{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T10:24:37Z","timestamp":1771669477817,"version":"3.50.1"},"reference-count":87,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T00:00:00Z","timestamp":1617580800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T00:00:00Z","timestamp":1617580800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001230","name":"Macquarie University","doi-asserted-by":"publisher","award":["2016044"],"award-info":[{"award-number":["2016044"]}],"id":[{"id":"10.13039\/501100001230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000943","name":"Commonwealth Scientific and Industrial Research Organisation","doi-asserted-by":"publisher","award":["Top-up scholarship"],"award-info":[{"award-number":["Top-up scholarship"]}],"id":[{"id":"10.13039\/501100000943","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s00521-021-05943-6","type":"journal-article","created":{"date-parts":[[2021,4,5]],"date-time":"2021-04-05T17:02:55Z","timestamp":1617642175000},"page":"7441-7465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Show, tell and summarise: learning to generate and summarise radiology findings from medical images"],"prefix":"10.1007","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6485-131X","authenticated-orcid":false,"given":"Sonit","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarvnaz","family":"Karimi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Ho-Shon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Len","family":"Hamey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,5]]},"reference":[{"issue":"4","key":"5943_CR1","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1002\/jmrs.369","volume":"66","author":"SJ Lewis","year":"2019","unstructured":"Lewis SJ, Gandomkar Z, Brennan PC (2019) Artificial intelligence in medical imaging practice: looking to the future. J Med Radiat Sci 66(4):292\u2013295","journal-title":"J Med Radiat Sci"},{"issue":"2","key":"5943_CR2","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","journal-title":"J Am Med Inform Assoc"},{"issue":"2\/3","key":"5943_CR3","doi-asserted-by":"publisher","first-page":"2:1","DOI":"10.1147\/JRD.2015.2393193","volume":"59","author":"P Kisilev","year":"2015","unstructured":"Kisilev P, Walach E, Barkan E, Ophir B, Alpert S, Hashoul SY (2015) From medical image to automatic medical report generation. IBM J Res Dev 59(2\/3):2:1\u20132:7","journal-title":"IBM J Res Dev"},{"key":"5943_CR4","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-319-46976-8_13","volume-title":"Deep learning and data labeling for medical applications","author":"P Kisilev","year":"2016","unstructured":"Kisilev P, Sason E, Barkan E, Hashoul S (2016) Medical image description using multi-task-loss CNN. In: Carneiro G, Mateus D, Peter L, Bradley A, Tavares JMRS, Belagiannis V, Papa JP, Nascimento JC, Loog M, Lu Z, Cardoso JS, Cornebise J (eds) Deep learning and data labeling for medical applications. Springer, Berlin, pp 121\u2013129"},{"key":"5943_CR5","doi-asserted-by":"crossref","unstructured":"Jing B, Xie P, Xing E (2018) On the automatic generation of medical imaging reports. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: long Papers). Association for Computational Linguistics, pp 2577\u20132586","DOI":"10.18653\/v1\/P18-1240"},{"key":"5943_CR6","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), pp 728\u2013737","DOI":"10.1109\/ICDM.2019.00083"},{"key":"5943_CR7","doi-asserted-by":"crossref","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. Association for Computational Linguistics, Florence, pp 6570\u20136580","DOI":"10.18653\/v1\/P19-1657"},{"issue":"4","key":"5943_CR8","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2017) Show and tell: lessons learned from the 2015 mscoco image captioning challenge. IEEE Trans Pattern Anal Mach Intell 39(4):652\u2013663","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5943_CR9","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. The MIT Press, Cambridge"},{"issue":"1","key":"5943_CR10","doi-asserted-by":"publisher","first-page":"20190037","DOI":"10.1259\/bjro.20190037","volume":"1","author":"LIT Lee","year":"2019","unstructured":"Lee LIT, Kanthasamy S, Ayyalaraju RS, Ganatra R (2019) The current state of artificial intelligence in medical imaging and nuclear medicine. BJR|Open 1(1):20190037","journal-title":"BJR|Open"},{"key":"5943_CR11","doi-asserted-by":"crossref","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017) ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: IEEE conference on computer vision and pattern recognition. Hawaii, United States, pp 3462\u20133471","DOI":"10.1109\/CVPR.2017.369"},{"key":"5943_CR12","doi-asserted-by":"crossref","unstructured":"Bustos A, Pertusa A, Salinas J, de\u00a0la Iglesia-Vay\u00e1 M (2019) Padchest: a large chest x-ray image dataset with multi-label annotated reports. arXiv:1901.07441","DOI":"10.1016\/j.media.2020.101797"},{"issue":"1","key":"5943_CR13","doi-asserted-by":"publisher","first-page":"317","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, Deng CY, Mark RG, Horng S (2019) MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data 6(1):317","journal-title":"Sci Data"},{"key":"5943_CR14","doi-asserted-by":"crossref","unstructured":"Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, Marklund H, Haghgoo B, Ball, RL, Shpanskaya KS, Seekins J, Mong DA, Halabi SS, Sandberg JK, Jones R, Larson DB, Langlotz CP, Patel BN, Lungren, MP, Ng AY (2019) Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: The thirty-third AAAI conference on artificial intelligence, AAAI 2019, the thirty-first innovative applications of artificial intelligence conference, IAAI 2019, the ninth AAAI symposium on educational advances in artificial intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27\u2013February 1, 2019. AAAI Press, pp 590\u2013597","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"5943_CR15","first-page":"1097","volume-title":"Advances in neural information processing systems","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems. Curran Associates, Inc., Red Hook, pp 1097\u20131105"},{"key":"5943_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"5943_CR17","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5943_CR18","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1007\/978-3-030-13469-3_88","volume-title":"Progress in pattern recognition, image analysis, computer vision, and applications","author":"S G\u00fcndel","year":"2019","unstructured":"G\u00fcndel S, Grbic S, Georgescu B, Liu S, Maier A, Comaniciu D (2019) Learning to recognize abnormalities in chest x-rays with location-aware dense networks. In: Vera-Rodriguez R, Fierrez J, Morales A (eds) Progress in pattern recognition, image analysis, computer vision, and applications. Springer, Berlin, pp 757\u2013765"},{"key":"5943_CR19","unstructured":"Rajpurkar P, Irvin J, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz C, Shpanskaya K, Lungren MP, Ng AY (2017) Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning"},{"issue":"1","key":"5943_CR20","doi-asserted-by":"publisher","first-page":"6381","DOI":"10.1038\/s41598-019-42294-8","volume":"9","author":"IM Baltruschat","year":"2019","unstructured":"Baltruschat IM, Nickisch H, Grass M, Knopp T, Saalbach A (2019) Comparison of deep learning approaches for multi-label chest X-ray classification. Sci Rep 9(1):6381","journal-title":"Sci Rep"},{"key":"5943_CR21","unstructured":"Yao L, Poblenz E, Dagunts D, Covington B, Bernard D, Lyman K (2017) Learning to diagnose from scratch by exploiting dependencies among labels. CoRR. arXiv:1710.10501"},{"key":"5943_CR22","doi-asserted-by":"crossref","unstructured":"Singh S, Ho-Shon K, Karimi S, Hamey L (2018) Modality classification and concept detection in medical images using deep transfer learning. In: 2018 International conference on image and vision computing New Zealand (IVCNZ), pp 1\u20139","DOI":"10.1109\/IVCNZ.2018.8634803"},{"key":"5943_CR23","first-page":"33","volume-title":"Medical image classification using deep learning","author":"W Wang","year":"2020","unstructured":"Wang W, Liang D, Chen Q, Iwamoto Y, Han XH, Zhang Q, Hu H, Lin L, Chen YW (2020) Medical image classification using deep learning. Springer, Berlin, pp 33\u201351"},{"issue":"1","key":"5943_CR24","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1186\/s40537-019-0276-2","volume":"6","author":"SS Yadav","year":"2019","unstructured":"Yadav SS, Jadhav SM (2019) Deep convolutional neural network based medical image classification for disease diagnosis. J Big Data 6(1):113","journal-title":"J Big Data"},{"key":"5943_CR25","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.media.2019.02.010","volume":"54","author":"J Zhang","year":"2019","unstructured":"Zhang J, Xie Y, Wu Q, Xia Y (2019) Medical image classification using synergic deep learning. Med Image Anal 54:10\u201319","journal-title":"Med Image Anal"},{"issue":"1","key":"5943_CR26","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/JBHI.2016.2635663","volume":"21","author":"A Kumar","year":"2017","unstructured":"Kumar A, Kim J, Lyndon D, Fulham M, Feng D (2017) An ensemble of fine-tuned convolutional neural networks for medical image classification. IEEE J Biomed Health Inform 21(1):31\u201340","journal-title":"IEEE J Biomed Health Inform"},{"issue":"5","key":"5943_CR27","doi-asserted-by":"publisher","first-page":"e232","DOI":"10.1016\/S2589-7500(19)30108-6","volume":"1","author":"L Faes","year":"2019","unstructured":"Faes L, Wagner SK, Fu DJ, Liu X, Korot E, Ledsam JR, Back T, Chopra R, Pontikos N, Kern C, Moraes G, Schmid MK, Sim D, Balaskas K, Bachmann LM, Denniston AK, Keane PA (2019) Automated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility study. Lancet Digit Health 1(5):e232\u2013e242","journal-title":"Lancet Digit Health"},{"issue":"6","key":"5943_CR28","doi-asserted-by":"publisher","first-page":"118:1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain MZ, Sohel F, Shiratuddin MF, Laga H (2019) A comprehensive survey of deep learning for image captioning. ACM Comput Surv 51(6):118:1\u2013118:36","journal-title":"ACM Comput Surv"},{"key":"5943_CR29","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer vision\u2014ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences from images. In: Daniilidis K, Maragos P, Paragios N (eds) Computer vision\u2014ECCV 2010. Springer, Berlin, pp 15\u201329"},{"key":"5943_CR30","unstructured":"Li S, Kulkarni G, Berg TL, Berg AC, Choi Y (2011) Composing simple image descriptions using web-scale n-grams. In: Proceedings of the fifteenth conference on computational natural language learning, CoNLL\u201911. Association for Computational Linguistics, USA, pp 220\u2013228"},{"issue":"12","key":"5943_CR31","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni G, Premraj V, Ordonez V, Dhar S, Li S, Choi Y, Berg AC, Berg TL (2013) Babytalk: understanding and generating simple image descriptions. IEEE Trans Pattern Anal Mach Intell 35(12):2891\u20132903","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"5943_CR32","first-page":"853","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: data, models and evaluation metrics. J Artif Int Res 47(1):853\u2013899","journal-title":"J Artif Int Res"},{"key":"5943_CR33","doi-asserted-by":"crossref","unstructured":"Mason R, Charniak E (2014) Nonparametric method for data-driven image captioning. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 2: short papers). Association for Computational Linguistics, Baltimore, pp 592\u2013598","DOI":"10.3115\/v1\/P14-2097"},{"key":"5943_CR34","first-page":"1143","volume-title":"Advances in neural information processing systems","author":"V Ordonez","year":"2011","unstructured":"Ordonez V, Kulkarni G, Berg TL (2011) Im2text: describing images using 1 million captioned photographs. In: Shawe-Taylor J, Zemel RS, Bartlett PL, Pereira F, Weinberger KQ (eds) Advances in neural information processing systems, vol 24. Curran Associates, Inc, Red Hook, pp 1143\u20131151"},{"key":"5943_CR35","doi-asserted-by":"crossref","unstructured":"Mason R, Charniak E (2014) Nonparametric method for data-driven image captioning. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 2: short papers). Association for Computational Linguistics, pp 592\u2013598","DOI":"10.3115\/v1\/P14-2097"},{"key":"5943_CR36","unstructured":"Kiros R, Salakhutdinov R, Zemel R (2014) Multimodal neural language models. In: Xing EP, Jebara T (eds) Proceedings of the 31st international conference on machine learning, proceedings of machine learning research, vol 32. PMLR, Bejing, China, pp 595\u2013603"},{"issue":"4","key":"5943_CR37","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2017","unstructured":"Karpathy A, Fei-Fei L (2017) Deep visual-semantic alignments for generating image descriptions. IEEE Trans Pattern Anal Mach Intell 39(4):664\u2013676","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5943_CR38","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: Bach F, Blei D (eds) Proceedings of the 32nd international conference on machine learning, proceedings of machine learning research, vol 37. PMLR, Lille, France, pp 2048\u20132057"},{"key":"5943_CR39","doi-asserted-by":"crossref","unstructured":"Liu C, Mao J, Sha F, Yuille A (2017) Attention correctness in neural image captioning. In: Proceedings of the thirty-first AAAI conference on artificial intelligence, AAAI\u201917. AAAI Press, pp 4176\u20134182","DOI":"10.1609\/aaai.v31i1.11197"},{"key":"5943_CR40","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 4651\u20134659","DOI":"10.1109\/CVPR.2016.503"},{"key":"5943_CR41","doi-asserted-by":"crossref","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","DOI":"10.1109\/CVPR.2018.00636"},{"key":"5943_CR42","doi-asserted-by":"crossref","unstructured":"Krause J, Johnson J, Krishna R, Fei-Fei L (2017) A hierarchical approach for generating descriptive image paragraphs. In: 2017 IEEE conference on computer vision and pattern recognition, pp 3337\u20133345","DOI":"10.1109\/CVPR.2017.356"},{"key":"5943_CR43","doi-asserted-by":"crossref","unstructured":"Johnson J, Karpathy A, Fei-Fei L (2016) DenseCap: fully Convolutional Localization Networks for Dense Captioning. In: 2016 IEEE conference on computer vision and pattern recognition, pp 4565\u20134574","DOI":"10.1109\/CVPR.2016.494"},{"key":"5943_CR44","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\u2014MICCAI 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\u2014MICCAI 2018. Springer, Berlin, pp 457\u2013466"},{"key":"5943_CR45","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/978-3-030-32692-0_77","volume-title":"Machine learning in medical imaging","author":"Y Xiong","year":"2019","unstructured":"Xiong Y, Du B, Yan P (2019) Reinforced transformer for medical image captioning. In: Suk HI, Liu M, Yan P, Lian C (eds) Machine learning in medical imaging. Springer, Berlin, pp 673\u2013680"},{"key":"5943_CR46","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/978-3-319-19992-4_34","volume-title":"Information processing in medical imaging","author":"T Schlegl","year":"2015","unstructured":"Schlegl T, Waldstein SM, Vogl WD, Schmidt-Erfurth U, Langs G (2015) Predicting semantic descriptions from medical images with convolutional neural networks. In: Ourselin S, Alexander DC, Westin CF, Cardoso MJ (eds) Information processing in medical imaging. Springer, Cham, pp 437\u2013448"},{"issue":"107","key":"5943_CR47","first-page":"1","volume":"17","author":"HC Shin","year":"2016","unstructured":"Shin HC, Lu L, Kim L, Seff A, Yao J, Summers RM (2016) Interleaved text\/image deep mining on a large-scale radiology database for automated image interpretation. J Mach Learn Res 17(107):1\u201331","journal-title":"J Mach Learn Res"},{"key":"5943_CR48","doi-asserted-by":"publisher","unstructured":"Shin H, 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":"5943_CR49","doi-asserted-by":"crossref","unstructured":"Zhang Z, Xie Y, Xing F, McGough M, Yang L (2017) MDNet: a Semantically and Visually interpretable medical image diagnosis network. In: IEEE conference on computer vision and pattern recognition, Hawaii, United States, pp 3549\u20133557","DOI":"10.1109\/CVPR.2017.378"},{"key":"5943_CR50","first-page":"1530","volume-title":"Advances in neural information processing systems","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. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in neural information processing systems, vol 31. Curran Associates, Inc, Red Hook, pp 1530\u20131540"},{"issue":"5","key":"5943_CR51","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1007\/s11390-018-1874-8","volume":"33","author":"XH Zeng","year":"2018","unstructured":"Zeng XH, Liu BG, Zhou M (2018) Understanding and generating ultrasound image description. J Comput Sci Technol 33(5):1086\u20131100","journal-title":"J Comput Sci Technol"},{"issue":"4","key":"5943_CR52","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1162\/089120102762671927","volume":"28","author":"DR Radev","year":"2002","unstructured":"Radev DR, Hovy E, McKeown K (2002) Introduction to the special issue on summarization. Comput Linguist 28(4):399\u2013408","journal-title":"Comput Linguist"},{"issue":"C","key":"5943_CR53","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.jbi.2014.06.009","volume":"52","author":"R Mishra","year":"2014","unstructured":"Mishra R, Bian J, Fiszman M, Weir CR, Jonnalagadda S, Mostafa J, Del Fiol G (2014) Text summarization in the biomedical domain. J Biomed Inform 52(C):457\u2013467","journal-title":"J Biomed Inform"},{"key":"5943_CR54","doi-asserted-by":"crossref","unstructured":"Neto JL, Freitas AA, Kaestner CAA (2002) Automatic text summarization using a machine learning approach. In: Proceedings of the 16th Brazilian symposium on artificial intelligence: advances in artificial intelligence, SBIA\u201902. Springer, Berlin, pp 205\u2013215","DOI":"10.1007\/3-540-36127-8_20"},{"key":"5943_CR55","unstructured":"Filippova K, Altun Y (2013) Overcoming the lack of parallel data in sentence compression. In: Proceedings of the 2013 conference on empirical methods in natural language processing. Association for Computational Linguistics, Seattle, Washington, USA, pp 1481\u20131491"},{"key":"5943_CR56","doi-asserted-by":"crossref","unstructured":"Colmenares CA, Litvak M, Mantrach A, Silvestri F (2015) HEADS: Headline generation as sequence prediction using an abstract feature-rich space. In: Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies. Association for Computational Linguistics, Denver, Colorado, pp 133\u2013142","DOI":"10.3115\/v1\/N15-1014"},{"key":"5943_CR57","doi-asserted-by":"crossref","unstructured":"Kryscinski W, Keskar NS, McCann B, Xiong C, Socher R (2019) Neural text summarization: a critical evaluation. 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). Association for Computational Linguistics, Hong Kong, China, pp 540\u2013551","DOI":"10.18653\/v1\/D19-1051"},{"key":"5943_CR58","doi-asserted-by":"crossref","unstructured":"See A, Liu PJ, Manning CD (2017) Get to the point: summarization with pointer-generator networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (volume 1: long papers). Association for Computational Linguistics, Vancouver, Canada, pp 1073\u20131083","DOI":"10.18653\/v1\/P17-1099"},{"key":"5943_CR59","doi-asserted-by":"crossref","unstructured":"Tan J, Wan X, Xiao J (2017) Abstractive document summarization with a graph-based attentional neural model. In: Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics, Vancouver, Canada, pp 1171\u20131181","DOI":"10.18653\/v1\/P17-1108"},{"key":"5943_CR60","doi-asserted-by":"crossref","unstructured":"Cohan A, Dernoncourt F, Kim DS, Bui T, Kim S, Chang W, Goharian N (2018) A discourse-aware attention model for abstractive summarization of long documents. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 2 (short papers). Association for Computational Linguistics, New Orleans, Louisiana, pp 615\u2013621","DOI":"10.18653\/v1\/N18-2097"},{"key":"5943_CR61","doi-asserted-by":"crossref","unstructured":"Hsu WT, Lin CK, Lee MY, Min K, Tang J, Sun M (2018) A unified model for extractive and abstractive summarization using inconsistency loss. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics, Melbourne, Australia, pp 132\u2013141","DOI":"10.18653\/v1\/P18-1013"},{"key":"5943_CR62","doi-asserted-by":"crossref","unstructured":"Liu L, Tang J, Wan X, Guo Z (2019) Generating diverse and descriptive image captions using visual paraphrases. In: 2019 IEEE\/CVF international conference on computer vision (ICCV), pp 4239\u20134248","DOI":"10.1109\/ICCV.2019.00434"},{"key":"5943_CR63","doi-asserted-by":"crossref","unstructured":"Gehrmann S, Deng Y, Rush A (2018) Bottom-up abstractive summarization. In: Proceedings of the 2018 conference on empirical methods in natural language processing. Association for Computational Linguistics, Brussels, Belgium, pp 4098\u20134109","DOI":"10.18653\/v1\/D18-1443"},{"key":"5943_CR64","doi-asserted-by":"crossref","unstructured":"Chen YC, Bansal M (2018) Fast abstractive summarization with reinforce-selected sentence rewriting. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: long papers). Association for Computational Linguistics, Melbourne, Australia, pp 675\u2013686","DOI":"10.18653\/v1\/P18-1063"},{"key":"5943_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2019.12.022","volume":"124","author":"DS Moirangthem","year":"2020","unstructured":"Moirangthem DS, Lee M (2020) Abstractive summarization of long texts by representing multiple compositionalities with temporal hierarchical pointer generator network. Neural Netw 124:1\u201311","journal-title":"Neural Netw"},{"key":"5943_CR66","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L, Kai L, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5943_CR67","doi-asserted-by":"crossref","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, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"5943_CR68","doi-asserted-by":"crossref","unstructured":"Zhang Y, Ding DY, Qian T, Manning CD, Langlotz CP (2018) Learning to summarize radiology findings. In: Proceedings of the ninth international workshop on health text mining and information analysis. Association for Computational Linguistics, Brussels, Belgium, pp 204\u2013213","DOI":"10.18653\/v1\/W18-5623"},{"key":"5943_CR69","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: 3rd International conference on learning representations, ICLR 2015; Conference date: 07-05-2015 Through 09-05-2015"},{"key":"5943_CR70","doi-asserted-by":"crossref","unstructured":"Razavian AS, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: 2014 IEEE conference on computer vision and pattern recognition workshops, pp 512\u2013519","DOI":"10.1109\/CVPRW.2014.131"},{"key":"5943_CR71","first-page":"3347","volume-title":"Advances in neural information processing systems","author":"M Raghu","year":"2019","unstructured":"Raghu M, Zhang C, Kleinberg J, Bengio S (2019) Transfusion: understanding transfer learning for medical imaging. In: Wallach H, Larochelle H, Beygelzimer A, AlcheBuc F, Fox E, Garnett R (eds) Advances in neural information processing systems, vol 32. Curran Associates, Inc, Red Hook, pp 3347\u20133357"},{"key":"5943_CR72","doi-asserted-by":"crossref","unstructured":"Singh S, Karimi S, Ho-Shon K, Hamey L (2019) From chest x-rays to radiology reports: a multimodal machine learning approach. In: 2019 digital image computing: techniques and applications (DICTA), pp 1\u20138","DOI":"10.1109\/DICTA47822.2019.8945819"},{"key":"5943_CR73","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. Philadelphia, Pennsylvania, United States","DOI":"10.3115\/1073083.1073135"},{"key":"5943_CR74","unstructured":"Lin CY (2004) ROUGE: a package for automatic evaluation of summaries. In: 42nd Annual meeting of the association for computational linguistics. Barcelona, Spain, pp 1\u20138"},{"key":"5943_CR75","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. Ann Arbor, Michigan, United States, pp 65\u201372"},{"key":"5943_CR76","doi-asserted-by":"crossref","unstructured":"Vedantam R, Zitnick CL, Parikh D (2015) CIDEr: consensus-based image description evaluation. In: IEEE conference on computer vision and pattern recognition. Boston, Massachusetts, United States, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"5943_CR77","unstructured":"Chen X, Hao\u00a0Fang TYL, Vedantam R, Gupta S, Doll\u00e1r P, Zitnick CL (2015) Microsoft COCO captions: data collection and evaluation server. arXiv:1504.00325"},{"key":"5943_CR78","unstructured":"Chollet F et al (2015) Keras. https:\/\/github.com\/fchollet\/keras"},{"key":"5943_CR79","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M et\u00a0al (2016) Tensorflow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX conference on operating systems design and implementation, OSDI\u201916. USENIX Association, USA, pp 265\u2013283"},{"key":"5943_CR80","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Bengio Y, LeCun Y (eds) 3rd International conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings"},{"key":"5943_CR81","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) GloVe: global Vectors for word representation. In: Empirical methods in natural language processing. Doha, Qatar, pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"5943_CR82","unstructured":"Johnson AEW, Pollard TJ, Greenbaum NR, Lungren MP, Deng CY, Peng Y, Lu Z, Mark RG, Berkowitz SJ, Horng S (2019) MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs"},{"key":"5943_CR83","doi-asserted-by":"crossref","unstructured":"Lindh A, Ross RJ, Mahalunkar A, Salton G, Kelleher JD (2018) Generating diverse and meaningful captions. In: K\u016frkov\u00e1 V, Manolopoulos Y, Hammer B, Iliadis L, Maglogiannis I (eds) Artificial neural networks and machine learning\u2014ICANN 2018. Springer, Cham, pp 176\u2013187","DOI":"10.1007\/978-3-030-01418-6_18"},{"key":"5943_CR84","doi-asserted-by":"crossref","unstructured":"Deshpande A, Aneja J, Wang L, Schwing AG, Forsyth D (2019) Fast, diverse and accurate image captioning guided by part-of-speech. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10687\u201310696","DOI":"10.1109\/CVPR.2019.01095"},{"key":"5943_CR85","doi-asserted-by":"crossref","unstructured":"Peters M, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. In: Proceedings of the 2018 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long papers). Association for Computational Linguistics, New Orleans, Louisiana, pp 2227\u20132237","DOI":"10.18653\/v1\/N18-1202"},{"key":"5943_CR86","first-page":"5998","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, Kaiser Lu, Polosukhin I (2017) 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, pp 5998\u20136008"},{"key":"5943_CR87","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). Association for Computational Linguistics, Minneapolis, Minnesota, pp 4171\u20134186"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05943-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05943-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05943-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T11:57:37Z","timestamp":1671796657000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-05943-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,5]]},"references-count":87,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["5943"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-05943-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,5]]},"assertion":[{"value":"18 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2021","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"}}]}}