{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T05:35:05Z","timestamp":1737610505824,"version":"3.33.0"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Council for the Humanities, Sciences, and Technologies (Conahcyt) of Mexico","award":["CF-2019\\1311317"],"award-info":[{"award-number":["CF-2019\\1311317"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00521-024-10382-0","type":"journal-article","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T05:56:09Z","timestamp":1731736569000},"page":"43-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward an enhanced automatic medical report generator based on large transformer models"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0023-9535","authenticated-orcid":false,"given":"Olanda","family":"Prieto-Ordaz","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-3010","authenticated-orcid":false,"given":"Graciela","family":"Ramirez-Alonso","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7601-501X","authenticated-orcid":false,"given":"Manuel","family":"Montes-y-Gomez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6186-0192","authenticated-orcid":false,"given":"Roberto","family":"Lopez-Santillan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,16]]},"reference":[{"issue":"1","key":"10382_CR1","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.imed.2022.07.002","volume":"3","author":"K He","year":"2023","unstructured":"He K, Gan C, Li Z, Rekik I, Yin Z, Ji W, Gao Y, Wang Q, Zhang J, Shen D (2023) Transformers in medical image analysis. Intell Med 3(1):59\u201378. https:\/\/doi.org\/10.1016\/j.imed.2022.07.002","journal-title":"Intell Med"},{"key":"10382_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-12575-2_1","volume-title":"Data compression and its application in medical imaging","author":"RM Thanki","year":"2019","unstructured":"Thanki RM, Kothari A (2019) Data compression and its application in medical imaging. Springer, Berlin, pp 1\u201315. https:\/\/doi.org\/10.1007\/978-3-030-12575-2_1"},{"key":"10382_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2023.101273","volume":"39","author":"Y Liao","year":"2023","unstructured":"Liao Y, Liu H, Spasic I (2023) Deep learning approaches to automatic radiology report generation: a systematic review. Inform Med Unlocked 39:101273. https:\/\/doi.org\/10.1016\/j.imu.2023.101273","journal-title":"Inform Med Unlocked"},{"key":"10382_CR4","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s12938-023-01113-y","volume":"22","author":"T Pang","year":"2023","unstructured":"Pang T, Li P, Zhao L (2023) A survey on automatic generation of medical imaging reports based on deep learning. Biomed Eng Online 22:48. https:\/\/doi.org\/10.1186\/s12938-023-01113-y","journal-title":"Biomed Eng Online"},{"key":"10382_CR5","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. Inform Med Unlocked 24:100557. https:\/\/doi.org\/10.1016\/j.imu.2021.100557","journal-title":"Inform Med Unlocked"},{"key":"10382_CR6","doi-asserted-by":"publisher","unstructured":"Mayor S (2015) Waiting times for x ray results in england are increasing, figures show. In: BMJ Clinical Research Ed. vol. 350, p. 1598. https:\/\/doi.org\/10.1136\/bmj.h1598","DOI":"10.1136\/bmj.h1598"},{"issue":"1","key":"10382_CR7","first-page":"3","volume":"81","author":"A Brady","year":"2012","unstructured":"Brady A, Laoide RO, McCarthy P, McDermott R (2012) Discrepancy and error in radiology: concepts, causes and consequences. Ulst Med J 81(1):3\u20139","journal-title":"Ulst Med J"},{"key":"10382_CR8","doi-asserted-by":"publisher","first-page":"20180845","DOI":"10.1259\/bjr.20180845","volume":"92","author":"G Maskell","year":"2018","unstructured":"Maskell G (2018) Error in radiology - where are we now? Br J Radiol 92:20180845. https:\/\/doi.org\/10.1259\/bjr.20180845","journal-title":"Br J Radiol"},{"key":"10382_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102762","volume":"85","author":"J Li","year":"2023","unstructured":"Li J, Chen J, Tang Y, Wang C, Landman BA, Zhou SK (2023) Transforming medical imaging with transformers? a comparative review of key properties, current progresses, and future perspectives. Med Image Anal 85:102762. https:\/\/doi.org\/10.1016\/j.media.2023.102762","journal-title":"Med Image Anal"},{"issue":"10s","key":"10382_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3522747","volume":"54","author":"P Messina","year":"2022","unstructured":"Messina P, Pino P, Parra D, Soto A, Besa C, Uribe S, And\u00eda M, Tejos C, Prieto C, Capurro D (2022) A survey on deep learning and explainability for automatic report generation from medical images. ACM Comput Surv 54(10s):1\u201340. https:\/\/doi.org\/10.1145\/3522747","journal-title":"ACM Comput Surv"},{"key":"10382_CR11","volume-title":"Advances in neural information processing systems","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN (2017) Kaiser, L.u., Polosukhin, I.: attention is all you need. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30. Curran Associates Inc, Red Hook, NY, USA"},{"key":"10382_CR12","doi-asserted-by":"publisher","first-page":"16056","DOI":"10.18653\/v1\/2020.emnlp-main.112","volume":"2010","author":"Z Chen","year":"2020","unstructured":"Chen Z, Song Y, Chang T-H, Wan X (2020) Generating radiology reports via memory-driven transformer. Assoc Comput Linguist(ACL) 2010:16056. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.112","journal-title":"Assoc Comput Linguist(ACL)"},{"key":"10382_CR13","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-030-87199-4_7","volume-title":"Medical image computing and computer assisted intervention - MICCAI 2021","author":"D You","year":"2021","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: Bruijne M, Cattin PC, Cotin S, Padoy N, Speidel S, Zheng Y, Essert C (eds) Medical image computing and computer assisted intervention - MICCAI 2021, vol 12903. LNCS. Cham, Springer, pp 72\u201382. https:\/\/doi.org\/10.1007\/978-3-030-87199-4_7"},{"key":"10382_CR14","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-87199-4_10","volume-title":"Medical image computing and computer assisted intervention - MICCAI 2021","author":"G Tulder","year":"2021","unstructured":"Tulder G, Tong Y, Marchiori E (2021) Multi-view analysis of unregistered medical images using cross-view transformers. Medical image computing and computer assisted intervention - MICCAI 2021. Springer, Strasbourg, pp 104\u2013113. https:\/\/doi.org\/10.1007\/978-3-030-87199-4_10"},{"key":"10382_CR15","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. association for computational linguistics.https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"10382_CR16","doi-asserted-by":"publisher","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S, Bikel D, Blecher L, Ferrer CC, Chen M, Cucurull G, Esiobu D, Fernandes J, Fu J, Fu W, Fuller B, Gao C, Goswami V, Goyal N, Hartshorn A, Hosseini S, Hou R, Inan H, Kardas M, Kerkez V, Khabsa M, Kloumann I, Korenev A, Koura PS, Lachaux M-A, Lavril T, Lee J, Liskovich D, Lu Y, Mao Y, Martinet X, Mihaylov T, Mishra P, Molybog I, Nie Y, Poulton A, Reizenstein J, Rungta R, Saladi K, Schelten A, Silva R, Smith EM, Subramanian R, Tan XE, Tang B, Taylor R, Williams A, Kuan JX, Xu P, Yan Z, Zarov I, Zhang Y, Fan A, Kambadur M, Narang S, Rodriguez A, Stojnic R, Edunov S, Scialom T (2023) Llama 2: open foundation and fine-tuned chat models. https:\/\/doi.org\/10.48550\/arXiv.2307.09288","DOI":"10.48550\/arXiv.2307.09288"},{"issue":"8","key":"10382_CR17","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I et al (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9","journal-title":"OpenAI blog"},{"key":"10382_CR18","doi-asserted-by":"publisher","unstructured":"Xie Q, Schenck EJ, Yang HS, Chen Y, Peng Y, Wang F (2023) Faithful AI in medicine: a systematic review with large language models and beyond. medRxiv. https:\/\/doi.org\/10.1101\/2023.04.18.23288752","DOI":"10.1101\/2023.04.18.23288752"},{"issue":"2","key":"10382_CR19","doi-asserted-by":"publisher","first-page":"81","DOI":"10.54097\/fcis.v2i2.4465","volume":"2","author":"J Deng","year":"2023","unstructured":"Deng J, Lin Y (2023) The benefits and challenges of ChatGPT: An overview. Frontiers in Computing and Intelligent Systems 2(2):81\u201383. https:\/\/doi.org\/10.54097\/fcis.v2i2.4465","journal-title":"Frontiers in Computing and Intelligent Systems"},{"key":"10382_CR20","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1007\/978-3-031-45673-2_46","volume-title":"International workshop on machine learning in medical imaging","author":"Z Liu","year":"2024","unstructured":"Liu Z, Zhong A, Li Y, Yang L, Ju C, Wu Z, Ma C, Shu P, Chen C, Kim S et al (2024) Tailoring large language models to radiology: a preliminary approach to LLM adaptation for a highly specialized domain. International workshop on machine learning in medical imaging. Springer, Cham, pp 464\u2013473. https:\/\/doi.org\/10.1007\/978-3-031-45673-2_46"},{"issue":"9","key":"10382_CR21","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1001\/jama.2023.14217","volume":"330","author":"NH Shah","year":"2023","unstructured":"Shah NH, Entwistle D, Pfeffer MA (2023) Creation and adoption of large language models in medicine. JAMA 330(9):866\u2013869. https:\/\/doi.org\/10.1001\/jama.2023.14217","journal-title":"JAMA"},{"key":"10382_CR22","unstructured":"Villa-Cueva E, Valles-Silva JM, L\u00f3pez-Monroy AP, Sanchez-Vega F, Lopez-Santillan R (2023) Few shot profiling of cryptocurrency influencers using natural language inference & Large Language Models. CEUR-WS.org"},{"key":"10382_CR23","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135","author":"K Papineni","year":"2002","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) BLEU: a method for automatic evaluation of machine translation. Assoc Comput Linguist. https:\/\/doi.org\/10.3115\/1073083.1073135","journal-title":"Assoc Comput Linguist"},{"key":"10382_CR24","unstructured":"Banerjee S, Lavie A (2005) METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. Assoc Comput Linguist"},{"key":"10382_CR25","first-page":"74","volume-title":"Text summarization branches out","author":"C-Y Lin","year":"2004","unstructured":"Lin C-Y (2004) ROUGE: a package for automatic evaluation of summaries. Text summarization branches out. Association for Computational Linguistics, Barcelona, Spain, pp 74\u201381"},{"key":"10382_CR26","doi-asserted-by":"publisher","unstructured":"Vedantam R, Zitnick CL, Parikh D (2015) CIDEr: Consensus-based image description evaluation. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp. 4566\u20134575. https:\/\/doi.org\/10.1109\/CVPR.2015.7299087","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"10382_CR27","doi-asserted-by":"publisher","first-page":"08195","DOI":"10.18653\/v1\/P18-1240","volume":"1711","author":"B Jing","year":"2017","unstructured":"Jing B, Xie P, Xing E (2017) On the automatic generation of medical imaging reports. Assoc Comput Linguist (ACL). 1711:08195. https:\/\/doi.org\/10.18653\/v1\/P18-1240","journal-title":"Assoc Comput Linguist (ACL)."},{"key":"10382_CR28","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/978-3-030-00928-1_52","volume-title":"Medical image computing and computer assisted intervention - MICCAI 2018","author":"Y Xue","year":"2018","unstructured":"Xue Y, Xu T, Rodney Long L, Xue Z, Antani S, Thoma GR, Huang X (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 - MICCAI 2018. Springer, Cham, pp 457\u2013466. https:\/\/doi.org\/10.1007\/978-3-030-00928-1_52"},{"key":"10382_CR29","first-page":"1530","volume":"5","author":"CY Li","year":"2018","unstructured":"Li CY, Liang X, Hu Z, Xing EP (2018) Hybrid retrieval-generation reinforced agent for medical image report generation. Adv Neural Inf Process Syst 5:1530\u20131540","journal-title":"Adv Neural Inf Process Syst"},{"key":"10382_CR30","doi-asserted-by":"publisher","unstructured":"Shin H-C, 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.https:\/\/doi.org\/10.1109\/CVPR.2015.7298712","DOI":"10.1109\/CVPR.2015.7298712"},{"key":"10382_CR31","doi-asserted-by":"publisher","unstructured":"Shin H-C, 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. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp. 2497\u20132506. https:\/\/doi.org\/10.1109\/CVPR.2016.274","DOI":"10.1109\/CVPR.2016.274"},{"key":"10382_CR32","doi-asserted-by":"publisher","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Summers RM (2018) TieNet: text-image embedding network for common thorax disease classification and reporting in chest x-rays. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp. 9049\u20139058. https:\/\/doi.org\/10.1109\/CVPR.2018.00943","DOI":"10.1109\/CVPR.2018.00943"},{"key":"10382_CR33","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. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp. 3549\u20133557. https:\/\/doi.org\/10.1109\/CVPR.2017.378","DOI":"10.1109\/CVPR.2017.378"},{"key":"10382_CR34","unstructured":"Liu G, Hsu T-MH, McDermott M, Boag W, Weng W-H, 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., Wiens, J. (eds.) Proceedings of the 4th machine learning for healthcare conference. proceedings of machine learning research, vol. 106, pp. 249\u2013269. PMLR, Ann Arbor, Michigan"},{"key":"10382_CR35","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1007\/978-3-030-18590-9_64","volume-title":"Database systems for advanced applications","author":"X Xie","year":"2019","unstructured":"Xie X, Xiong Y, Yu PS, Li K, Zhang S, Zhu Y (2019) Attention-based abnormal-aware fusion network for radiology report generation. In: Li G, Yang J, Gama J, Natwichai J, Tong Y (eds) Database systems for advanced applications, vol 11448. LNCS. Cham, Springer, pp 448\u2013452. https:\/\/doi.org\/10.1007\/978-3-030-18590-9_64"},{"key":"10382_CR36","doi-asserted-by":"publisher","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: medical image computing and computer assisted intervention \u2013 MICCAI 2019, vol. 11769 LNCS, pp. 721\u2013729. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-32226-7_80","DOI":"10.1007\/978-3-030-32226-7_80"},{"key":"10382_CR37","doi-asserted-by":"publisher","first-page":"7441","DOI":"10.1007\/s00521-021-05943-6","volume":"33","author":"S Singh","year":"2021","unstructured":"Singh S, Karimi S, Ho-Shon K, Hamey L (2021) Show, tell and summarise: learning to generate and summarise radiology findings from medical images. Neural Comput Appl 33:7441\u20137465. https:\/\/doi.org\/10.1007\/s00521-021-05943-6","journal-title":"Neural Comput Appl"},{"key":"10382_CR38","doi-asserted-by":"publisher","first-page":"269","DOI":"10.18653\/v1\/2021.findings-acl.23","volume-title":"Findings of the association for computational linguistics: ACL-IJCNLP 2021","author":"F Liu","year":"2021","unstructured":"Liu F, Yin C, Wu X, Ge S, Zhang P, Sun X (2021) Contrastive attention for automatic chest x-ray report generation. Findings of the association for computational linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, Stroudsburg, PA, USA, pp 269\u2013280. https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.23"},{"key":"10382_CR39","doi-asserted-by":"publisher","unstructured":"Liu F, Ge S, Wu X (2021) 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, Vol 1: Long Papers, pp. 3001\u20133012. Association for Computational Linguistics, Stroudsburg, PA, USA. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.234","DOI":"10.18653\/v1\/2021.acl-long.234"},{"issue":"07","key":"10382_CR40","doi-asserted-by":"publisher","first-page":"12910","DOI":"10.1609\/aaai.v34i07.6989","volume":"34","author":"Y Zhang","year":"2020","unstructured":"Zhang Y, Wang X, Xu Z, Yu Q, Yuille A, Xu D (2020) When radiology report generation meets knowledge graph. Proc AAAI Conf Artif Intell 34(07):12910\u201312917. https:\/\/doi.org\/10.1609\/aaai.v34i07.6989","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10382_CR41","doi-asserted-by":"publisher","unstructured":"Liu F, Wu X, Ge S, Fan W, Zou Y (2021) Exploring and distilling posterior and prior knowledge for radiology report generation. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 13748\u201313757. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01354","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"10382_CR42","doi-asserted-by":"publisher","unstructured":"Nooralahzadeh F, Perez\u00a0Gonzalez N, Frauenfelder T, Fujimoto K, Krauthammer M (2021) Progressive transformer-based generation of radiology reports. In: Moens, M.-F., Huang, X., Specia, L., Yih, S.W.-t. (eds.) Findings of the association for computational linguistics: EMNLP 2021, pp. 2824\u20132832. Association for Computational Linguistics, Punta Cana, Dominican Republic. https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.241","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"issue":"1","key":"10382_CR43","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):60. https:\/\/doi.org\/10.1186\/s40537-019-0197-0","journal-title":"J Big Data"},{"issue":"3","key":"10382_CR44","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.1007\/s00521-022-07953-4","volume":"35","author":"P Celard","year":"2023","unstructured":"Celard P, Iglesias EL, Sorribes-Fdez JM, Romero R, Vieira AS, Borrajo L (2023) A survey on deep learning applied to medical images: from simple artificial neural networks to generative models. Neural Comput Appl 35(3):2291\u20132323. https:\/\/doi.org\/10.1007\/s00521-022-07953-4","journal-title":"Neural Comput Appl"},{"key":"10382_CR45","doi-asserted-by":"publisher","first-page":"24055","DOI":"10.1007\/s00521-023-09100-z","volume":"35","author":"A Makhlouf","year":"2023","unstructured":"Makhlouf A, Maayah M, Abughanam N, Catal C (2023) The use of generative adversarial networks in medical image augmentation. Neural Comput Appl 35:24055\u201324068. https:\/\/doi.org\/10.1007\/s00521-023-09100-z","journal-title":"Neural Comput Appl"},{"key":"10382_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109803","volume":"132","author":"LFAO Pellicer","year":"2023","unstructured":"Pellicer LFAO, Ferreira TM, Costa AHR (2023) Data augmentation techniques in natural language processing. Appl Soft Comput 132:109803. https:\/\/doi.org\/10.1016\/j.asoc.2022.109803","journal-title":"Appl Soft Comput"},{"key":"10382_CR47","unstructured":"Dai H, Liu Z, Liao W, Huang X, Cao Y, Wu Z, Zhao L, Xu S, Liu W, Liu N, Li S, Zhu D, Cai H, Sun L, Li Q, Shen D, Liu T, Li X (2023) AugGPT: leveraging ChatGPT for text data augmentation. arXiv.2302:13007"},{"key":"10382_CR48","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. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"10382_CR49","doi-asserted-by":"publisher","unstructured":"Davier M (2019) Training optimus prime, M.D.: Generating medical certification items by fine-tuning openAI\u2019s gpt2 transformer model. https:\/\/doi.org\/10.48550\/arXiv.1908.08594","DOI":"10.48550\/arXiv.1908.08594"},{"key":"10382_CR50","doi-asserted-by":"publisher","unstructured":"Cornia M, Stefanini M, Baraldi L, Cucchiara R (2020) Meshed-memory transformer for image captioning. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 10575\u201310584. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01059","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"10382_CR51","doi-asserted-by":"publisher","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp. 6077\u20136086. https:\/\/doi.org\/10.1109\/CVPR.2018.00636","DOI":"10.1109\/CVPR.2018.00636"},{"issue":"1","key":"10382_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AEW Johnson","year":"2019","unstructured":"Johnson AEW, Pollard TJ, Berkowitz SJ, Greenbaum NR, Lungren MP, Cy Den, Mark RG, Horng S (2019) MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data 6(1):1\u20138. https:\/\/doi.org\/10.1038\/s41597-019-0322-0","journal-title":"Sci Data"},{"key":"10382_CR53","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 23:304\u2013310. https:\/\/doi.org\/10.1093\/jamia\/ocv080","journal-title":"J Am Med Inform Assoc"},{"key":"10382_CR54","doi-asserted-by":"publisher","unstructured":"Chen X, Fang H, Lin T-Y, Vedantam R, Gupta S, Dollar P, Zitnick CL (2015) Microsoft COCO captions: data collection and evaluation server. https:\/\/doi.org\/10.48550\/arXiv.1504.00325","DOI":"10.48550\/arXiv.1504.00325"},{"key":"10382_CR55","unstructured":"Fellbaum C (2005) WordNet publications WordNet. https:\/\/wordnet.princeton.edu\/publications"},{"issue":"12","key":"10382_CR56","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 Y-H, 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":"10382_CR57","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1007\/978-3-642-04898-2_616","volume-title":"International encyclopedia of statistical science","author":"D Rey","year":"2011","unstructured":"Rey D, Neuh\u00e4user M (2011) Wilcoxon-signed-rank test. In: Lovric M (ed) International encyclopedia of statistical science. Springer, Germany, pp 1658\u20131659. https:\/\/doi.org\/10.1007\/978-3-642-04898-2_616"},{"key":"10382_CR58","doi-asserted-by":"publisher","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp. 3156\u20133164.https:\/\/doi.org\/10.1109\/CVPR.2015.7298935","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"10382_CR59","doi-asserted-by":"publisher","unstructured":"Jing B, Wang Z, Xing E (2019) 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, pp. 6570\u20136580. Association for computational linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/P19-1657","DOI":"10.18653\/v1\/P19-1657"},{"key":"10382_CR60","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 (2022) 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":"10382_CR61","doi-asserted-by":"publisher","unstructured":"Lu J, Xiong C, Parikh D, Socher R (2017) Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp. 3242\u20133250. https:\/\/doi.org\/10.1109\/CVPR.2017.345","DOI":"10.1109\/CVPR.2017.345"},{"issue":"01","key":"10382_CR62","doi-asserted-by":"publisher","first-page":"6666","DOI":"10.1609\/aaai.v33i01.33016666","volume":"33","author":"CY Li","year":"2019","unstructured":"Li CY, Liang X, Hu Z, Xing EP (2019) Knowledge-driven encode, retrieve, paraphrase for medical image report generation. Proc AAAI Conf Artif Intell 33(01):6666\u20136673. https:\/\/doi.org\/10.1609\/aaai.v33i01.33016666","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10382_CR63","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s11280-022-01013-6","volume":"26","author":"M Li","year":"2022","unstructured":"Li M, Liu R, Wang F, Chang X (2022) Liang X (2022) Auxiliary signal-guided knowledge encoder-decoder for medical report generation. World Wide Web 26:253\u2013270. https:\/\/doi.org\/10.1007\/s11280-022-01013-6","journal-title":"World Wide Web"},{"key":"10382_CR64","doi-asserted-by":"publisher","unstructured":"Nooralahzadeh F, Perez\u00a0Gonzalez NA, Frauenfelder T, Fujimoto K, Krauthammer M (2021) Progressive transformer-based generation of radiology reports. https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.241","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"10382_CR65","doi-asserted-by":"publisher","unstructured":"Mccormick JR, Sama AJ, Schiller NC, Butler AJ, Donnally CJ Cervical spondylotic myelopathy: A guide to diagnosis and management https:\/\/doi.org\/10.3122\/jabfm.2020.02.190195","DOI":"10.3122\/jabfm.2020.02.190195"},{"key":"10382_CR66","doi-asserted-by":"publisher","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Assoc Comput Linguist.https:\/\/doi.org\/10.18653\/v1\/D19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"10382_CR67","doi-asserted-by":"publisher","unstructured":"Chen J, Kao S-H, He H, Zhuo W, Wen S, Lee C-H, Chan S-HG (2023) Run, don\u2019t walk: chasing higher flops for faster neural networks. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 12021\u201312031. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01157","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"10382_CR68","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1259652","author":"W Lu","year":"2023","unstructured":"Lu W, Jiang J, Shi Y, Zhong X, Gu J, Huangfu L, Gong M (2023) Application of entity-bert model based on neuroscience and brain-like cognition in electronic medical record entity recognition. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2023.1259652","journal-title":"Front Neurosci"},{"key":"10382_CR69","unstructured":"Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y (2024) Transformer in transformer. In: Proceedings of the 35th international conference on neural information processing systems. NIPS \u201921. Curran Associates Inc., Red Hook, NY, USA"},{"key":"10382_CR70","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus W, Zoph B, Shazeer N (2022) Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J Mach Learn Res 23:1\u201339","journal-title":"J Mach Learn Res"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10382-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10382-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10382-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T02:05:25Z","timestamp":1737597925000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10382-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,16]]},"references-count":70,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10382"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10382-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,11,16]]},"assertion":[{"value":"8 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2024","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}