{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:19:40Z","timestamp":1780571980421,"version":"3.54.1"},"reference-count":162,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1311300"],"award-info":[{"award-number":["2019YFB1311300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"DOI":"10.1007\/s10462-025-11337-0","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:17:54Z","timestamp":1755764274000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic radiology report generation with deep learning: a comprehensive review of methods and advances"],"prefix":"10.1007","volume":"58","author":[{"given":"Yilin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"11337_CR1","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.48550\/arXiv.2204.14198","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac JB, Donahue J, Luc P, Miech A, Barr I, Hasson Y, Lenc K, Mensch A, Millican K, Reynolds M et al (2022) Flamingo: a visual language model for few-shot learning. Adv Neural Inf Process Syst 35:23716\u201323736. https:\/\/doi.org\/10.48550\/arXiv.2204.14198","journal-title":"Adv Neural Inf Process Syst"},{"key":"11337_CR2","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. Inf Med Unlock 24:100557. https:\/\/doi.org\/10.1016\/j.imu.2021.100557","journal-title":"Inf Med Unlock"},{"key":"11337_CR3","unstructured":"Banerjee S, Lavie A (2005) Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization, pp 65\u201372"},{"key":"11337_CR4","doi-asserted-by":"crossref","unstructured":"Bannur S, Hyland S, Liu Q, Perez-Garcia F, Ilse M, Castro DC, Boecking B, Sharma H, Bouzid K, Thieme A et\u00a0al (2023) Learning to exploit temporal structure for biomedical vision-language processing. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15016\u201315027","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"11337_CR5","doi-asserted-by":"crossref","unstructured":"Beltagy I, Lo K, Cohan A (2019) SciBERT: A pretrained language model for scientific text. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), Hong Kong, China, pp 3615\u20133620. Association for Computational Linguistics","DOI":"10.18653\/v1\/D19-1371"},{"key":"11337_CR6","doi-asserted-by":"crossref","unstructured":"Boecking B, Usuyama N, Bannur S, Castro DC, Schwaighofer A, Hyland S, Wetscherek M, Naumann T, Nori A, Alvarez-Valle J et\u00a0al (2022) Making the most of text semantics to improve biomedical vision\u2013language processing. In European conference on computer vision. Springer, pp 1\u201321","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"11337_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797","volume":"66","author":"A Bustos","year":"2020","unstructured":"Bustos A, Pertusa A, Salinas JM, De La Iglesia-Vaya 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":"11337_CR9","doi-asserted-by":"crossref","unstructured":"Chen Z, Tang Y (2022) Improving radiology report generation via object dropout strategy and mlp-based captioner. In 2022 IEEE 5th Advanced Information Management. Commun Electron Automat Control Conf (IMCEC) 5:316\u2013322","DOI":"10.1109\/IMCEC55388.2022.10019809"},{"key":"11337_CR8","doi-asserted-by":"crossref","unstructured":"Chen YC, Li L, Yu L, El\u00a0Kholy A, Ahmed F, Gan Z, Cheng Y, Liu J (2020a) Uniter: Universal image-text representation learning. In European conference on computer vision. Springer, pp 104\u2013120","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"11337_CR12","doi-asserted-by":"crossref","unstructured":"Chen Z, Song Y, Chang TH, Wan X (2020b) Generating radiology reports via memory-driven transformer. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), Online, pp 1439\u20131449. Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"11337_CR14","doi-asserted-by":"crossref","unstructured":"Chen Z, Y\u00a0Shen Song Y, Wan X (2021) Cross-modal memory networks for radiology report generation. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (Volume 1: Long Papers), Online, pp 5904\u20135914. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"11337_CR11","doi-asserted-by":"crossref","unstructured":"Chen Z, Li G, Wan X (2022) Align, reason and learn: enhancing medical vision-and-language pre-training with knowledge. In Proceedings of the 30th ACM international conference on multimedia, pp 5152\u20135161","DOI":"10.1145\/3503161.3547948"},{"key":"11337_CR10","doi-asserted-by":"publisher","unstructured":"Chen W, Liu Y, Wang C, Li G, Zhu J, Lin L (2023a) Visual-linguistic causal intervention for radiology report generation. arXiv preprint arXiv:2303.09117. https:\/\/doi.org\/10.48550\/arXiv.2303.09117","DOI":"10.48550\/arXiv.2303.09117"},{"key":"11337_CR13","doi-asserted-by":"publisher","unstructured":"Chen Q, Xie Y, Wu B, To MS, Ang J, Wu Q (2023b) S4m: Generating radiology reports by a single model for multiple body parts. arXiv preprint arXiv:2305.16685. https:\/\/doi.org\/10.48550\/arXiv.2305.16685","DOI":"10.48550\/arXiv.2305.16685"},{"key":"11337_CR15","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, pp 10578\u201310587","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"11337_CR16","doi-asserted-by":"crossref","unstructured":"Delbrouck JB, Chambon P, Bluethgen C, Tsai E, Almusa O, Langlotz C (2022) Improving the factual correctness of radiology report generation with semantic rewards. In Findings of the association for computational linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, pp 4348\u20134360. Association for Computational Linguistics","DOI":"10.18653\/v1\/2022.findings-emnlp.319"},{"issue":"2","key":"11337_CR17","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman D, Kohli MD, Rosenman MB, Shooshan SE, Rodriguez L, Antani S, Thoma GR, McDonald CJ (2016) Preparing a collection of radiology examinations for distribution and retrieval. J Am Med Inform Assoc 23(2):304\u2013310. https:\/\/doi.org\/10.1093\/jamia\/ocv080","journal-title":"J Am Med Inform Assoc"},{"key":"11337_CR18","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. https:\/\/doi.org\/10.48550\/arXiv.1810.04805","DOI":"10.48550\/arXiv.1810.04805"},{"key":"11337_CR19","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne\u00a0Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"11337_CR20","doi-asserted-by":"publisher","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. ICLR. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"11337_CR21","unstructured":"Forgues G, Pineau J, Larchev\u00eaque JM, Tremblay R (2014) Bootstrapping dialog systems with word embeddings. In Nips modern machine learning and natural language processing workshop 2:168"},{"key":"11337_CR23","doi-asserted-by":"crossref","unstructured":"Han Z, Wei B, Leung S, Chung J, Li S (2018) Towards automatic report generation in spine radiology using weakly supervised framework. In Medical image computing and computer assisted intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part IV 11. Springer, pp 185\u2013193","DOI":"10.1007\/978-3-030-00937-3_22"},{"key":"11337_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101872","volume":"67","author":"Z Han","year":"2021","unstructured":"Han Z, Wei B, Xi X, Chen B, Yin Y, Li S (2021) Unifying neural learning and symbolic reasoning for spinal medical report generation. Med Image Anal 67:101872. https:\/\/doi.org\/10.1016\/j.media.2020.101872","journal-title":"Med Image Anal"},{"key":"11337_CR24","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, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"11337_CR25","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"key":"11337_CR26","doi-asserted-by":"crossref","unstructured":"Hou B, Kaissis G, Summers RM, Kainz B (2021) Ratchet: Medical transformer for chest x-ray diagnosis and reporting. In Medical image computing and computer assisted intervention\u2013MICCAI 2021: 24th international conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part VII 24. Springer, pp 293\u2013303","DOI":"10.1007\/978-3-030-87234-2_28"},{"key":"11337_CR27","doi-asserted-by":"crossref","unstructured":"Hou W, Xu K, Cheng Y, Li W, Liu J (2023) ORGAN: Observation-guided radiology report generation via tree reasoning. In Proceedings of the 61st annual meeting of the association for computational linguistics (Volume 1: Long Papers), Toronto, Canada, pp 8108\u20138122. Association for Computational Linguistics","DOI":"10.18653\/v1\/2023.acl-long.451"},{"key":"11337_CR29","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"11337_CR28","doi-asserted-by":"crossref","unstructured":"Huang SC, Shen L, Lungren MP, Yeung S (2021) Gloria: a multimodal global-local representation learning framework for label-efficient medical image recognition. In Proceedings of the IEEE\/cvf international conference on computer vision, pp 3942\u20133951","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"11337_CR30","doi-asserted-by":"crossref","unstructured":"Huang Z, Zhang X, Zhang S (2023) Kiut: Knowledge-injected u-transformer for radiology report generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19809\u201319818","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"11337_CR31","doi-asserted-by":"crossref","unstructured":"Hu J, Chen Z, Liu Y, Wan X, Chang TH (2023) Improving radiology summarization with radiograph and anatomy prompts. In Findings of the association for computational linguistics: ACL 2023, Toronto, Canada, pp 12066\u201312080. Association for Computational Linguistics","DOI":"10.18653\/v1\/2023.findings-acl.764"},{"key":"11337_CR32","first-page":"590","volume":"33","author":"J Irvin","year":"2019","unstructured":"Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, Marklund H, Haghgoo B, Ball R, Shpanskaya K et al (2019) Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Proc AAAI Conf Artif Intell 33:590\u2013597","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"11337_CR34","doi-asserted-by":"publisher","unstructured":"Jain S, grawal A, Saporta A, Truong SQ, D uong DN, Bui T, Chambon P, Zhang Y, Lungren MP, Ng AY et\u00a0al (2021a) Radgraph: Extracting clinical entities and relations from radiology reports https:\/\/doi.org\/10.48550\/arXiv.2106.14463. arXiv preprint arXiv:2106.14463","DOI":"10.48550\/arXiv.2106.14463"},{"key":"11337_CR33","doi-asserted-by":"publisher","unstructured":"Jain S, Agrawal A, Saporta A, Truong SQ, Duong DN, Bui T, Chambon P, Zhang Y, Lungren MP, Ng AY et\u00a0al (2021b) Radgraph: Extracting clinical entities and relations from radiology reports. arXiv preprint arXiv:2106.14463. https:\/\/doi.org\/10.48550\/arXiv.2106.14463","DOI":"10.48550\/arXiv.2106.14463"},{"key":"11337_CR35","unstructured":"Jeong J, Tian K, Li A, Hartung S, Adithan S, Behzadi F, Calle J, Osayande D, Pohlen M, Rajpurkar P (2023) Multimodal image-text matching improves retrieval-based chest x-ray report generation. In Medical imaging with deep learning"},{"key":"11337_CR36","doi-asserted-by":"crossref","unstructured":"Jia X, Xiong Y, Zhang J, Zhang Y, Suzanne B, Zhu Y, Tang C (2021a) Radiology report generation for rare diseases via few-shot transformer. In 2021 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE, pp 1347\u20131352","DOI":"10.1109\/BIBM52615.2021.9669825"},{"key":"11337_CR38","unstructured":"Jia C, Yang Y, Xia Y, Chen YT, Parekh Z, Pham H, Le Q, Sung YH, Li Z, Duerig T (2021b) 18\u201324. Scaling up visual and vision-language representation learning with noisy text supervision. In M\u00a0Meila and T\u00a0Zhang (Eds.), Proceedings of the 38th International Conference on Machine Learning, Volume 139 of Proceedings of Machine Learning Research. PMLR, pp 4904\u20134916"},{"key":"11337_CR37","doi-asserted-by":"crossref","unstructured":"Jia X, Xiong Y, Zhang J, Zhang Y, Zhu Y, Yu PS (2022) Few-shot radiology report generation via knowledge transfer and multi-modal alignment. In 2022 IEEE international conference on bioinformatics and biomedicine (BIBM), pp 1574\u20131579","DOI":"10.1109\/BIBM55620.2022.9995533"},{"key":"11337_CR39","doi-asserted-by":"crossref","unstructured":"Jin H, Che H, Lin Y, Chen H (2024) Promptmrg: Diagnosis-driven prompts for medical report generation. In Proceedings of the AAAI conference on artificial intelligence 38:2607\u20132615","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"11337_CR41","doi-asserted-by":"publisher","unstructured":"Jing B, Xie P, Xing E (2018) On the automatic generation of medical imaging reports, pp 2577\u20132586. https:\/\/doi.org\/10.18653\/v1\/P18-1240","DOI":"10.18653\/v1\/P18-1240"},{"key":"11337_CR40","doi-asserted-by":"crossref","unstructured":"Jing B, Wang Z, Xing E (2019) July. Show, describe and conclude: on exploiting the structure information of chest X-ray reports. In Proceedings of the 57th annual meeting of the association for computational linguistics, Florence, Italy, pp 6570\u20136580. Association for Computational Linguistics","DOI":"10.18653\/v1\/P19-1657"},{"key":"11337_CR42","doi-asserted-by":"publisher","unstructured":"Johnson AE, Pollard TJ, Greenbaum NR, Lungren MP, Deng Cy, Peng Y, Lu Z, Mark RG, Berkowitz SJ, Horng S (2019a) Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs. https:\/\/doi.org\/10.1038\/s41597-019-0322-0 . arXiv preprint arXiv:1901.07042","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"1","key":"11337_CR43","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"Johnson AE, Pollard TJ, Berkowitz SJ, Greenbaum NR, Lungren MP, Deng C, Mark RG, Horng S (2019b) Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data 6(1):317. https:\/\/doi.org\/10.1038\/s41597-019-0322-0","journal-title":"Sci Data"},{"key":"11337_CR44","doi-asserted-by":"crossref","unstructured":"Kale K, Bhattacharyya P, Jadhav K (2023) Replace and report: NLP assisted radiology report generation. In Findings of the association for computational linguistics: ACL 2023, Toronto, Canada, pp 10731\u201310742. Association for Computational Linguistics","DOI":"10.18653\/v1\/2023.findings-acl.683"},{"key":"11337_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105498","volume":"145","author":"N Kaur","year":"2022","unstructured":"Kaur N, Mittal A (2022a) Cadxreport: Chest x-ray report generation using co-attention mechanism and reinforcement learning. Comput Biol Med 145:105498. https:\/\/doi.org\/10.1016\/j.compbiomed.2022.105498","journal-title":"Comput Biol Med"},{"key":"11337_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2022.104220","volume":"135","author":"N Kaur","year":"2022","unstructured":"Kaur N, Mittal A (2022b) Radiobert: A deep learning-based system for medical report generation from chest x-ray images using contextual embeddings. J Biomed Inform 135:104220. https:\/\/doi.org\/10.1016\/j.jbi.2022.104220","journal-title":"J Biomed Inform"},{"key":"11337_CR47","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s11042-021-11272-6","volume":"10","author":"N Kaur","year":"2022","unstructured":"Kaur N, Mittal A, Singh G (2022) Methods for automatic generation of radiological reports of chest radiographs: a comprehensive survey. Multimed Tools Appl 10:81. https:\/\/doi.org\/10.1007\/s11042-021-11272-6","journal-title":"Multimed Tools Appl"},{"key":"11337_CR48","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks"},{"key":"11337_CR49","doi-asserted-by":"publisher","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo WY et al (2023) Segment anything https:\/\/doi.org\/10.48550\/arXiv.2304.02643. arXiv preprint arXiv:2304.02643","DOI":"10.48550\/arXiv.2304.02643"},{"key":"11337_CR50","unstructured":"Kiros R, Zhu Y, Salakhutdinov RR, Zemel R, Urtasun R, Torralba A, Fidler S (2015) Skip-thought vectors. Adv Neural Inf Process Syst 28"},{"key":"11337_CR51","doi-asserted-by":"crossref","unstructured":"Kong M, Huang Z, Kuang K, Zhu Q, Wu F (2022) Transq: Transformer-based semantic query for medical report generation. In International conference on medical image computing and computer-assisted intervention. Springer, pp 610\u2013620","DOI":"10.1007\/978-3-031-16452-1_58"},{"key":"11337_CR52","doi-asserted-by":"crossref","unstructured":"Krause J, Johnson J, Krishna R, Fei-Fei L (2017) A hierarchical approach for generating descriptive image paragraphs. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 317\u2013325","DOI":"10.1109\/CVPR.2017.356"},{"key":"11337_CR53","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li LJ, Shamma DA et al (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis 123:32\u201373. https:\/\/doi.org\/10.1007\/s11263-016-0981-7","journal-title":"Int J Comput Vis"},{"issue":"1\u20132","key":"11337_CR54","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn HW (1955) The Hungarian method for the assignment problem. Naval Res Logist Quart 2(1\u20132):83\u201397. https:\/\/doi.org\/10.1002\/nav.3800020109","journal-title":"Naval Res Logist Quart"},{"key":"11337_CR55","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th annual meeting of the association for computational linguistics, Online, pp 7871\u20137880. Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"11337_CR57","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. Inf Med Unlock 39:101273. https:\/\/doi.org\/10.1016\/j.imu.2023.101273","journal-title":"Inf Med Unlock"},{"key":"11337_CR59","doi-asserted-by":"crossref","unstructured":"Li J, Hong Y (2019) Label generation system based on generative adversarial network for medical image. In Proceedings of the 2nd international conference on artificial intelligence and pattern recognition, pp 78\u201382","DOI":"10.1145\/3357254.3357256"},{"issue":"5555\/3326943","key":"11337_CR60","first-page":"3327084","volume":"10","author":"Y Li","year":"2018","unstructured":"Li Y, Liang X, Hu Z, Xing EP (2018) Hybrid retrieval-generation reinforced agent for medical image report generation. Adv Neural Inf Process Syst 10(5555\/3326943):3327084","journal-title":"Adv Neural Inf Process Syst"},{"key":"11337_CR56","doi-asserted-by":"crossref","unstructured":"Li CY, Liang X, Hu Z, Xing EP (2019) Knowledge-driven encode, retrieve, paraphrase for medical image report generation. In Proceedings of the AAAI conference on artificial intelligence 33:6666\u20136673","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"11337_CR73","doi-asserted-by":"crossref","unstructured":"Li R, Wang Z, Zhang L (2021a) Image caption and medical report generation based on deep learning: a review and algorithm analysis. In 2021 International conference on computer information science and artificial intelligence (CISAI), pp 373\u2013379","DOI":"10.1109\/CISAI54367.2021.00078"},{"key":"11337_CR58","unstructured":"Li M, Cai W, Liu R, Weng Y, Zhao X, Wang C, Chen X, Liu Z, Pan C, Li M et\u00a0al (2021b) Ffa-ir: Towards an explainable and reliable medical report generation benchmark. In Thirty-fifth conference on neural information processing systems datasets and benchmarks track (Round 2)"},{"key":"11337_CR64","doi-asserted-by":"publisher","first-page":"9694","DOI":"10.48550\/arXiv.2107.07651","volume":"34","author":"J Li","year":"2021","unstructured":"Li J, Selvaraju R, Gotmare A, Joty S, Xiong C, Hoi SCH (2021c) Align before fuse: vision and language representation learning with momentum distillation. Adv Neural Inf Process Syst 34:9694\u20139705. https:\/\/doi.org\/10.48550\/arXiv.2107.07651","journal-title":"Adv Neural Inf Process Syst"},{"key":"11337_CR61","doi-asserted-by":"crossref","unstructured":"Li M, Lin B, Chen Z, Lin H, Liang X, Chang X (2023a) Dynamic graph enhanced contrastive learning for chest x-ray report generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3334\u20133343","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"11337_CR62","doi-asserted-by":"publisher","unstructured":"Li J, Li D, Savarese S, Hoi S (2023b) Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models https:\/\/doi.org\/10.48550\/arXiv.2301.12597. arXiv preprint arXiv:2301.12597","DOI":"10.48550\/arXiv.2301.12597"},{"key":"11337_CR63","unstructured":"Lin CY (2004) Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pp 74\u201381"},{"key":"11337_CR65","doi-asserted-by":"crossref","unstructured":"Liu W Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"11337_CR72","doi-asserted-by":"crossref","unstructured":"Liu S, Zhu Z, Ye N, Guadarrama S, Murphy K (2017) Improved image captioning via policy gradient optimization of spider. In Proceedings of the IEEE international conference on computer vision, pp 873\u2013881","DOI":"10.1109\/ICCV.2017.100"},{"key":"11337_CR68","unstructured":"Liu G, Hsu TMH, McDermott M, Boag W, Weng WH, Szolovits P, Ghassemi M (2019) Clinically accurate chest x-ray report generation. In Doshi-Velez F, Fackler J, Jung K, Kale D, Ranganath R, Wallace B, and Wiens J (Eds.), Proceedings of the 4th machine learning for healthcare conference, volume 106 of proceedings of machine learning research. PMLR, pp 249\u2013269"},{"key":"11337_CR67","doi-asserted-by":"crossref","unstructured":"Liu F, Ge S, Wu X (2021a) Competence-based multimodal curriculum learning for medical report generation. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (Volume 1: Long Papers), Online, pp 3001\u20133012. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.acl-long.234"},{"key":"11337_CR69","doi-asserted-by":"crossref","unstructured":"Liu F, Wu X, Ge S, Fan W, Zou Y (2021b) Exploring and distilling posterior and prior knowledge for radiology report generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 13753\u201313762","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"11337_CR70","doi-asserted-by":"crossref","unstructured":"Liu F, Yin C, Wu X, Ge S, Zhang P, Sun X (2021c) Contrastive attention for automatic chest X-ray report generation. In Findings of the association for computational linguistics: ACL-IJCNLP 2021, Online, pp 269\u2013280. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"11337_CR71","doi-asserted-by":"publisher","first-page":"16266","DOI":"10.48550\/arXiv.2111.04318","volume":"34","author":"F Liu","year":"2021","unstructured":"Liu F, You C, Wu X, Ge S, Sun X et al (2021d) Auto-encoding knowledge graph for unsupervised medical report generation. Adv Neural Inf Process Syst 34:16266\u201316279. https:\/\/doi.org\/10.48550\/arXiv.2111.04318","journal-title":"Adv Neural Inf Process Syst"},{"key":"11337_CR66","doi-asserted-by":"crossref","unstructured":"Liu F, Eisenschlos J, Piccinno F, Krichene S, Pang C, Lee K, Joshi M, Chen W, Collier N, Altun Y (2023) DePlot: One-shot visual language reasoning by plot-to-table translation. In Findings of the association for computational linguistics: ACL 2023, Toronto, Canada, pp 10381\u201310399. Association for Computational Linguistics","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"11337_CR74","doi-asserted-by":"crossref","unstructured":"Lovelace J, Mortazavi B (2020) Learning to generate clinically coherent chest X-ray reports. In Cohn T, He Y, Liu Y (Eds.), Findings of the association for computational linguistics: EMNLP 2020, Online, pp 1235\u20131243. Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.findings-emnlp.110"},{"key":"11337_CR75","doi-asserted-by":"publisher","unstructured":"Magalh\u00e3es GV, Santos RLS, Vogado LH, de Paiva AC, dos Santos Neto PdA, (2024) Xrayswingen: Automatic medical reporting for x-ray exams with multimodal model. Heliyon. https:\/\/doi.org\/10.1016\/j.heliyon.2024.e27516","DOI":"10.1016\/j.heliyon.2024.e27516"},{"key":"11337_CR76","doi-asserted-by":"crossref","unstructured":"Manning CD, Surdeanu M, Bauer J, Finkel JR, Bethard S, McClosky D (2014) The stanford corenlp natural language processing toolkit. In Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations, pp 55\u201360","DOI":"10.3115\/v1\/P14-5010"},{"key":"11337_CR77","doi-asserted-by":"publisher","unstructured":"Messina P, Pino P, Parra D, Soto A, Besa C, Uribe S, And\u00eda M, Tejos C, Prieto C, Capurro D (2022) sep. A survey on deep learning and explainability for automatic report generation from medical images. ACM Comput Surv. https:\/\/doi.org\/10.1145\/3522747","DOI":"10.1145\/3522747"},{"key":"11337_CR78","doi-asserted-by":"crossref","unstructured":"Miura Y, Zhang Y, Tsai E, Langlotz C, Jurafsky D (2021) June. Improving factual completeness and consistency of image-to-text radiology report generation. In Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies, Online, pp 5288\u20135304. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.naacl-main.416"},{"key":"11337_CR79","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 106:101878. https:\/\/doi.org\/10.1016\/j.artmed.2020.101878","journal-title":"Artif Intell Med"},{"issue":"12","key":"11337_CR80","doi-asserted-by":"publisher","first-page":"6070","DOI":"10.1109\/JBHI.2022.3207502","volume":"26","author":"JH Moon","year":"2022","unstructured":"Moon JH, Lee H, Shin W, Kim YH, Choi E (2022) Multi-modal understanding and generation for medical images and text via vision-language pre-training. IEEE J Biomed Health Inform 26(12):6070\u20136080. https:\/\/doi.org\/10.1109\/JBHI.2022.3207502","journal-title":"IEEE J Biomed Health Inform"},{"key":"11337_CR81","doi-asserted-by":"crossref","unstructured":"Najdenkoska I, Zhen X, Worring M, Shao L (2021) Variational topic inference for chest x-ray report generation. In International conference on medical image computing and computer-assisted intervention. Springer, pp 625\u2013635","DOI":"10.1007\/978-3-030-87199-4_59"},{"key":"11337_CR82","doi-asserted-by":"crossref","unstructured":"Nguyen H, Nie D, Badamdorj T, Liu Y, Zhu Y, Truong J, Cheng L (2021) Automated generation of accurate & fluent medical X-ray reports. In Proceedings of the 2021 conference on empirical methods in natural language processing, Online and Punta Cana, Dominican Republic, pp 3552\u20133569. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.emnlp-main.288"},{"key":"11337_CR83","doi-asserted-by":"crossref","unstructured":"Ni J, Hsu CN, Gentili A, McAuley J (2020) Learning visual-semantic embeddings for reporting abnormal findings on chest X-rays. In Findings of the association for computational linguistics: EMNLP 2020, Online, pp 1954\u20131960. Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.findings-emnlp.176"},{"key":"11337_CR84","doi-asserted-by":"crossref","unstructured":"Nooralahzadeh F, Perez\u00a0Gonzalez N, Frauenfelder T, Fujimoto K, Krauthammer M (2021) Progressive transformer-based generation of radiology reports. In Findings of the association for computational linguistics: EMNLP 2021, Punta Cana, Dominican Republic, pp 2824\u20132832. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"11337_CR85","doi-asserted-by":"crossref","unstructured":"Pan Y, Yao T, Li Y, Mei T (2020) X-linear attention networks for image captioning. In 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10968\u201310977","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"11337_CR86","doi-asserted-by":"crossref","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, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"issue":"4","key":"11337_CR87","doi-asserted-by":"publisher","first-page":"351","DOI":"10.3390\/bioengineering11040351","volume":"11","author":"D Parres","year":"2024","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\/bioengineering11040351","journal-title":"Bioengineering"},{"key":"11337_CR88","doi-asserted-by":"crossref","unstructured":"Pelka O, Koitka S, R\u00fcckert J, Nensa F, Friedrich CM (2018) Radiology objects in context (roco): a multimodal image dataset. In Intravascular imaging and computer assisted stenting and large-scale annotation of biomedical data and expert label synthesis: 7th joint international workshop, CVII-STENT 2018 and Third International Workshop, LABELS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings 3, pp 180\u2013189. Springer","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"11337_CR89","doi-asserted-by":"publisher","unstructured":"Peng Y, Wang X, Lu L, Bagheri M, Summers R, Lu Z (2018) Negbio: a high-performance tool for negation and uncertainty detection in radiology reports. AMIA Summits on Translational Science Proceedings 2018:188. https:\/\/doi.org\/10.13140\/RG.2.2.19745.10087","DOI":"10.13140\/RG.2.2.19745.10087"},{"key":"11337_CR90","doi-asserted-by":"crossref","unstructured":"Qin H, Song Y (2022) May. Reinforced cross-modal alignment for radiology report generation. In Findings of the association for computational linguistics: ACL 2022, Dublin, Ireland, pp 448\u2013458. Association for Computational Linguistics","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"11337_CR91","unstructured":"Radford A Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners"},{"key":"11337_CR92","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) 18\u201324 Jul. Learning transferable visual models from natural language supervision. In M\u00a0Meila and T\u00a0Zhang (Eds.), Proceedings of the 38th international conference on machine learning, Volume 139 of Proceedings of Machine Learning Research. PMLR, pp 8748\u20138763"},{"key":"11337_CR93","unstructured":"Ramesh V, Chi N, Rajpurkar P Cxr-pro: Mimic-cxr with prior references omitted"},{"issue":"6","key":"11337_CR94","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1109\/TLA.2022.9757742","volume":"20","author":"G Ramirez-Alonso","year":"2022","unstructured":"Ramirez-Alonso G, Prieto-Ordaz O, L\u00f3pez-Santillan R, Montes-Y-G\u00f3mez M (2022) Medical report generation through radiology images: an overview. IEEE Lat Am Trans 20(6):986\u2013999. https:\/\/doi.org\/10.1109\/TLA.2022.9757742","journal-title":"IEEE Lat Am Trans"},{"key":"11337_CR95","unstructured":"Ramos J et\u00a0al (2003) Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, 242, pp 29\u201348. Citeseer"},{"key":"11337_CR96","doi-asserted-by":"publisher","unstructured":"Ranzato M, Chopra S, Auli M, Zaremba W (2015) Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732. https:\/\/doi.org\/10.48550\/arXiv.1511.06732","DOI":"10.48550\/arXiv.1511.06732"},{"key":"11337_CR97","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) November. Sentence-BERT: sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), Hong Kong, China, pp 3982\u20133992. Association for Computational Linguistics","DOI":"10.18653\/v1\/D19-1410"},{"issue":"6","key":"11337_CR98","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11337_CR99","doi-asserted-by":"crossref","unstructured":"Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) Self-critical sequence training for image captioning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7008\u20137024","DOI":"10.1109\/CVPR.2017.131"},{"key":"11337_CR100","unstructured":"R\u00fcckert J, Ben\u00a0Abacha A, Seco\u00a0de Herrera AG, Bloch L, Br\u00fcngel R, Idrissi-Yaghir A, Sch\u00e4fer H, M\u00fcller H, Friedrich CM (2023) Overview of imageclefmedical 2023\u2013caption prediction and concept detection. In Working notes of the conference and labs of the evaluation forum (CLEF 2023), 3497, pp 1328\u20131346"},{"key":"11337_CR101","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-023-01113-y","author":"L Rui","year":"2019","unstructured":"Rui L, Xian-Bo HE (2019) Research progress of lung medical image analysis based on deep learning. J North Sichuan Med Coll. https:\/\/doi.org\/10.1186\/s12938-023-01113-y","journal-title":"J North Sichuan Med Coll"},{"key":"11337_CR102","doi-asserted-by":"crossref","unstructured":"Rus V, Lintean M (2012) An optimal assessment of natural language student input using word-to-word similarity metrics. In Intelligent tutoring systems: 11th international conference, ITS 2012, Chania, Crete, Greece, June 14-18, 2012. Proceedings 11. Springer, pp 675\u2013676","DOI":"10.1007\/978-3-642-30950-2_116"},{"key":"11337_CR103","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2019a) Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter"},{"key":"11337_CR104","doi-asserted-by":"publisher","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2019b) Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. https:\/\/doi.org\/10.48550\/arXiv.1910.01108","DOI":"10.48550\/arXiv.1910.01108"},{"key":"11337_CR105","doi-asserted-by":"publisher","unstructured":"Shen Y Song K, Tan X, Li D, Lu W, Zhuang Y (2023) Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580. https:\/\/doi.org\/10.48550\/arXiv.2303.17580","DOI":"10.48550\/arXiv.2303.17580"},{"key":"11337_CR106","doi-asserted-by":"crossref","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. In 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 1090\u20131099","DOI":"10.1109\/CVPR.2015.7298712"},{"key":"11337_CR107","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In International conference on learning representations"},{"key":"11337_CR108","unstructured":"Song X, Zhang X, Ji J, Liu Y, Wei P (2022) Cross-modal contrastive attention model for medical report generation. In Proceedings of the 29th international conference on computational linguistics, Gyeongju, Republic of Korea, pp 2388\u20132397. International Committee on Computational Linguistics"},{"key":"11337_CR109","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103248","volume":"96","author":"G Spinks","year":"2019","unstructured":"Spinks G, Moens MF (2019) Justifying diagnosis decisions by deep neural networks. J Biomed Inform 96:103248. https:\/\/doi.org\/10.1016\/j.jbi.2019.103248","journal-title":"J Biomed Inform"},{"key":"11337_CR110","doi-asserted-by":"publisher","unstructured":"Sun Z, Deng ZH, Nie JY, Tang J (2019) Rotate: Knowledge graph embedding by relational rotation in complex space. arXiv preprint arXiv:1902.10197. https:\/\/doi.org\/10.48550\/arXiv.1902.10197","DOI":"10.48550\/arXiv.1902.10197"},{"key":"11337_CR111","doi-asserted-by":"crossref","unstructured":"Syeda-Mahmood T, Wong KC, Gur Y, Wu JT, Jadhav A, Kashyap S, Karargyris A, Pillai A, Sharma A, Syed AB et\u00a0al (2020) Chest x-ray report generation through fine-grained label learning. In Medical image computing and computer assisted intervention\u2013MICCAI 2020: 23rd international conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part II 23, pp 561\u2013571. Springer","DOI":"10.1007\/978-3-030-59713-9_54"},{"key":"11337_CR112","doi-asserted-by":"crossref","unstructured":"Tanida T, M\u00fcller P, Kaissis G, Rueckert D (2023) Interactive and explainable region-guided radiology report generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7433\u20137442","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"11337_CR113","doi-asserted-by":"crossref","unstructured":"Tanwani AK, Barral J, Freedman D (2022) Repsnet: Combining vision with language for automated medical reports. In International conference on medical image computing and computer-assisted intervention. Springer, pp 714\u2013724","DOI":"10.1007\/978-3-031-16443-9_68"},{"key":"11337_CR114","unstructured":"Topol E (2019) Deep medicine: how artificial intelligence can make healthcare human again. Hachette UK"},{"key":"11337_CR115","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3364373","author":"H Tsaniya","year":"2024","unstructured":"Tsaniya H, Fatichah C, Suciati N (2024) Automatic radiology report generator using transformer with contrast-based image enhancement. IEEE Access. https:\/\/doi.org\/10.1109\/access.2024.3364373","journal-title":"IEEE Access"},{"key":"11337_CR116","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.00937","author":"A Van Den Oord","year":"2017","unstructured":"Van Den Oord A, Vinyals O et al (2017) Neural discrete representation learning. Adv Neural Inf Process Syst. https:\/\/doi.org\/10.48550\/arXiv.1711.00937","journal-title":"Adv Neural Inf Process Syst"},{"key":"11337_CR117","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Lu, Polosukhin I (2017) Attention is all you need. 30"},{"key":"11337_CR118","doi-asserted-by":"crossref","unstructured":"Vedantam, R, Lawrence\u00a0Zitnick C, Parikh D (2015) Cider: Consensus-based image description evaluation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"11337_CR119","unstructured":"Veli\u010dkovi\u00e9 P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y (2018) Graph attention networks"},{"key":"11337_CR120","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"11337_CR129","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhou L, Wang L, Li X (2021) A self-boosting framework for automated radiographic report generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2433\u20132442","DOI":"10.1109\/CVPR46437.2021.00246"},{"issue":"6","key":"11337_CR121","doi-asserted-by":"publisher","first-page":"5015","DOI":"10.1109\/TCYB.2020.3026098","volume":"52","author":"F Wang","year":"2022","unstructured":"Wang F, Liang X, Xu L, Lin L (2022a) Unifying relational sentence generation and retrieval for medical image report composition. IEEE Trans Cybernet 52(6):5015\u20135025. https:\/\/doi.org\/10.1109\/TCYB.2020.3026098","journal-title":"IEEE Trans Cybernet"},{"key":"11337_CR122","doi-asserted-by":"publisher","first-page":"33536","DOI":"10.48550\/arXiv.2210.06044","volume":"35","author":"F Wang","year":"2022","unstructured":"Wang F, Zhou Y, Wang S, Vardhanabhuti V, Yu L (2022b) Multi-granularity cross-modal alignment for generalized medical visual representation learning. Adv Neural Inf Process Syst 35:33536\u201333549. https:\/\/doi.org\/10.48550\/arXiv.2210.06044","journal-title":"Adv Neural Inf Process Syst"},{"key":"11337_CR123","doi-asserted-by":"publisher","unstructured":"Wang J, Bhalerao A, He Y (2022c) Cross-modal prototype driven network for radiology report generation. pp 563\u2013579. https:\/\/doi.org\/10.1007\/978-3-031-19833-5_33","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"11337_CR125","doi-asserted-by":"crossref","unstructured":"Wang L, Ning M, Lu D, Wei D, Zheng Y, Chen J (2022d) An inclusive task-aware framework for radiology report generation. In International conference on medical image computing and computer-assisted intervention. Springer, pp 568\u2013577","DOI":"10.1007\/978-3-031-16452-1_54"},{"key":"11337_CR126","doi-asserted-by":"crossref","unstructured":"Wang Z, Tang M, Wang L, Li X, Zhou L (2022e) A medical semantic-assisted transformer for radiographic report generation. In International conference on medical image computing and computer-assisted intervention. Springer, pp 655\u2013664","DOI":"10.1007\/978-3-031-16437-8_63"},{"key":"11337_CR127","doi-asserted-by":"crossref","unstructured":"Wang Z, Wu Z, Agarwal D, Sun J (2022f) MedCLIP: Contrastive learning from unpaired medical images and text. In Proceedings of the 2022 conference on empirical methods in natural language processing, Abu Dhabi, United Arab Emirates, pp 3876\u20133887. Association for Computational Linguistics","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"11337_CR128","unstructured":"Wang Z, Yu J, Yu AW, Dai Z, Tsvetkov Y, Cao Y (2022g) SimVLM: Simple visual language model pretraining with weak supervision. In International conference on learning representations"},{"key":"11337_CR124","doi-asserted-by":"crossref","unstructured":"Wang Z, Liu L, Wang L, Zhou L (2023) Metransformer: Radiology report generation by transformer with multiple learnable expert tokens. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11558\u201311567","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"11337_CR131","doi-asserted-by":"publisher","unstructured":"Wu JT, Agu NN, Lourentzou I, Sharma A, Paguio JA, Yao JS, Dee EC, Mitchell W, Kashyap S, Giovannini A et\u00a0al (2021a) Chest imagenome dataset for clinical reasoning. arXiv preprint arXiv:2108.00316. https:\/\/doi.org\/10.48550\/arXiv.2108.00316","DOI":"10.48550\/arXiv.2108.00316"},{"key":"11337_CR130","unstructured":"Wu JT, Agu NN, Lourentzou I, Sharma A, Paguio JA, Yao JS, Dee EC, Mitchell WG, Kashyap S, Giovannini A, Celi LA, Moradi M (2021b) Chest imagenome dataset for clinical reasoning. In Thirty-fifth conference on neural information processing systems datasets and benchmarks track (Round 2)"},{"key":"11337_CR132","doi-asserted-by":"publisher","unstructured":"Wu X, Yang S, Qiu Z, Ge S, Yan Y, Wu X, Zheng Y, Zhou SK, Xiao L (2022) Deltanet: Conditional medical report generation for covid-19 diagnosis. arXiv preprint arXiv:2211.13229. https:\/\/doi.org\/10.48550\/arXiv.2211.13229","DOI":"10.48550\/arXiv.2211.13229"},{"key":"11337_CR133","doi-asserted-by":"publisher","unstructured":"Wu C, Yin S, Qi W, Wang X, Tang Z, Duan N (2023a) Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671. https:\/\/doi.org\/10.48550\/arXiv.2303.04671","DOI":"10.48550\/arXiv.2303.04671"},{"key":"11337_CR134","doi-asserted-by":"publisher","unstructured":"Wu C, Zhang X, Zhang Y, Wang Y, Xie W (2023b) Medklip: Medical knowledge enhanced language-image pre-training for x-ray diagnosis. pp 21315\u201321326. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01954","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"11337_CR135","unstructured":"Xu K Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In F\u00a0Bach and D\u00a0Blei (Eds.), Proceedings of the 32nd international conference on machine learning, Volume\u00a037 of Proceedings of Machine Learning Research, Lille, France. PMLR, pp 2048\u20132057"},{"key":"11337_CR138","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3343391","author":"Z Xu","year":"2023","unstructured":"Xu Z, Xu W, Wang R, Chen J, Qi C, Lukasiewicz T (2023) Hybrid reinforced medical report generation with m-linear attention and repetition penalty. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2023.3343391","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"11337_CR136","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4369200","volume":"97","author":"D Xu","year":"2023","unstructured":"Xu D, Zhu H, Huang Y, Jin Z, Ding W, Li H, Ran M (2023) Vision-knowledge fusion model for multi-domain medical report generation. Inform Fus 97:101817. https:\/\/doi.org\/10.2139\/ssrn.4369200","journal-title":"Inform Fus"},{"key":"11337_CR137","doi-asserted-by":"crossref","unstructured":"Xue Y, Xu T, Rodney\u00a0Long L, Xue Z, Antani S, Thoma GR, Huang X (2018) Multimodal recurrent model with attention for automated radiology report generation. In Medical image computing and computer assisted intervention\u2013MICCAI 2018: 21st international conference, Granada, Spain, September 16\u201320, 2018, Proceedings, Part I. Springer, pp 457\u2013466","DOI":"10.1007\/978-3-030-00928-1_52"},{"key":"11337_CR139","doi-asserted-by":"crossref","unstructured":"Yan S (2022) May. Memory-aligned knowledge graph for clinically accurate radiology image report generation. In Proceedings of the 21st workshop on biomedical language processing, Dublin, Ireland, pp 116\u2013122. Association for Computational Linguistics","DOI":"10.18653\/v1\/2022.bionlp-1.11"},{"key":"11337_CR140","doi-asserted-by":"crossref","unstructured":"Yan B, Pei M (2022) Clinical-bert: Vision-language pre-training for radiograph diagnosis and reports generation. In Proceedings of the AAAI Conference on Artificial Intelligence 36:2982\u20132990","DOI":"10.1609\/aaai.v36i3.20204"},{"issue":"11","key":"11337_CR141","doi-asserted-by":"publisher","first-page":"5631","DOI":"10.1109\/JBHI.2022.3197162","volume":"26","author":"B Yan","year":"2022","unstructured":"Yan B, Pei M, Zhao M, Shan C, Tian Z (2022) Prior guided transformer for accurate radiology reports generation. IEEE J Biomed Health Inform 26(11):5631\u20135640. https:\/\/doi.org\/10.1109\/JBHI.2022.3197162","journal-title":"IEEE J Biomed Health Inform"},{"issue":"8","key":"11337_CR142","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1109\/TMI.2023.3245608","volume":"42","author":"S Yan","year":"2023","unstructured":"Yan S, Cheung WK, Chiu K, Tong TM, Cheung KC, See S (2023) Attributed abnormality graph embedding for clinically accurate x-ray report generation. IEEE Trans Med Imaging 42(8):2211\u20132222. https:\/\/doi.org\/10.1109\/TMI.2023.3245608","journal-title":"IEEE Trans Med Imaging"},{"key":"11337_CR143","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3122542","author":"Y Yang","year":"2021","unstructured":"Yang Y, Yu J, Zhang J, Han W, Jiang H, Huang Q (2021a) Joint embedding of deep visual and semantic features for medical image report generation. IEEE Trans Multimedia. https:\/\/doi.org\/10.1109\/TMM.2021.3122542","journal-title":"IEEE Trans Multimedia"},{"key":"11337_CR147","doi-asserted-by":"crossref","unstructured":"Yang X, Ye M, You Q, Ma F (2021b) Writing by memorizing: hierarchical retrieval-based medical report generation. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (Volume 1: Long Papers), Online, pp 5000\u20135009. Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.acl-long.387"},{"key":"11337_CR144","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510","volume":"80","author":"S Yang","year":"2022","unstructured":"Yang S, Wu X, Ge S, Zhou SK, Xiao L (2022a) Knowledge matters: chest radiology report generation with general and specific knowledge. Med Image Anal 80:102510. https:\/\/doi.org\/10.1016\/j.media.2022.102510","journal-title":"Med Image Anal"},{"key":"11337_CR145","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.neucom.2022.06.063","volume":"502","author":"Y Yang","year":"2022","unstructured":"Yang Y, Yu J, Jiang H, Han W, Zhang J, Jiang W (2022b) A contrastive triplet network for automatic chest x-ray reporting. Neurocomputing 502:71\u201383. https:\/\/doi.org\/10.1016\/j.neucom.2022.06.063","journal-title":"Neurocomputing"},{"key":"11337_CR146","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102798","volume":"86","author":"S Yang","year":"2023","unstructured":"Yang S, Wu X, Ge S, Zheng Z, Zhou SK, Xiao L (2023) Radiology report generation with a learned knowledge base and multi-modal alignment. Med Image Anal 86:102798. https:\/\/doi.org\/10.1016\/j.media.2023.102798","journal-title":"Med Image Anal"},{"key":"11337_CR148","doi-asserted-by":"crossref","unstructured":"Yan S, Wu F, Smith JS, Lu W, Zhang B (2018) Image captioning using adversarial networks and reinforcement learning. In 2018 24th International conference on pattern recognition (ICPR). IEEE, pp 248\u2013253","DOI":"10.1109\/ICPR.2018.8545049"},{"issue":"4","key":"11337_CR149","doi-asserted-by":"publisher","first-page":"2152","DOI":"10.1109\/JBHI.2024.3350077","volume":"28","author":"X Yi","year":"2024","unstructured":"Yi X, Fu Y, Liu R, Zhang H, Hua R (2024) Tsget: Two-stage global enhanced transformer for automatic radiology report generation. IEEE J Biomed Health Inform 28(4):2152\u20132160. https:\/\/doi.org\/10.1109\/JBHI.2024.3350077","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"11337_CR150","doi-asserted-by":"publisher","first-page":"1494","DOI":"10.1109\/TMI.2024.3507073","volume":"44","author":"X Yi","year":"2025","unstructured":"Yi X, Fu Y, Yu J, Liu R, Zhang H, Hua R (2025) Lhr-rfl: Linear hybrid-reward-based reinforced focal learning for automatic radiology report generation. IEEE Trans Med Imaging 44(3):1494\u20131500. https:\/\/doi.org\/10.1109\/TMI.2024.3507073","journal-title":"IEEE Trans Med Imaging"},{"key":"11337_CR151","doi-asserted-by":"crossref","unstructured":"Yin C, Qian B, Wei J, Li X, Zhang X, Li Y, Zheng Q (2019) Automatic generation of medical imaging diagnostic report with hierarchical recurrent neural network. In 2019 IEEE international conference on data mining (ICDM). IEEE, pp 728\u2013737","DOI":"10.1109\/ICDM.2019.00083"},{"key":"11337_CR152","doi-asserted-by":"crossref","unstructured":"You D, Liu F, Ge S, Xie X, Zhang J, Wu X (2021) Aligntransformer: hierarchical alignment of visual regions and disease tags for medical report generation. In International conference on medical image computing and computer-assisted intervention. Springer, pp 72\u201382","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"11337_CR153","doi-asserted-by":"crossref","unstructured":"Yuan J, Liao H, Luo R, Luo J (2019) Automatic radiology report generation based on multi-view image fusion and medical concept enrichment. In International conference on medical image computing and computer-assisted intervention. Springer, pp 721\u2013729","DOI":"10.1007\/978-3-030-32226-7_80"},{"key":"11337_CR155","doi-asserted-by":"crossref","unstructured":"Yu H, Zhang Q (2022) Clinically coherent radiology report generation with imbalanced chest x-rays. In 2022 IEEE International conference on bioinformatics and biomedicine (BIBM), pp 1781\u20131786","DOI":"10.1109\/BIBM55620.2022.9994871"},{"key":"11337_CR156","doi-asserted-by":"crossref","unstructured":"Yu L, Zhang W, Wang J, Yu Y (2017) Seqgan: Sequence generative adversarial nets with policy gradient. In Proceedings of the AAAI conference on artificial intelligence, 31","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"11337_CR154","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802","author":"F Yu","year":"2023","unstructured":"Yu F, Endo M, Krishnan R, Pan I, Tsai A, Reis EP, Fonseca EKUN, Lee HMH, Abad ZSH, Ng AY, Langlotz CP, Venugopal VK, Rajpurkar P (2023) Evaluating progress in automatic chest x-ray radiology report generation. Patterns. https:\/\/doi.org\/10.1016\/j.patter.2023.100802","journal-title":"Patterns"},{"key":"11337_CR157","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wang X, Xu Z, Yu Q, Yuille A, Xu D (2020) When radiology report generation meets knowledge graph. In Proceedings of the AAAI Conference on Artificial Intelligence 34:12910\u201312917","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"11337_CR160","unstructured":"Zhang Y, Jiang H, Miura Y, Manning CD, Langlotz CP (2022) Contrastive learning of medical visual representations from paired images and text. In Z\u00a0Lipton, R\u00a0Ranganath, M\u00a0Sendak, M\u00a0Sjoding, and S\u00a0Yeung (Eds.), Proceedings of the 7th machine learning for healthcare conference, Volume 182 of Proceedings of Machine Learning Research, pp 2\u201325. PMLR"},{"issue":"1","key":"11337_CR158","doi-asserted-by":"publisher","first-page":"4542","DOI":"10.1038\/s41467-023-40260-7","volume":"14","author":"X Zhang","year":"2023","unstructured":"Zhang X, Wu C, Zhang Y, Xie W, Wang Y (2023) Knowledge-enhanced visual-language pre-training on chest radiology images. Nat Commun 14(1):4542. https:\/\/doi.org\/10.1038\/s41467-023-40260-7","journal-title":"Nat Commun"},{"key":"11337_CR159","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2024.3424505","author":"K Zhang","year":"2024","unstructured":"Zhang K, Yang Y, Yu J, Fan J, Jiang H, Huang Q, Han W (2024) Attribute prototype-guided iterative scene graph for explainable radiology report generation. IEEE Trans Med Imaging. https:\/\/doi.org\/10.1109\/tmi.2024.3424505","journal-title":"IEEE Trans Med Imaging"},{"key":"11337_CR161","doi-asserted-by":"publisher","unstructured":"Zhao W, Wu C, Zhang X, Zhang Y, Wang Y, Xie W (2024) Ratescore: A metric for radiology report generation. arXiv preprint arXiv:2406.16845. https:\/\/doi.org\/10.1101\/2024.06.24.24309405","DOI":"10.1101\/2024.06.24.24309405"},{"key":"11337_CR162","doi-asserted-by":"crossref","unstructured":"Zhou Y, Huang L, Zhou T, Fu H, Shao L (2021) Visual-textual attentive semantic consistency for medical report generation. In Proceedings of the IEEE\/CVF international conference on computer vision, pp 3985\u20133994","DOI":"10.1109\/ICCV48922.2021.00395"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11337-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-025-11337-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11337-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T01:49:22Z","timestamp":1761356962000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-025-11337-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":162,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["11337"],"URL":"https:\/\/doi.org\/10.1007\/s10462-025-11337-0","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"22 July 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","order":2,"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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"344"}}