{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:53:08Z","timestamp":1781484788249,"version":"3.54.1"},"reference-count":104,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":49,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"DOI":"10.1007\/s10462-026-11556-z","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T08:55:06Z","timestamp":1777280106000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic radiology report generation: a systematic review of emerging AI architectures and multimodal\u00a0technologies"],"prefix":"10.1007","volume":"59","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3914-4944","authenticated-orcid":false,"given":"Moustapha","family":"Boubacar Hamma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0903-6160","authenticated-orcid":false,"given":"Zakariae","family":"Alami Merrouni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9711-0841","authenticated-orcid":false,"given":"Bouchra","family":"Frikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-5617","authenticated-orcid":false,"given":"Brahim","family":"Ouhbi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"11556_CR1","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi A, Berrada M (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6:52138\u201352160. https:\/\/doi.org\/10.1109\/ACCESS.2018.2870052","journal-title":"IEEE Access"},{"key":"11556_CR2","doi-asserted-by":"publisher","unstructured":"Alam HM, Srivastav D, Mohamed Selim A, Kadir MA, Shuvo MM, Sonntag D (2025) CBM-RAG: demonstrating enhanced interpretability in radiology report generation with multi-agent rag and concept bottleneck models. In: Companion Proceedings of the 17th ACM SIGCHI Symposium on Engineering Interactive Computing Systems (pp. 59-61). https:\/\/doi.org\/10.1145\/3731406.3731970","DOI":"10.1145\/3731406.3731970"},{"key":"11556_CR3","doi-asserted-by":"publisher","unstructured":"Alayrac JB, Donahue J, Luc P, et al. 2022. Flamingo: a visual language model for few-shot learning. arXiv:2204.14198. Preprint, arXiv https:\/\/doi.org\/10.48550\/arXiv.2204.14198.","DOI":"10.48550\/arXiv.2204.14198"},{"key":"11556_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100557","volume":"24","author":"O Alfarghaly","year":"2021","unstructured":"Alfarghaly O, Khaled R, Elkorany A, Helal M, Fahmy A (2021) Automated radiology report generation using conditioned transformers. Informatics Med Unlocked 24:100557. https:\/\/doi.org\/10.1016\/j.imu.2021.100557","journal-title":"Informatics Med Unlocked"},{"key":"11556_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3286606.3286863","volume":"18","author":"I Allaouzi","year":"2018","unstructured":"Allaouzi I, Ben Ahmed M, Benamrou B, Ouardouz M (2018) Automatic caption generation for medical images. Proceedings of the 3rd International Conference on Smart City Applications 18:1\u20136. https:\/\/doi.org\/10.1145\/3286606.3286863","journal-title":"Proceedings of the 3rd International Conference on Smart City Applications"},{"key":"11556_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson P, Fernando B, Johnson M, Gould S (2016) SPICE: Semantic propositional image caption evaluation. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision \u2013 ECCV 2016. Springer International Publishing, Cham. https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"issue":"4","key":"11556_CR7","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240476","volume":"7","author":"ST Arasteh","year":"2025","unstructured":"Arasteh ST, Lotfinia M, Bressem K et al (2025) RadioRAG: online retrieval-augmented generation for radiology question answering. Radiol Artif Intell 7(4):e240476. https:\/\/doi.org\/10.1148\/ryai.240476","journal-title":"Radiol Artif Intell"},{"key":"11556_CR8","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural Machine Translation by Jointly Learning to Align and Translate\u2019. arXiv.Org. https:\/\/arxiv.org\/abs\/1409.0473v7."},{"key":"11556_CR9","unstructured":"Banerjee S, Lavie A (2005) METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Jade Goldstein, Alon Lavie, Chin-Yew Lin, and Clare Voss (eds) Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. Association for Computational Linguistics. https:\/\/aclanthology.org\/W05-0909."},{"issue":"1","key":"11556_CR10","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/s42058-023-00132-x","volume":"7","author":"S Biswas","year":"2024","unstructured":"Biswas S, Khan S, Awal SS (2024) Can ChatGPT write radiology reports? Chin J Acad Radiol 7(1):102\u2013106. https:\/\/doi.org\/10.1007\/s42058-023-00132-x","journal-title":"Chin J Acad Radiol"},{"key":"11556_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2023.110786","volume":"162","author":"K Borys","year":"2023","unstructured":"Borys K, Schmitt YA, Nauta M et al (2023) Explainable AI in medical imaging: an overview for clinical practitioners \u2013 beyond saliency-based XAI approaches. Eur J Radiol 162:110786. https:\/\/doi.org\/10.1016\/j.ejrad.2023.110786","journal-title":"Eur J Radiol"},{"key":"11556_CR12","doi-asserted-by":"publisher","unstructured":"Brauwers G, Frasincar F (2022) A general survey on attention mechanisms in deep learning. arXiv.Org. https:\/\/doi.org\/10.1109\/TKDE.2021.3126456.","DOI":"10.1109\/TKDE.2021.3126456"},{"key":"11556_CR13","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.csbj.2024.12.027","volume":"27","author":"A Budhkar","year":"2025","unstructured":"Budhkar A, Song Q, Su J, Zhang X (2025) Demystifying the black box: a survey on explainable artificial intelligence (XAI) in bioinformatics. Comput Struct Biotechnol J 27:346\u2013359. https:\/\/doi.org\/10.1016\/j.csbj.2024.12.027","journal-title":"Comput Struct Biotechnol J"},{"key":"11556_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797","volume":"66","author":"A Bustos","year":"2020","unstructured":"Bustos A, Pertusa A, Salinas J-M, de la Iglesia-Vay\u00e1 M (2020) PadChest: a large chest x-ray image dataset with multi-label annotated reports. Med Image Anal 66:101797. https:\/\/doi.org\/10.1016\/j.media.2020.101797","journal-title":"Med Image Anal"},{"key":"11556_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102814","volume":"149","author":"CS Pereira","year":"2024","unstructured":"Pereira CS, Mendon\u00e7a AM, Campilho A, Sousa P, Lopes CT (2024) Automated image label extraction from radiology reports \u2014 a review. Artif Intell Med 149:102814. https:\/\/doi.org\/10.1016\/j.artmed.2024.102814","journal-title":"Artif Intell Med"},{"key":"11556_CR16","doi-asserted-by":"publisher","unstructured":"Cheddi F, Habbani A, Nait-Charif H (2024) A multi-modal feature fusion-based approach for chest X-ray report generation. 2024 11th international conference on wireless networks and mobile communications (WINCOM). https:\/\/doi.org\/10.1109\/WINCOM62286.2024.10657835.","DOI":"10.1109\/WINCOM62286.2024.10657835"},{"key":"11556_CR17","volume-title":"Proceedings of the 2020 Conference on empirical methods in natural language processing (EMNLP)","author":"Z Chen","year":"2020","unstructured":"Chen Z, Song Y, Chang T-H, 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). Association for Computational Linguistics, Stroudsburg"},{"key":"11556_CR18","unstructured":"Chou B (2018) 2024. Brucechou1983\/CheXNet-Keras. Python. released August 23. https:\/\/github.com\/brucechou1983\/CheXNet-Keras."},{"key":"11556_CR19","unstructured":"CIFAR-10 and CIFAR-100 Datasets. n.d. Accessed 7 September 2024. https:\/\/www.cs.toronto.edu\/~kriz\/cifar.html."},{"key":"11556_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-3195-9_4","volume-title":"Machine learning for brain disorders","author":"S Das","year":"2023","unstructured":"Das S, Tariq A, Santos T, Kantareddy SS, Banerjee I (2023) Recurrent neural networks (RNNs): architectures, training tricks, and introduction to influential research. In: Colliot O (ed) Machine learning for brain disorders. Springer US, New York. https:\/\/doi.org\/10.1007\/978-1-0716-3195-9_4"},{"key":"11556_CR21","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080","author":"D Demner-Fushman","year":"2015","unstructured":"Demner-Fushman D, Kohli M, Rosenman M et al (2015) Preparing a collection of radiology examinations for distribution and retrieval. J Am Med Inform Assoc. https:\/\/doi.org\/10.1093\/jamia\/ocv080","journal-title":"J Am Med Inform Assoc"},{"issue":"1174","key":"11556_CR22","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1093\/bjr\/tqaf173","volume":"98","author":"N Dietrich","year":"2025","unstructured":"Dietrich N (2025) Agentic AI in radiology: emerging potential and unresolved challenges. Br J Radiol 98(1174):1582\u20131584. https:\/\/doi.org\/10.1093\/bjr\/tqaf173","journal-title":"Br J Radiol"},{"key":"11556_CR23","doi-asserted-by":"publisher","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A et al. (2020) An image is worth 16x16 words: transformers for image recognition at scale. https:\/\/doi.org\/10.48550\/arXiv.2010.11929.","DOI":"10.48550\/arXiv.2010.11929"},{"key":"11556_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-025-11445-z","author":"A Fink","year":"2025","unstructured":"Fink A, Nattenm\u00fcller J, Rau S et al (2025) Retrieval-augmented generation improves precision and trust of a GPT-4 model for Emergency Radiology diagnosis and classification: a proof-of-concept study. Eur Radiol. https:\/\/doi.org\/10.1007\/s00330-025-11445-z","journal-title":"Eur Radiol"},{"key":"11556_CR25","unstructured":"Gale W, Oakden-Rayner L, Carneiro G, Bradley AP, Palmer LJ (2017) Detecting hip fractures with radiologist-level performance using deep neural networks. arXiv.Org. https:\/\/arxiv.org\/abs\/1711.06504v1."},{"key":"11556_CR26","doi-asserted-by":"publisher","unstructured":"Gale W, Oakden-Rayner L, Carneiro G, Palmer LJ, Bradley AP (2019) Producing radiologist-quality reports for interpretable deep learning. 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019), 1275\u201379. https:\/\/doi.org\/10.1109\/ISBI.2019.8759236.","DOI":"10.1109\/ISBI.2019.8759236"},{"key":"11556_CR27","doi-asserted-by":"publisher","unstructured":"Gu T, Yang K, An X, Feng Z, Liu D, Cai W (2024) ORID: Organ-regional information driven framework for radiology report generation. arXiv:2411.13025. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2411.13025.","DOI":"10.48550\/arXiv.2411.13025"},{"key":"11556_CR28","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv:1512.03385. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.1512.03385.","DOI":"10.48550\/arXiv.1512.03385"},{"key":"11556_CR29","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (eds) Computer vision \u2013 ECCV 2016. Springer International Publishing, Cham https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"11556_CR30","doi-asserted-by":"publisher","unstructured":"Hessel J, Holtzman A, Forbes M, Le Bras R, Choi Y (2022) CLIPScore: a reference-free evaluation metric for image captioning. arXiv:2104.08718. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2104.08718.","DOI":"10.48550\/arXiv.2104.08718"},{"key":"11556_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104496","volume":"146","author":"X Hou","year":"2023","unstructured":"Hou X, Liu Z, Li X, Li X, Sang S, Zhang Y (2023) MKCL: medical knowledge with contrastive learning model for radiology report generation. J Biomed Inform 146:104496. https:\/\/doi.org\/10.1016\/j.jbi.2023.104496","journal-title":"J Biomed Inform"},{"key":"11556_CR32","doi-asserted-by":"publisher","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. 2017 IEEE conference on computer vision and pattern recognition (CVPR), 2261\u201369. https:\/\/doi.org\/10.1109\/CVPR.2017.243.","DOI":"10.1109\/CVPR.2017.243"},{"key":"11556_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109100","volume":"182","author":"Q Huang","year":"2024","unstructured":"Huang Q, Li G (2024) Knowledge graph based reasoning in medical image analysis: a scoping review. Comput Biol Med 182:109100. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.109100","journal-title":"Comput Biol Med"},{"key":"11556_CR34","doi-asserted-by":"publisher","unstructured":"Irvin J, Rajpurkar P, Ko M, et al. (2019) CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Proceedings of the thirty-third AAAI conference on artificial intelligence and thirty-first innovative applications of artificial intelligence conference and ninth AAAI symposium on educational advances in artificial intelligence (Honolulu, Hawaii, USA), AAAI\u201919\/IAAI\u201919\/EAAI\u201919, 590\u201397. https:\/\/doi.org\/10.1609\/aaai.v33i01.3301590.","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"11556_CR35","doi-asserted-by":"publisher","unstructured":"Jing B, Xie P, Xing E (2018a) On the automatic generation of medical imaging reports. In: Iryna Gurevych and Yusuke Miyao (eds) Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Stroudsburg https:\/\/doi.org\/10.18653\/v1\/P18-1240.","DOI":"10.18653\/v1\/P18-1240"},{"key":"11556_CR36","doi-asserted-by":"publisher","unstructured":"Jing B, Xie P, Xing E (2018b) On the automatic generation of medical imaging reports. In: Iryna Gurevych and Yusuke Miyao (eds) proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Stroudsburg https:\/\/doi.org\/10.18653\/v1\/P18-1240.","DOI":"10.18653\/v1\/P18-1240"},{"key":"11556_CR37","doi-asserted-by":"publisher","unstructured":"Jing B, Xie P, Xing E (2018c) On the automatic generation of medical imaging reports. In: Iryna Gurevych and Yusuke Miyao. Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Stroudsburg. https:\/\/doi.org\/10.18653\/v1\/P18-1240.","DOI":"10.18653\/v1\/P18-1240"},{"issue":"1","key":"11556_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AE Johnson","year":"2023","unstructured":"Johnson AE, Bulgarelli L, Shen L et al (2023) MIMIC-IV, a freely accessible electronic health record dataset. Sci Data 10(1):1. https:\/\/doi.org\/10.1038\/s41597-022-01899-x","journal-title":"Sci Data"},{"key":"11556_CR39","unstructured":"Johnson AE, Pollard TJ, Greenbaum NR et al. (2019) MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv.Org. https:\/\/arxiv.org\/abs\/1901.07042v5."},{"issue":"10","key":"11556_CR40","doi-asserted-by":"publisher","first-page":"13409","DOI":"10.1007\/s11042-021-11272-6","volume":"81","author":"N Kaur","year":"2022","unstructured":"Kaur N, Mittal A, Singh G (2022) Methods for automatic generation of radiological reports of chest X-Rays: a comprehensive survey. Multim Tools Appl 81(10):13409\u201313439. https:\/\/doi.org\/10.1007\/s11042-021-11272-6","journal-title":"Multim Tools Appl"},{"key":"11556_CR41","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.250651","author":"B Khosravi","year":"2026","unstructured":"Khosravi B, Rouzrokh P, Akinci D\u2019Antonoli T et al (2026) Agentic AI in radiology: evolution from large language models to future clinical integration. Radiol Artif Intell. https:\/\/doi.org\/10.1148\/ryai.250651","journal-title":"Radiol Artif Intell"},{"key":"11556_CR42","unstructured":"Li Y, Liang X, Hu Z, Xing EP (2018) Hybrid retrieval-generation reinforced agent for medical image report generation\u2019. arXiv.Org. https:\/\/arxiv.org\/abs\/1805.08298v2."},{"key":"11556_CR43","doi-asserted-by":"publisher","unstructured":"Li CY, Liang X, Hu Z, Xing EP (2019) Knowledge-driven encode, retrieve, paraphrase for medical image report generation. Proceedings of the thirty-third AAAI conference on artificial intelligence and thirty-first innovative applications of artificial intelligence conference and ninth AAAI symposium on educational advances in artificial intelligence (Honolulu, Hawaii, USA), AAAI\u201919\/IAAI\u201919\/EAAI\u201919, January 27, 6666\u201373. https:\/\/doi.org\/10.1609\/aaai.v33i01.33016666.","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"11556_CR44","doi-asserted-by":"publisher","unstructured":"Li C, Wong C, Zhang S et al. (2023a) LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. arXiv:2306.00890. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2306.00890.","DOI":"10.48550\/arXiv.2306.00890"},{"key":"11556_CR45","doi-asserted-by":"publisher","unstructured":"Li M, Lin B, Chen Z, Lin H, Liang X, Chang X (2023b) Dynamic graph enhanced contrastive learning for chest x-ray report generation. 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 3334\u201343. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00325.","DOI":"10.1109\/CVPR52729.2023.00325"},{"issue":"1","key":"11556_CR46","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s11280-022-01013-6","volume":"26","author":"M Li","year":"2023","unstructured":"Li M, Liu R, Wang F, Chang X, Liang X (2023c) Auxiliary signal-guided knowledge encoder-decoder for medical report generation. World Wide Web 26(1):253\u2013270. https:\/\/doi.org\/10.1007\/s11280-022-01013-6","journal-title":"World Wide Web"},{"key":"11556_CR47","doi-asserted-by":"publisher","unstructured":"Li Y, Wang Z, Liu Y, Wang L, Liu L, Zhou L (2024) KARGEN: Knowledge-enhanced automated radiology report generation using large language models. In: Marius George Linguraru, Qi Dou, Aasa Feragen, et al. Medical image computing and computer assisted intervention \u2013 MICCAI 2024. Springer Nature Switzerland, Cham https:\/\/doi.org\/10.1007\/978-3-031-72086-4_36.","DOI":"10.1007\/978-3-031-72086-4_36"},{"key":"11556_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2023.101273","volume":"39","author":"Y Liao","year":"2023","unstructured":"Liao Y, Liu H, Spasi\u0107 I (2023) Deep learning approaches to automatic radiology report generation: a systematic review. Informatics Med Unlocked 39:101273. https:\/\/doi.org\/10.1016\/j.imu.2023.101273","journal-title":"Informatics Med Unlocked"},{"key":"11556_CR49","unstructured":"Lin, C-Y (2004) ROUGE: a package for automatic evaluation of summaries. Text Summarization branches out (Barcelona, Spain), July, 74\u201381. https:\/\/aclanthology.org\/W04-1013."},{"key":"11556_CR50","unstructured":"Lin TY, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2016) Feature pyramid networks for object detection. arXiv.Org. https:\/\/arxiv.org\/abs\/1612.03144v2."},{"key":"11556_CR51","doi-asserted-by":"publisher","unstructured":"Liu C, Tian Y, Song Y (2024) A systematic review of deep learning-based research on radiology report generation. arXiv:2311.14199. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2311.14199.","DOI":"10.48550\/arXiv.2311.14199"},{"key":"11556_CR52","first-page":"16266","volume":"34","author":"F Liu","year":"2021","unstructured":"Liu F, You C, Wu X, Ge S, Sun X (2021) Auto-encoding knowledge graph for unsupervised medical report generation. Adv Neural Inform Process Syst 34:16266\u201316279","journal-title":"Adv Neural Inform Process Syst"},{"key":"11556_CR53","doi-asserted-by":"publisher","unstructured":"Liu G, Hsu TM, McDermott M et al. (2019) Clinically accurate chest X-ray report generation. https:\/\/doi.org\/10.48550\/arXiv.1904.02633.","DOI":"10.48550\/arXiv.1904.02633"},{"key":"11556_CR54","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102486","volume":"120","author":"X Liu","year":"2025","unstructured":"Liu X, Xin J, Shen Q, Huang Z, Wang Z (2025) Automatic medical report generation based on deep learning: a state of the art survey. Comput Med Imaging Graph 120:102486. https:\/\/doi.org\/10.1016\/j.compmedimag.2024.102486","journal-title":"Comput Med Imaging Graph"},{"issue":"January","key":"11556_CR55","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1016\/j.procs.2024.10.170","volume":"247","author":"Y Liu","year":"2024","unstructured":"Liu Y, Zhang G, Ma C, Zongyun G (2024b) Dual graph convolutional networks for chest X-ray report generation. Procedia Computer Science, the 11th International Conference on Applications and Techniques in Cyber Intelligence 247(January):1416\u20131425. https:\/\/doi.org\/10.1016\/j.procs.2024.10.170","journal-title":"Procedia Computer Science, the 11th International Conference on Applications and Techniques in Cyber Intelligence"},{"key":"11556_CR56","unstructured":"Lundberg SM, Lee SI (2017) A Unified Approach to interpreting model predictions. proceedings of the 31st international conference on neural information processing systems (Red Hook, NY, USA), NIPS\u201917, 4768\u201377."},{"key":"11556_CR57","unstructured":"Luping Liu Y, Wang Z, Li Y, Liang X, Liu L, Wang L, Zhou L (2024) MRScore: Evaluating medical report with LLM-based reward system. MICCAI 2024 - Open Access. https:\/\/papers.miccai.org\/miccai-2024\/537-Paper1151."},{"key":"11556_CR58","unstructured":"Messina P, Pino P, Parra D, et al. (2020) A survey on deep learning and explainability for automatic report generation from medical images. arXiv.Org. https:\/\/arxiv.org\/abs\/2010.10563v2."},{"issue":"June","key":"11556_CR59","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101878","volume":"106","author":"MMA Monshi","year":"2020","unstructured":"Monshi MMA, Poon J, Chung V (2020) Deep learning in generating radiology reports: a survey. Artif Intell Med 106(June):101878. https:\/\/doi.org\/10.1016\/j.artmed.2020.101878","journal-title":"Artif Intell Med"},{"issue":"2","key":"11556_CR60","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/s11604-023-01487-y","volume":"42","author":"T Nakaura","year":"2024","unstructured":"Nakaura T, Yoshida N, Kobayashi N et al (2024) Preliminary assessment of automated radiology report generation with generative pre-trained transformers: comparing results to radiologist-generated reports. Jpn J Radiol 42(2):190\u2013200. https:\/\/doi.org\/10.1007\/s11604-023-01487-y","journal-title":"Jpn J Radiol"},{"issue":"1","key":"11556_CR61","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01498-w","volume":"9","author":"HQ Nguyen","year":"2022","unstructured":"Nguyen HQ, Lam K, Le LT et al (2022) VinDr-CXR: an open dataset of chest X-Rays with radiologist\u2019s annotations. Sci Data 9(1):429. https:\/\/doi.org\/10.1038\/s41597-022-01498-w","journal-title":"Sci Data"},{"key":"11556_CR62","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","volume":"452","author":"Z Niu","year":"2021","unstructured":"Niu Z, Zhong G, Yu H (2021) A review on the attention mechanism of deep learning. Neurocomputing 452:48\u201362. https:\/\/doi.org\/10.1016\/j.neucom.2021.03.091","journal-title":"Neurocomputing"},{"key":"11556_CR63","doi-asserted-by":"publisher","unstructured":"Nooralahzadeh F, Gonzalez NP, Frauenfelder T, Fujimoto K, Krauthammer M (2021) Progressive transformer-based generation of radiology reports. In: Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih (eds) Findings of the association for computational linguistics: EMNLP 2021. Association for Computational Linguistics, Stroudsburghttps:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.241","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"11556_CR64","doi-asserted-by":"publisher","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) BLEU: a method for automatic evaluation of machine translation. Proceedings of the 40th annual meeting on association for computational linguistics (USA), ACL, 311\u201318. https:\/\/doi.org\/10.3115\/1073083.1073135.","DOI":"10.3115\/1073083.1073135"},{"issue":"7","key":"11556_CR65","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1007\/s10115-022-01684-7","volume":"64","author":"J Pavlopoulos","year":"2022","unstructured":"Pavlopoulos J, Kougia V, Androutsopoulos I, Papamichail D (2022) Diagnostic captioning: a survey. Knowl Inf Syst 64(7):1691\u20131722. https:\/\/doi.org\/10.1007\/s10115-022-01684-7","journal-title":"Knowl Inf Syst"},{"key":"11556_CR66","unstructured":"PEIR Digital Library. n.d. Accessed 10 August 2024. https:\/\/peir.path.uab.edu\/library\/."},{"key":"11556_CR67","doi-asserted-by":"publisher","unstructured":"Picha SG, Chanti DA, Caplier A (2024) Semantic textual similarity assessment in chest X-Ray reports using a domain-specific cosine-based metric. Proceedings of the 17th international joint conference on biomedical engineering systems and technologies, 487\u201394. https:\/\/doi.org\/10.5220\/0012429600003657.","DOI":"10.5220\/0012429600003657"},{"key":"11556_CR68","doi-asserted-by":"publisher","unstructured":"Rajpurkar P, Irvin J, Zhu K et al. (2017) CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv:1711.05225. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.1711.05225.","DOI":"10.48550\/arXiv.1711.05225"},{"key":"11556_CR69","doi-asserted-by":"publisher","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) \u201cWhy Should I Trust You?\u201d: explaining the predictions of any classifier\u2019. proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (New York, NY, USA), KDD 1135\u201344. https:\/\/doi.org\/10.1145\/2939672.2939778.","DOI":"10.1145\/2939672.2939778"},{"key":"11556_CR70","doi-asserted-by":"publisher","DOI":"10.3390\/ai7010008","author":"PM Rojas","year":"2025","unstructured":"Rojas PM, Rojas JJ, Dellafiori MFV et al (2025) The current landscape of automatic radiology report generation with deep learning: a scoping review. AI. https:\/\/doi.org\/10.3390\/ai7010008","journal-title":"AI"},{"key":"11556_CR71","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12101100","author":"S Salehi","year":"2025","unstructured":"Salehi S, Singh Y, Habibi P, Erickson BJ (2025) Beyond single systems: how multi-agent AI is reshaping ethics in radiology. Bioengineering. https:\/\/doi.org\/10.3390\/bioengineering12101100","journal-title":"Bioengineering"},{"key":"11556_CR72","doi-asserted-by":"publisher","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: visual explanations from deep networks via gradient-based localization. 2017 IEEE International Conference on Computer Vision (ICCV), 618\u201326. https:\/\/doi.org\/10.1109\/ICCV.2017.74.","DOI":"10.1109\/ICCV.2017.74"},{"key":"11556_CR73","doi-asserted-by":"publisher","unstructured":"Shin HC, Lu L, Kim L, Seff A, Yao J, Summers RM (2015) Interleaved text\/image deep mining on a large-scale radiology database for automated image interpretation. arXiv:1505.00670. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.1505.00670.","DOI":"10.48550\/arXiv.1505.00670"},{"key":"11556_CR74","doi-asserted-by":"publisher","unstructured":"Shin HC, Roberts K, Lu L, Demner-Fushman D, Yao J, Summers RM. (2016) Learning to read chest X-Rays: recurrent neural cascade model for automated image annotation. arXiv:1603.08486. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.1603.08486.","DOI":"10.48550\/arXiv.1603.08486"},{"key":"11556_CR75","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv.Org. https:\/\/arxiv.org\/abs\/1409.1556v6."},{"key":"11556_CR76","doi-asserted-by":"publisher","unstructured":"Sloan P, Clatworthy P, Simpson E, Mirmehdi M (2024) Automated radiology report generation: a review of recent advances. IEEE Reviews in Biomedical Engineering, 1\u201320. https:\/\/doi.org\/10.1109\/RBME.2024.3408456.","DOI":"10.1109\/RBME.2024.3408456"},{"key":"11556_CR77","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129003","volume":"296","author":"Z Su","year":"2026","unstructured":"Su Z, Song H, Lin Y et al (2026) MedKit: multi-level feature distillation with knowledge injection for radiology report generation. Expert Syst Appl 296:129003. https:\/\/doi.org\/10.1016\/j.eswa.2025.129003","journal-title":"Expert Syst Appl"},{"key":"11556_CR78","doi-asserted-by":"publisher","unstructured":"Sun L, Zhao JJ, Han W, Xiong C (2025) Fact-aware multimodal retrieval augmentation for accurate medical radiology report generation. arXiv:2407.15268. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2407.15268.","DOI":"10.48550\/arXiv.2407.15268"},{"key":"11556_CR79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59713-9_54","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2020","author":"T Syeda-Mahmood","year":"2020","unstructured":"Syeda-Mahmood T, Wong KCL, Gur Y et al (2020) Chest X-ray report generation through fine-grained label learning. In: Martel AL, Abolmaesumi P, Stoyanov D et al (eds) Medical image computing and computer assisted intervention \u2013 MICCAI 2020. Springer International Publishing, Cham. https:\/\/doi.org\/10.1007\/978-3-030-59713-9_54"},{"key":"11556_CR80","doi-asserted-by":"publisher","unstructured":"Tu T, Azizi S, Driess D et al. (2023) Towards generalist biomedical AI. arXiv:2307.14334. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2307.14334.","DOI":"10.48550\/arXiv.2307.14334"},{"key":"11556_CR81","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2014) CIDEr: consensus-based image description evaluation. arXiv.Org. https:\/\/arxiv.org\/abs\/1411.5726v2."},{"key":"11556_CR82","doi-asserted-by":"publisher","unstructured":"Wang H, Wang Z, Du M et al. (2020) Score-CAM: score-weighted visual explanations for convolutional neural Networks. 2020 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW). 111\u201319. https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00020.","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"11556_CR83","doi-asserted-by":"publisher","unstructured":"Wang J, Yang Z, Hu X, et al. (2022) GIT: a generative image-to-text transformer for vision and language. arXiv:2205.14100. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2205.14100.","DOI":"10.48550\/arXiv.2205.14100"},{"key":"11556_CR84","doi-asserted-by":"crossref","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017a) ChestX-Ray14: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases.","DOI":"10.1109\/CVPR.2017.369"},{"key":"11556_CR85","doi-asserted-by":"publisher","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017b) ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. arXiv.Org. https:\/\/doi.org\/10.1109\/CVPR.2017.369.","DOI":"10.1109\/CVPR.2017.369"},{"key":"11556_CR86","doi-asserted-by":"publisher","unstructured":"Wang X, Figueredo G, Li R, Zhang WE, Chen W, Chen X (2024) A survey of deep learning-based radiology report generation using multimodal data. Version 2. https:\/\/doi.org\/10.48550\/ARXIV.2405.12833.","DOI":"10.48550\/ARXIV.2405.12833"},{"issue":"April","key":"11556_CR87","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127374","volume":"578","author":"Y Wang","year":"2024","unstructured":"Wang Y, Lin Z, Xu Z et al (2024) Trust it or not: confidence-guided automatic radiology report generation. Neurocomputing 578(April):127374. https:\/\/doi.org\/10.1016\/j.neucom.2024.127374","journal-title":"Neurocomputing"},{"key":"11556_CR88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Z Wang","year":"2022","unstructured":"Wang Z, Wu Z, Agarwal D, Sun J (2022b) MedCLIP: Contrastive Learning from Unpaired Medical Images and Text. In: Goldberg Y, Kozareva Z, Zhang Y (eds) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Stroudsburg. https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.256"},{"issue":"3","key":"11556_CR89","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240313","volume":"7","author":"DA Weinert","year":"2025","unstructured":"Weinert DA, Rauschecker AM (2025) Enhancing large language models with retrieval-augmented generation: a radiology-specific approach. Radiol Artif Intell 7(3):e240313. https:\/\/doi.org\/10.1148\/ryai.240313","journal-title":"Radiol Artif Intell"},{"key":"11556_CR90","doi-asserted-by":"publisher","unstructured":"Xia P, Zhu K, Li H et al. (2025) MMed-RAG: versatile multimodal RAG system for medical vision language models. arXiv:2410.13085. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2410.13085.","DOI":"10.48550\/arXiv.2410.13085"},{"key":"11556_CR91","doi-asserted-by":"publisher","unstructured":"Xiao T, Shi L, Liu P, Wang Z, Bai C (2024) Radiology report generation via multi-objective preference optimization. arXiv:2412.08901. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.2412.08901.","DOI":"10.48550\/arXiv.2412.08901"},{"key":"11556_CR92","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947134","author":"H Xin","year":"2019","unstructured":"Xin H, Yan F, Xu W, Li M (2019) Multi-attention and incorporating background information model for chest X-Ray image report generation. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2019.2947134","journal-title":"IEEE Access"},{"key":"11556_CR93","doi-asserted-by":"publisher","unstructured":"Xu K, Ba J, Kiros R et al. (2016) Show, attend and tell: neural image caption generation with visual attention. arXiv:1502.03044. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.1502.03044.","DOI":"10.48550\/arXiv.1502.03044"},{"key":"11556_CR94","doi-asserted-by":"publisher","unstructured":"Xue Y, Tan Y, Tan L, Qin J, Xiang X (2022) Generating radiology report via auxiliary signal guidance and memory-driven network. SSRN scholarly paper No. 4149520. Social science research network. https:\/\/doi.org\/10.2139\/ssrn.4149520.","DOI":"10.2139\/ssrn.4149520"},{"key":"11556_CR95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_52","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2018","author":"Y Xue","year":"2018","unstructured":"Xue Y, Tao X, Rodney Long L et al (2018) Multimodal recurrent model with attention for automated radiology report generation. In: Frangi AF, Schnabel JA, Davatzikos C, Alberola-L\u00f3pez C, Fichtinger G (eds) Medical image computing and computer assisted intervention \u2013 MICCAI 2018. Springer International Publishing, Cham. https:\/\/doi.org\/10.1007\/978-3-030-00928-1_52"},{"key":"11556_CR96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60248-2_48","volume-title":"Algorithms and architectures for parallel processing","author":"S Yang","year":"2020","unstructured":"Yang S, Niu J, Jiyan W, Liu X (2020) Automatic medical image report generation with multi-view and multi-modal attention mechanism. In: Qiu M (ed) Algorithms and architectures for parallel processing. Springer International Publishing, Cham. https:\/\/doi.org\/10.1007\/978-3-030-60248-2_48"},{"issue":"March","key":"11556_CR97","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105742","volume":"89","author":"X Yi","year":"2024","unstructured":"Yi X, Fu Y, Hua R, Liu R, Zhang H (2024) Unsupervised disease tags for automatic radiology report generation. Biomed Signal Process Control 89(March):105742. https:\/\/doi.org\/10.1016\/j.bspc.2023.105742","journal-title":"Biomed Signal Process Control"},{"issue":"2","key":"11556_CR98","doi-asserted-by":"publisher","DOI":"10.3390\/info16020136","volume":"16","author":"Z Yi","year":"2025","unstructured":"Yi Z, Xiao T, Albert MV (2025) A survey on multimodal large language models in radiology for report generation and visual question answering. Information Basel 16(2):2. https:\/\/doi.org\/10.3390\/info16020136","journal-title":"Information Basel"},{"issue":"16","key":"11556_CR99","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13163306","volume":"13","author":"H Yin","year":"2024","unstructured":"Yin H, Wu W, Hao Y (2024) DKA-RG: disease-knowledge-enhanced fine-grained image\u2013text alignment for automatic radiology report generation. Electronics 13(16):16. https:\/\/doi.org\/10.3390\/electronics13163306","journal-title":"Electronics"},{"issue":"9","key":"11556_CR100","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802","volume":"4","author":"F Yu","year":"2023","unstructured":"Yu F, Endo M, Krishnan R et al (2023) Evaluating progress in automatic chest X-Ray radiology report generation. Patterns N Y 4(9):100802. https:\/\/doi.org\/10.1016\/j.patter.2023.100802","journal-title":"Patterns N Y"},{"key":"11556_CR101","doi-asserted-by":"publisher","unstructured":"Zhang T, Kishore V, Wu F, Weinberger KQ, Artzi Y (2020a) BERTScore: evaluating text generation with BERT. arXiv:1904.09675. Preprint, arXiv. https:\/\/doi.org\/10.48550\/arXiv.1904.09675.","DOI":"10.48550\/arXiv.1904.09675"},{"key":"11556_CR102","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.698","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Wang X, Xu Z, Yu Q, Yuille A, Xu D (2020b) When radiology report generation meets knowledge graph. Proc AAAI Conf Artif Intell. https:\/\/doi.org\/10.1609\/aaai.v34i07.698","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"September","key":"11556_CR103","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104718","volume":"157","author":"Z Zhang","year":"2024","unstructured":"Zhang Z, Jiang A (2024) Interactive dual-stream contrastive learning for radiology report generation. J Biomed Inform 157(September):104718. https:\/\/doi.org\/10.1016\/j.jbi.2024.104718","journal-title":"J Biomed Inform"},{"key":"11556_CR104","doi-asserted-by":"publisher","unstructured":"Zhang Z, Xie Y, Xing F, McGough M, Yang L (2017) MDNet: A semantically and visually interpretable medical image diagnosis network. arXiv:1707.02485. https:\/\/doi.org\/10.48550\/arXiv.1707.02485.","DOI":"10.48550\/arXiv.1707.02485"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-026-11556-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-026-11556-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-026-11556-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:17:20Z","timestamp":1781482640000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-026-11556-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":104,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["11556"],"URL":"https:\/\/doi.org\/10.1007\/s10462-026-11556-z","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"9 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":3,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"168"}}