{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:04:58Z","timestamp":1757621098682,"version":"3.44.0"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T00:00:00Z","timestamp":1754092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T00:00:00Z","timestamp":1754092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Netw Model Anal Health Inform Bioinforma"],"DOI":"10.1007\/s13721-025-00579-1","type":"journal-article","created":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T09:26:24Z","timestamp":1754126784000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal multimodal transformer for automated radiology reporting in traumatic brain injuries"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3944-0607","authenticated-orcid":false,"given":"Riadh","family":"Bouslimi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariem","family":"Medini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maissa","family":"Ben Fradj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,2]]},"reference":[{"issue":"11","key":"579_CR1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.10.11.110501","volume":"10","author":"N Aksoy","year":"2023","unstructured":"Aksoy N, Ravikumar N, Frangi AF (2023) Radiology report generation using transformers conditioned with non-imaging data. J Med Imag 10(11):110501. https:\/\/doi.org\/10.1117\/1.JMI.10.11.110501","journal-title":"Journal of Medical Imaging"},{"issue":"1","key":"579_CR2","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1186\/s12909-023-04698-z","volume":"23","author":"SA Alowais","year":"2023","unstructured":"Alowais SA, Alghamdi SS, Alsuhebany N, Alqahtani T, Alshaya AI, Almohareb SN, Aldairem A, Alrashed M, Bin Saleh K, Badreldin HA, Al Yami MS, Al Harbi S, Albekairy AM (2023) Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ 23(1):689. https:\/\/doi.org\/10.1186\/s12909-023-04698-z","journal-title":"BMC Med Educ"},{"key":"579_CR3","doi-asserted-by":"publisher","unstructured":"AlSaad R, Abd-alrazaq A, Boughorbel S, Ahmed A, Renault MA, Damseh R, Sheikh J (2024) Multimodal large language models in health care: applications, challenges, and future outlook. J Med Internet Res 26(1):e59505. https:\/\/doi.org\/10.2196\/59505, https:\/\/www.jmir.org\/2024\/1\/e59505","DOI":"10.2196\/59505"},{"key":"579_CR4","doi-asserted-by":"publisher","unstructured":"Bajwa J, Munir U, Nori A, Williams B (2021) Artificial intelligence in healthcare: transforming the practice of medicine. Fut Healthc J 8(2):e188\u2013e194. https:\/\/doi.org\/10.7861\/fhj.2021-0095, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC8285156\/","DOI":"10.7861\/fhj.2021-0095"},{"key":"579_CR5","doi-asserted-by":"publisher","unstructured":"Boecking B, Usuyama N, Bannur S, Castro DC, Schwaighofer A, Hyland S, Wetscherek M, Naumann T, Nori A, Alvarez-Valle J, Poon H, Oktay O (2022) Making the most of text semantics to improve biomedical vision-language processing In: Avidan S, Brostow G, Ciss\u00e9 M, Farinella GM, Hassner T (eds) Computer vision\u2013ECCV 2022. pp 1\u201321. Springer Nature Switzerland, Cham https:\/\/doi.org\/10.1007\/978-3-031-20059-5_1","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"579_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01411-y","author":"R Bouslimi","year":"2025","unstructured":"Bouslimi R, Trabelsi H, Karaa WBA, Hedhli H (2025) AI-driven radiology report generation for traumatic brain injuries. J Imag Inform Med. https:\/\/doi.org\/10.1007\/s10278-025-01411-y","journal-title":"Journal of Imaging Informatics in Medicine"},{"key":"579_CR7","doi-asserted-by":"publisher","unstructured":"Chen T, Zeng Q (2024) Research on bubble detection based on improved YOLOv8n. IEEE Access 12:9659\u20139668. https:\/\/doi.org\/10.1109\/ACCESS.2024.3353196, https:\/\/ieeexplore.ieee.org\/document\/10398207, conference Name: IEEE Access","DOI":"10.1109\/ACCESS.2024.3353196"},{"key":"579_CR8","doi-asserted-by":"publisher","unstructured":"Chen Z, Song Y, Chang TH, Wan X (2020) Generating radiology reports via memory-driven transformer In: Webber B, Cohn T, He Y, Liu Y (eds) Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). pp 1439\u20131449. Association for computational linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.112, https:\/\/aclanthology.org\/2020.emnlp-main.112\/","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"579_CR9","doi-asserted-by":"publisher","unstructured":"Chen Z, Song Y, Chang TH, Wan X (2020) Generating radiology reports via memory-driven transformer. In: Webber B, Cohn T, He Y, Liu Y (eds) Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). pp 1439\u20131449. Association for computational linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.112, https:\/\/aclanthology.org\/2020.emnlp-main.112\/","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"issue":"10162","key":"579_CR10","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.1016\/S0140-6736(18)31645-3","volume":"392","author":"S Chilamkurthy","year":"2018","unstructured":"Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, Mahajan V, Rao P, Warier P (2018) Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet (London England) 392(10162):2388\u20132396. https:\/\/doi.org\/10.1016\/S0140-6736(18)31645-3","journal-title":"Lancet (London England)"},{"key":"579_CR11","doi-asserted-by":"crossref","unstructured":"Cornia M, Stefanini M, Baraldi L, Cucchiara R (2020) Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 10578\u201310587","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"579_CR12","doi-asserted-by":"publisher","unstructured":"Dai Y, Gao Y, Liu F (2021) TransMed: transformers advance multi-modal medical image classification. Diagnostics 11(8):1384. https:\/\/doi.org\/10.3390\/diagnostics11081384, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC8391808\/","DOI":"10.3390\/diagnostics11081384"},{"key":"579_CR13","doi-asserted-by":"publisher","unstructured":"Dixon J, Comstock G, Whitfield J, Richards D, Burkholder TW, Leifer N, Mould-Millman NK, Calvello Hynes EJ (2020) Emergency department management of traumatic brain injuries: a resource tiered review. Afr J Emerg Med 10(3):159\u2013166. https:\/\/doi.org\/10.1016\/j.afjem.2020.05.006, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2211419X2030046X","DOI":"10.1016\/j.afjem.2020.05.006"},{"key":"579_CR14","doi-asserted-by":"publisher","unstructured":"Eker AG, Pehlivanoglu MK, Ince I, Duru N (2023) Deep learning and transfer learning based brain tumor segmentation. In: 2023 8th international conference on computer science and engineering (UBMK). pp 163\u2013168. https:\/\/doi.org\/10.1109\/UBMK59864.2023.10286591, https:\/\/ieeexplore.ieee.org\/document\/10286591, iSSN: 2521-1641","DOI":"10.1109\/UBMK59864.2023.10286591"},{"issue":"1","key":"579_CR15","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s44326-024-00043-w","volume":"11","author":"SC Fanni","year":"2024","unstructured":"Fanni SC, Tumminello L, Formica V, Caputo FP, Aghakhanyan G, Ambrosini I, Francischello R, Faggioni L, Cioni D, Neri E (2024) The journey from natural language processing to large language models: key insights for radiologists. J Med Imag Intervent Radiol 11(1):43. https:\/\/doi.org\/10.1007\/s44326-024-00043-w","journal-title":"Journal of Medical Imaging and Interventional Radiology"},{"key":"579_CR16","doi-asserted-by":"publisher","unstructured":"Guo KH, Chaudhari NN, Jafar T, Chowdhury NF, Bogdan P, Irimia A (2024) Anatomic interpretability in neuroimage deep learning: saliency approaches for typical aging and traumatic brain injury. Neuroinformatics 22(4):591\u2013606. https:\/\/doi.org\/10.1007\/s12021-024-09694-2, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC11579113\/","DOI":"10.1007\/s12021-024-09694-2"},{"key":"579_CR17","doi-asserted-by":"publisher","unstructured":"Guo Z, Gu Z, Zheng B, Dong J, Zheng H (2023) Transformer for image harmonization and beyond. IEEE Trans Pattern Anal Mach Intell 45(11):12960\u201312977. https:\/\/doi.org\/10.1109\/TPAMI.2022.3207091https:\/\/ieeexplore.ieee.org\/document\/9893399, conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2022.3207091"},{"key":"579_CR18","doi-asserted-by":"publisher","unstructured":"Han Q, Liu J, Qin Z, Zheng Z (2024) Integrating MedCLIP and cross-modal fusion for automatic radiology report generation. In: 2024 IEEE international conference on big data (BigData). pp. 7313\u20137317. https:\/\/doi.org\/10.1109\/BigData62323.2024.10825240, https:\/\/ieeexplore.ieee.org\/document\/10825240, iSSN: 2573-2978","DOI":"10.1109\/BigData62323.2024.10825240"},{"key":"579_CR19","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 770\u2013778, http:\/\/arxiv.org\/abs\/1512.03385","DOI":"10.1109\/CVPR.2016.90"},{"key":"579_CR20","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"579_CR21","doi-asserted-by":"publisher","unstructured":"He K, Gan C, Li Z, Rekik I, Yin Z, Ji W, Gao Y, Wang Q, Zhang J, Shen D (2023) Transformers in medical image analysis. Intell Med 03(01):59\u201378. https:\/\/doi.org\/10.1016\/j.imed.2022.07.002, https:\/\/mednexus.org\/doi\/10.1016\/j.imed.2022.07.002, publisher: Chinese Medical Association Publishing House","DOI":"10.1016\/j.imed.2022.07.002"},{"key":"579_CR22","doi-asserted-by":"publisher","unstructured":"Jain S, Agrawal A, Saporta A, Truong SQ, Nguyen\u00a0Duong D, Bui T, Chambon P, Lungren M, Ng A, Langlotz C, Rajpurkar P RadGraph: Extracting clinical entities and relations from radiology reports. https:\/\/doi.org\/10.13026\/HM87-5P47, https:\/\/physionet.org\/content\/radgraph\/1.0.0\/","DOI":"10.13026\/HM87-5P47"},{"key":"579_CR23","doi-asserted-by":"publisher","unstructured":"Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y, Dong Q, Shen H, Wang Y (2017) Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2(4) https:\/\/doi.org\/10.1136\/svn-2017-000101https:\/\/svn.bmj.com\/content\/2\/4\/230, publisher: BMJ Publishing Group Ltd","DOI":"10.1136\/svn-2017-000101"},{"issue":"1","key":"579_CR24","first-page":"128","volume":"26","author":"X Jiang","year":"2022","unstructured":"Jiang X, Liu Y, Wang Q (2022) Deepgan-based data augmentation for improved brain lesion segmentation in low-data regimes. IEEE J Biomed Health Inform 26(1):128\u2013137","journal-title":"IEEE J Biomed Health Inform"},{"key":"579_CR25","doi-asserted-by":"publisher","unstructured":"Karaboue MAA, Ministeri F, Sessa F, Nannola C, Chisari MG, Cocimano G, Di Mauro L, Salerno M, Esposito M (2024) Traumatic brain injury as a public health issue: epidemiology, prognostic factors and useful data from forensic practice. Healthcare 12(22):2266. https:\/\/doi.org\/10.3390\/healthcare12222266, https:\/\/www.mdpi.com\/2227-9032\/12\/22\/2266, number: 22 Publisher: Multidisciplinary Digital Publishing Institute","DOI":"10.3390\/healthcare12222266"},{"key":"579_CR26","doi-asserted-by":"publisher","unstructured":"Karalis VD (2024) The integration of artificial intelligence into clinical practice. Appl Biosci 3(1):14\u201344. https:\/\/doi.org\/10.3390\/applbiosci3010002, https:\/\/www.mdpi.com\/2813-0464\/3\/1\/2, number: 1 Publisher: Multidisciplinary Digital Publishing Institute","DOI":"10.3390\/applbiosci3010002"},{"key":"579_CR27","doi-asserted-by":"publisher","unstructured":"Khan RF, Lee BD, Lee MS (2023) Transformers in medical image segmentation: a narrative review. Quant Imag Med Surg 13(12):8747\u20138767 https:\/\/doi.org\/10.21037\/qims-23-542, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC10722011\/","DOI":"10.21037\/qims-23-542"},{"key":"579_CR28","unstructured":"Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. International conference on learning representations (ICLR)"},{"key":"579_CR29","doi-asserted-by":"publisher","unstructured":"Kushnure DT, Talbar SN (2021) MS-UNet: A multi-scale UNet with feature recalibration approach for automatic liver and tumor segmentation in CT images. Comput Med Imag Graph 89:101885. https:\/\/doi.org\/10.1016\/j.compmedimag.2021.101885, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0895611121000331","DOI":"10.1016\/j.compmedimag.2021.101885"},{"key":"579_CR30","volume":"101","author":"J Lee","year":"2023","unstructured":"Lee J, Park M, Kim S (2023) Neurogen: Generating clinically consistent brain imaging sequences using attention-guided gans. Comput Med Imag Graph 101:102156","journal-title":"Comput Med Imaging Graph"},{"key":"579_CR31","doi-asserted-by":"publisher","unstructured":"Lei B, Liang Y, Xie J, Wu Y, Liang E, Liu Y, Yang P, Wang T, Liu C, Du J, Xiao X, Wang S (2024) Hybrid federated learning with brain-region attention network for multi-center Alzheimer\u2019s disease detection. Pattern Recogn 153:110423. https:\/\/doi.org\/10.1016\/j.patcog.2024.110423, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320324001742","DOI":"10.1016\/j.patcog.2024.110423"},{"key":"579_CR32","doi-asserted-by":"publisher","unstructured":"Li L (2024) Research on personalized recommendation system for e-commerce products based on collaborative filtering algorithm. In: 2024 IEEE 3rd international conference on electrical engineering, big data and algorithms (EEBDA). pp 876\u2013880. https:\/\/doi.org\/10.1109\/EEBDA60612.2024.10485710,","DOI":"10.1109\/EEBDA60612.2024.10485710"},{"key":"579_CR33","doi-asserted-by":"publisher","unstructured":"Li LM, Dilley MD, Carson A, Twelftree J, Hutchinson PJ, Belli A, Betteridge S, Cooper PN, Griffin CM, Jenkins PO, Liu C, Sharp DJ, Sylvester R, Wilson MH, Turner MS, Greenwood R (2021) Management of traumatic brain injury (TBI): a clinical neuroscience-led pathway for the NHS. Clin Med 21(2):e198\u2013e205. https:\/\/doi.org\/10.7861\/clinmed.2020-0336, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1470211824033487","DOI":"10.7861\/clinmed.2020-0336"},{"key":"579_CR34","unstructured":"Lin CY (2004) Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out: proceedings of the ACL-04 Workshop. pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain, https:\/\/aclanthology.org\/W04-1013\/"},{"key":"579_CR35","doi-asserted-by":"publisher","unstructured":"Lin J, Li Z, Zeng Y, Liu X, Li L, Jahanshad N, Ge X, Zhang D, Lu M, Liu M (2024) Harmonizing three-dimensional MRI using pseudo-warping field guided GAN. Neuroimage 295:120635. https:\/\/doi.org\/10.1016\/j.neuroimage.2024.120635https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1053811924001307","DOI":"10.1016\/j.neuroimage.2024.120635"},{"key":"579_CR36","doi-asserted-by":"publisher","unstructured":"Maas, AIR, Menon DK, Manley GT, Abrams M, Akerlund C, Andelic N, Aries M, Bashford T, Bell MJ, Bodien YG, Brett BL, B\u00fcki A, Chesnut RM, Citerio G, Clark D, Clasby B, Cooper DJ, Czeiter E, Czosnyka M, Dams-O\u2019Connor K, De Keyser V, Diaz-Arrastia R, Ercole A, van Essen TA, Falvey \u00c9, Ferguson AR, Figaji A, Fitzgerald M, Foreman B, Gantner D, Gao G, Giacino J, Gravesteijn B, Guiza F, Gupta D, Gurnell M, Haagsma JA, Hammond FM, Hawryluk G, Hutchinson P, van der Jagt M, Jain S, Jain S, Jiang, Jy, Kent H, Kolias A, Kompanje EJO, Lecky F, Lingsma HF, Maegele M, Majdan M, Markowitz A, McCrea M, Meyfroidt G, Mikolic A, Mondello S, Mukherjee P, Nelson D, Nelson LD, Newcombe V, Okonkwo D, Oresic M, Peul W, Pisic\u0103 D, Polinder S, Ponsford J, Puybasset L, Raj R, Robba C, R\u00f8e C, Rosand J, Schueler P, Sharp DJ, Smielewski P, Stein MB, von Steinb\u00fcchel N, Stewart W, Steyerberg EW, Stocchetti N, Temkin N, Tenovuo O, Theadom A, Thomas I, Espin AT, Turgeon AF, Unterberg A, Van Praag D, van Veen E, Verheyden J, Vyvere TV, Wang KKW, Wiegers EJA, Williams WH, Wilson L, Wisniewski SR, Younsi A, Yue JK, Yuh EL, Zeiler FA, Zeldovich M, Zemek R (2022) Traumatic brain injury: progress and challenges in prevention, clinical care, and research. Lancet Neurol 21(11):1004\u20131060 https:\/\/doi.org\/10.1016\/S1474-4422(22)00309-X, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC10427240\/","DOI":"10.1016\/S1474-4422(22)00309-X"},{"key":"579_CR37","doi-asserted-by":"publisher","unstructured":"Maleki Varnosfaderani S, Forouzanfar M (2024) The role of AI in hospitals and clinics: transforming healthcare in the 21st century. Bioengineering 11(4):337. https:\/\/doi.org\/10.3390\/bioengineering11040337, https:\/\/www.mdpi.com\/2306-5354\/11\/4\/337, number: 4 Publisher: Multidisciplinary Digital Publishing Institute","DOI":"10.3390\/bioengineering11040337"},{"key":"579_CR38","doi-asserted-by":"publisher","unstructured":"Mota GSdL, Silva MVd, Mari JF, Backes AR (2025) Identifying malignant skin diseases through deep learning. Rev Inform Te\u00f3r Apli 32(1):204\u2013211 https:\/\/doi.org\/10.22456\/2175-2745.143463, https:\/\/seer.ufrgs.br\/index.php\/rita\/article\/view\/143463, number: 1","DOI":"10.22456\/2175-2745.143463"},{"issue":"5","key":"579_CR39","doi-asserted-by":"publisher","first-page":"e295","DOI":"10.1016\/S2589-7500(21)00040-6","volume":"3","author":"O Nitski","year":"2021","unstructured":"Nitski O, Azhie A, Qazi-Arisar FA, Wang X, Ma S, Lilly L, Watt KD, Levitsky J, Asrani SK, Lee DS, Rubin BB, Bhat M, Wang B (2021) Long-term mortality risk stratification of liver transplant recipients: real-time application of deep learning algorithms on longitudinal data. Lancet Dig Health 3(5):e295\u2013e305. https:\/\/doi.org\/10.1016\/S2589-7500(21)00040-6","journal-title":"The Lancet Digital Health"},{"key":"579_CR40","unstructured":"of\u00a0North\u00a0America RS (2019) Rsna intracranial hemorrhage detection challenge. https:\/\/www.kaggle.com\/c\/rsna-intracranial-hemorrhage-detection, rSNA 2019 Challenge"},{"key":"579_CR41","doi-asserted-by":"publisher","unstructured":"Pan Y, Liu LJ, Yang XB, Peng W, Huang QS (2024) Chest radiology report generation based on cross-modal multi-scale feature fusion. J Radiat Res Appl Sci 17(1):100823. https:\/\/doi.org\/10.1016\/j.jrras.2024.100823, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1687850724000074","DOI":"10.1016\/j.jrras.2024.100823"},{"key":"579_CR42","unstructured":"Pan Y, Zhao L, Liu Y, et\u00a0al (2023) Longitudinal brain image synthesis via clinical conditioned diffusion models. In: Proceedings of MICCAI"},{"key":"579_CR43","doi-asserted-by":"publisher","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics (ACL). pp 311\u2013318. Association for Computational Linguistics. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"579_CR44","doi-asserted-by":"publisher","unstructured":"Parres D, Albiol A, Paredes R (2024) Improving radiology report generation quality and diversity through reinforcement learning and text augmentation. Bioengineering 11(4):351. https:\/\/doi.org\/10.3390\/bioengineering11040351https:\/\/www.mdpi.com\/2306-5354\/11\/4\/351, number: 4 Publisher: Multidisciplinary Digital Publishing Institute","DOI":"10.3390\/bioengineering11040351"},{"key":"579_CR45","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, K\u00f6pf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S (2019) Pytorch An imperative style high-performance deep learning library https:\/\/arxiv.org\/abs\/1912.01703"},{"key":"579_CR46","doi-asserted-by":"publisher","unstructured":"Pinto-Coelho L (2023) How artificial intelligence is shaping medical imaging technology: a survey of innovations and applications. Bioengineering 10(12):1435. https:\/\/doi.org\/10.3390\/bioengineering10121435, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC10740686\/","DOI":"10.3390\/bioengineering10121435"},{"key":"579_CR47","unstructured":"Prabhakar C, Li H, Yang J, Shit S, Wiestler B, Menze B (2014) ViT-AE++ improving vision transformer autoencoder for self-supervised medical image representations In: Medical imaging with deep learning. pp 666\u2013679. PMLR (Jan 2024), https:\/\/proceedings.mlr.press\/v227\/prabhakar24b.html, iSSN: 2640-3498"},{"key":"579_CR48","doi-asserted-by":"publisher","unstructured":"Qin Z, Liu J, Zhang X, Tian M, Zhou A, Yi S, Li H (2024) Pyramid fusion transformer for semantic segmentation. IEEE Trans Multimedia 26:9630\u20139643. https:\/\/doi.org\/10.1109\/TMM.2024.3396281, https:\/\/ieeexplore.ieee.org\/abstract\/document\/10540365, conference Name: IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2024.3396281"},{"key":"579_CR49","unstructured":"Ramesh V, Chi NA, Rajpurkar P (2022) Improving radiology report generation systems by removing hallucinated references to non-existent priors https:\/\/arxiv.org\/abs\/2210.06340"},{"key":"579_CR50","doi-asserted-by":"publisher","unstructured":"Rauchman SH, Albert J, Pinkhasov A, Reiss AB (2022) Mild-to-moderate traumatic brain injury: a review with focus on the visual system. Neurol Int 14(2):453\u2013470. https:\/\/doi.org\/10.3390\/neurolint14020038, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC9227114\/","DOI":"10.3390\/neurolint14020038"},{"key":"579_CR51","doi-asserted-by":"publisher","unstructured":"Sadeghi Z, Alizadehsani R, Cifci MA, Kausar S, Rehman R, Mahanta P, Bora PK, Almasri A, Alkhawaldeh RS, Hussain S, Alatas B, Shoeibi A, Moosaei H, Hlad\u00edk M, Nahavandi S, Pardalos PM (2024) A review of explainable artificial intelligence in healthcare. Comput Electr Eng 118:109370, https:\/\/doi.org\/10.1016\/j.compeleceng.2024.109370https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0045790624002982","DOI":"10.1016\/j.compeleceng.2024.109370"},{"key":"579_CR52","doi-asserted-by":"publisher","unstructured":"Shah J, Che Y, Sohankar J, Luo J, Li B, Su Y, Wu T (2024) for the Alzheimer\u2019s disease neuroimaging initiative: enhancing amyloid PET quantification: MRI-guided super-resolution using latent diffusion models. Life 14(12):1580. https:\/\/doi.org\/10.3390\/life14121580, https:\/\/www.mdpi.com\/2075-1729\/14\/12\/1580, number: 12 Publisher: Multidisciplinary Digital Publishing Institute","DOI":"10.3390\/life14121580"},{"key":"579_CR53","doi-asserted-by":"publisher","unstructured":"Shamshad F, Khan S, Zamir SW, Khan MH, Hayat M, Khan FS, Fu H (2023) Transformers in medical imaging: a survey. Med Image Anal 88:102802. https:\/\/doi.org\/10.1016\/j.media.2023.102802, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1361841523000634","DOI":"10.1016\/j.media.2023.102802"},{"key":"579_CR54","doi-asserted-by":"publisher","unstructured":"Sharma D, Purushotham S, Reddy CK (2021) MedFuseNet: an attention-based multimodal deep learning model for visual question answering in the medical domain. Sci Rep 11(1):19826. https:\/\/doi.org\/10.1038\/s41598-021-98390-1, https:\/\/www.nature.com\/articles\/s41598-021-98390-1, publisher: Nature Publishing Group","DOI":"10.1038\/s41598-021-98390-1"},{"key":"579_CR55","doi-asserted-by":"crossref","unstructured":"Singh H, Sharma A, Pant M (2024) Pixels to prose: understanding the art of image captioning, https:\/\/arxiv.org\/abs\/2408.15714","DOI":"10.2139\/ssrn.5351410"},{"key":"579_CR56","doi-asserted-by":"publisher","unstructured":"Sun S, Mei Z, Li X, Tang T, Su Z, Wu Y (2024) A label information fused medical image report generation framework. Artif Intell Med 150:102823. https:\/\/doi.org\/10.1016\/j.artmed.2024.102823, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0933365724000654","DOI":"10.1016\/j.artmed.2024.102823"},{"key":"579_CR57","doi-asserted-by":"publisher","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 10781\u201310790. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01080","DOI":"10.1109\/CVPR42600.2020.01080"},{"key":"579_CR58","doi-asserted-by":"publisher","unstructured":"Tsaniya H, Fatichah C, Suciati N (2024) Automatic radiology report generator using transformer with contrast-based image enhancement. IEEE Access 12:25429\u201325442. https:\/\/doi.org\/10.1109\/ACCESS.2024.3364373, https:\/\/ieeexplore.ieee.org\/document\/10430201, conference Name: IEEE Access","DOI":"10.1109\/ACCESS.2024.3364373"},{"key":"579_CR59","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need In: Proceedings of the 31st international conference on neural information processing systems. pp 6000\u20136010. NIPS\u201917, Curran Associates Inc., Red Hook, NY, USA"},{"key":"579_CR60","doi-asserted-by":"publisher","unstructured":"Vedantam R, Zitnick CL, Parikh D (2015) Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 4566\u20134575. IEEE. https:\/\/doi.org\/10.1109\/CVPR.2015.7299087","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"579_CR61","doi-asserted-by":"publisher","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). pp 3156\u20133164. https:\/\/doi.org\/10.1109\/CVPR.2015.7298935, https:\/\/ieeexplore.ieee.org\/document\/7298935, iSSN: 1063-6919","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"579_CR62","doi-asserted-by":"publisher","unstructured":"Wang H, Chen Y, Ma C, Avery J, Hull L, Carneiro G (2023) Multi-modal learning with missing modality via shared-specific feature modelling. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 15878\u201315887. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01524","DOI":"10.1109\/CVPR52729.2023.01524"},{"key":"579_CR63","doi-asserted-by":"publisher","unstructured":"Wang L, Ning M, Lu D, Wei D, Zheng Y, Chen J (2022) An inclusive task-aware framework for radiology report generation. In: Wang L, Dou Q, Fletcher PT, Speidel S, Li S (eds) Medical image computing and computer assisted intervention\u2013MICCAI 2022. pp 568\u2013577. Springer Nature Switzerland, Cham. https:\/\/doi.org\/10.1007\/978-3-031-16452-1_54","DOI":"10.1007\/978-3-031-16452-1_54"},{"key":"579_CR64","unstructured":"Xu L, Liu B, Khan AH, Fan L, Wu XM (2023) Multi-modal pre-training for medical vision-language understanding and generation: an empirical study with a new benchmark. In: Proceedings of the conference on health, inference, and learning. pp 117\u2013132. PMLR, https:\/\/proceedings.mlr.press\/v209\/xu23a.html, iSSN: 2640-3498"},{"key":"579_CR65","doi-asserted-by":"publisher","unstructured":"Yan S, Cheung WK, Tsang IW, Chiu K, Tong TM, Cheung KC, See S (2024) AHIVE: Anatomy-aware hierarchical vision encoding for interactive radiology report retrieval: 2024 37th IEEE\/CVF conference on computer vision and pattern recognition, CVPR 2024. Proceedings of 2024 IEEE\/CVF conference on computer vision and pattern recognition, CVPR 2024 pp 14324\u201314333. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01358, https:\/\/ieeexplore.ieee.org\/document\/10656768, publisher: IEEE","DOI":"10.1109\/CVPR52733.2024.01358"},{"key":"579_CR66","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101552","volume":"58","author":"X Yi","year":"2020","unstructured":"Yi X, Walia E, Babyn P (2020) Generative adversarial network in medical imaging: a review. Med Image Anal 58:101552","journal-title":"Med Image Anal"},{"key":"579_CR67","unstructured":"Zhang L, Alavi A, Hossain M (2024) Conditional gans for progressive brain lesion simulation in traumatic injury imaging. IEEE Trans Med Imag. in press"},{"key":"579_CR68","unstructured":"Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2020) Bertscore: Evaluating text generation with bert. In: Proceedings of the international conference on learning representations (ICLR), https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"579_CR69","doi-asserted-by":"publisher","unstructured":"Zhang Y, Peng C, Wang Q, Song D, Li K, Kevin Zhou S (2025) Unified multi-modal image synthesis for missing modality imputation. IEEE Trans Med Imag 44(1):4\u201318. https:\/\/doi.org\/10.1109\/TMI.2024.3424785, https:\/\/ieeexplore.ieee.org\/document\/10589432, conference Name: IEEE Transactions on Medical Imaging","DOI":"10.1109\/TMI.2024.3424785"},{"key":"579_CR70","doi-asserted-by":"publisher","unstructured":"Zhao L, Zhang J, Xu B, Yang Y, Zhang Y, Ma R (2024) Multimodal contrastive learning with neuroimaging and cognitive tests for Alzheimer\u2019s disease diagnosis. In: 2024 IEEE international conference on bioinformatics and biomedicine (BIBM). pp 2971\u20132976. https:\/\/doi.org\/10.1109\/BIBM62325.2024.10822064, https:\/\/ieeexplore.ieee.org\/abstract\/document\/10822064, iSSN: 2156-1133","DOI":"10.1109\/BIBM62325.2024.10822064"},{"issue":"6","key":"579_CR71","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1038\/s41551-023-01045-x","volume":"7","author":"HY Zhou","year":"2023","unstructured":"Zhou HY, Yu Y, Wang C, Zhang S, Gao Y, Pan J, Shao J, Lu G, Zhang K, Li W (2023) A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nat Biomed Eng 7(6):743\u2013755. https:\/\/doi.org\/10.1038\/s41551-023-01045-x","journal-title":"Nature Biomedical Engineering"},{"key":"579_CR72","doi-asserted-by":"publisher","unstructured":"Zhu D, Wang D (2023) Transformers and their application to medical image processing: a review. J Radiat Res Appl Sci 16(4):100680. https:\/\/doi.org\/10.1016\/j.jrras.2023.100680, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1687850723001589","DOI":"10.1016\/j.jrras.2023.100680"}],"container-title":["Network Modeling Analysis in Health Informatics and Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13721-025-00579-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13721-025-00579-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13721-025-00579-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T12:00:21Z","timestamp":1757332821000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13721-025-00579-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,2]]},"references-count":72,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["579"],"URL":"https:\/\/doi.org\/10.1007\/s13721-025-00579-1","relation":{},"ISSN":["2192-6670"],"issn-type":[{"type":"electronic","value":"2192-6670"}],"subject":[],"published":{"date-parts":[[2025,8,2]]},"assertion":[{"value":"24 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"78"}}