tuberculosis screening using chest X-ray images","volume":"164","author":"Mor\u00eds","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.compmedimag.2026.102718_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2024.101585","article-title":"Longitudinal data and a semantic similarity reward for chest X-ray report generation","volume":"50","author":"Nicolson","year":"2024","journal-title":"Informatics Med. Unlocked"},{"key":"10.1016\/j.compmedimag.2026.102718_b36","series-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"10.1016\/j.compmedimag.2026.102718_b37","series-title":"2023 IEEE 20th International Symposium on Biomedical Imaging","first-page":"1","article-title":"Generation of anonymous chest radiographs using latent diffusion models for training thoracic abnormality classification systems","author":"Packh\u00e4user","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102718_b38","doi-asserted-by":"crossref","unstructured":"Papineni, Kishore, Roukos, Salim, Ward, Todd, Zhu, Wei-Jing, 2002. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.compmedimag.2026.102718_b39","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"8","key":"10.1016\/j.compmedimag.2026.102718_b40","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"issue":"2","key":"10.1016\/j.compmedimag.2026.102718_b41","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1378\/chest.10-1302","article-title":"Interpretation of plain chest roentgenogram","volume":"141","author":"Raoof","year":"2012","journal-title":"Chest"},{"key":"10.1016\/j.compmedimag.2026.102718_b42","doi-asserted-by":"crossref","unstructured":"Rombach, Robin, Blattmann, Andreas, Lorenz, Dominik, Esser, Patrick, Ommer, Bj\u00f6rn, 2022. High-Resolution Image Synthesis With Latent Diffusion Models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.compmedimag.2026.102718_b43","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"10.1016\/j.compmedimag.2026.102718_b44","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10462-023-10624-y","article-title":"A survey on training challenges in generative adversarial networks for biomedical image analysis","volume":"57","author":"Saad","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.compmedimag.2026.102718_b45","doi-asserted-by":"crossref","first-page":"1447","DOI":"10.1007\/s11517-018-1786-3","article-title":"Angular relational signature-based chest radiograph image view classification","volume":"56","author":"Santosh","year":"2018","journal-title":"Med. Biol. Eng. Comput."},{"key":"10.1016\/j.compmedimag.2026.102718_b46","series-title":"Big Data Analytics and Artificial Intelligence Against COVID-19: Innovation Vision and Approach","first-page":"147","article-title":"Why are generative adversarial networks vital for deep neural networks? A case study on COVID-19 chest X-ray images","author":"Shams","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102718_b47","series-title":"2021 11th International Conference on Cloud Computing, Data Science & Engineering","first-page":"433","article-title":"Improved classification for pneumonia detection using transfer learning with GAN based synthetic image augmentation","author":"Srivastav","year":"2021"},{"key":"10.1016\/j.compmedimag.2026.102718_b48","doi-asserted-by":"crossref","unstructured":"Tang, Zineng, Yang, Ziyi, Zhu, Chenguang, Zeng, Michael, Bansal, Mohit, 2023. Any-to-Any Generation via Composable Diffusion. In: Thirty-Seventh Conference on Neural Information Processing Systems.","DOI":"10.52202\/075280-0707"},{"key":"10.1016\/j.compmedimag.2026.102718_b49","series-title":"Deep Generative Models, and Data Augmentation, Labelling, and Imperfections: First Workshop, DGM4MICCAI 2021, and First Workshop, DALI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021, Proceedings 1","first-page":"112","article-title":"Evaluating GANs in medical imaging","author":"Tronchin","year":"2021"},{"key":"10.1016\/j.compmedimag.2026.102718_b50","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102718_b51","doi-asserted-by":"crossref","unstructured":"Wu, Yuxin, He, Kaiming, 2018. Group normalization. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"10.1016\/j.compmedimag.2026.102718_b52","doi-asserted-by":"crossref","unstructured":"Xu, Xingqian, Wang, Zhangyang, Zhang, Gong, Wang, Kai, Shi, Humphrey, 2023. Versatile diffusion: Text, images and variations all in one diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 7754\u20137765.","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"10.1016\/j.compmedimag.2026.102718_b53","series-title":"Ratescore: A metric for radiology report generation","author":"Zhao","year":"2024"}],"container-title":["Computerized Medical Imaging and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611126000212?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0895611126000212?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T21:44:19Z","timestamp":1785447859000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0895611126000212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":53,"alternative-id":["S0895611126000212"],"URL":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102718","relation":{},"ISSN":["0895-6111"],"issn-type":[{"value":"0895-6111","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"XGeM: A multi-prompt foundation model for multimodal medical data generation","name":"articletitle","label":"Article Title"},{"value":"Computerized Medical Imaging and Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102718","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"102718"}}