{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:08:38Z","timestamp":1766732918335,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819980758"},{"type":"electronic","value":"9789819980765"}],"license":[{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8076-5_5","type":"book-chapter","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:02:10Z","timestamp":1699884130000},"page":"57-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["IIHT: Medical Report Generation with\u00a0Image-to-Indicator Hierarchical Transformer"],"prefix":"10.1007","author":[{"given":"Keqiang","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohao","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahesan","family":"Niranjan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,14]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","key":"5_CR1","DOI":"10.1109\/CVPR.2018.00636"},{"doi-asserted-by":"publisher","unstructured":"Chen, Z., Shen, Y., Song, Y., Wan, X.: 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), pp. 5904\u20135914. Association for Computational Linguistics, August 2021. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.459. https:\/\/aclanthology.org\/2021.acl-long.459","key":"5_CR2","DOI":"10.18653\/v1\/2021.acl-long.459"},{"doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.H., Wan, X.: Generating radiology reports via memory-driven transformer. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, November 2020","key":"5_CR3","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"issue":"2","key":"5_CR4","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D., et al.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23(2), 304\u2013310 (2016)","journal-title":"J. Am. Med. Inform. Assoc."},{"doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","key":"5_CR5","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the 9th Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","key":"5_CR6","DOI":"10.3115\/v1\/W14-3348"},{"unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)","key":"5_CR7"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"5_CR8","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","key":"5_CR9","DOI":"10.1109\/ICCV.2019.00473"},{"doi-asserted-by":"publisher","unstructured":"Jing, B., Wang, Z., Xing, E.: 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, July 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1657. https:\/\/aclanthology.org\/P19-1657","key":"5_CR10","DOI":"10.18653\/v1\/P19-1657"},{"doi-asserted-by":"publisher","unstructured":"Jing, B., Xie, P., Xing, E.: 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), pp. 2577\u20132586. Association for Computational Linguistics, Melbourne, Australia, July 2018. https:\/\/doi.org\/10.18653\/v1\/P18-1240. https:\/\/aclanthology.org\/P18-1240","key":"5_CR11","DOI":"10.18653\/v1\/P18-1240"},{"doi-asserted-by":"publisher","unstructured":"Kudo, T., Richardson, J.: SentencePiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 66\u201371. Association for Computational Linguistics, Brussels, Belgium, November 2018. https:\/\/doi.org\/10.18653\/v1\/D18-2012. https:\/\/aclanthology.org\/D18-2012","key":"5_CR12","DOI":"10.18653\/v1\/D18-2012"},{"doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, L., Liu, P., Yang, Y.: Entangled transformer for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8928\u20138937 (2019)","key":"5_CR13","DOI":"10.1109\/ICCV.2019.00902"},{"unstructured":"Li, Y., Liang, X., Hu, Z., Xing, E.P.: Hybrid retrieval-generation reinforced agent for medical image report generation. In: Advances in Neural Information Processing Systems, vol. 31 (2018)","key":"5_CR14"},{"doi-asserted-by":"crossref","unstructured":"Liang, X., Hu, Z., Zhang, H., Gan, C., Xing, E.P.: Recurrent topic-transition GAN for visual paragraph generation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3362\u20133371 (2017)","key":"5_CR15","DOI":"10.1109\/ICCV.2017.364"},{"unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)","key":"5_CR16"},{"doi-asserted-by":"publisher","unstructured":"Liu, F., Ge, S., Wu, X.: 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), pp. 3001\u20133012. Association for Computational Linguistics, August 2021. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.234. https:\/\/aclanthology.org\/2021.acl-long.234","key":"5_CR17","DOI":"10.18653\/v1\/2021.acl-long.234"},{"doi-asserted-by":"publisher","unstructured":"Liu, F., Ren, X., Liu, Y., Wang, H., Sun, X.: simNet: stepwise image-topic merging network for generating detailed and comprehensive image captions. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 137\u2013149. Association for Computational Linguistics, Brussels, Belgium, October\u2013November 2018. https:\/\/doi.org\/10.18653\/v1\/D18-1013. https:\/\/aclanthology.org\/D18-1013","key":"5_CR18","DOI":"10.18653\/v1\/D18-1013"},{"unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)","key":"5_CR19"},{"key":"5_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/978-3-030-87199-4_59","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"I Najdenkoska","year":"2021","unstructured":"Najdenkoska, I., Zhen, X., Worring, M., Shao, L.: Variational topic inference for chest X-ray report generation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 625\u2013635. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87199-4_59"},{"doi-asserted-by":"crossref","unstructured":"Nguyen, H.T., et al.: Eddie-transformer: enriched disease embedding transformer for X-ray report generation. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp. 1\u20135. IEEE (2022)","key":"5_CR21","DOI":"10.1109\/ISBI52829.2022.9761459"},{"doi-asserted-by":"crossref","unstructured":"European Society of Radiology (ESR) communications@myesr.org: Medical imaging in personalised medicine: a white paper of the research committee of the European society of radiology (ESR). Insights Imag. 6, 141\u2013155 (2015)","key":"5_CR22","DOI":"10.1007\/s13244-015-0394-0"},{"doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: 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 (2002)","key":"5_CR23","DOI":"10.3115\/1073083.1073135"},{"doi-asserted-by":"crossref","unstructured":"Shin, H.C., Roberts, K., Lu, L., Demner-Fushman, D., Yao, J., Summers, R.M.: Learning to read chest x-rays: recurrent neural cascade model for automated image annotation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2497\u20132506 (2016)","key":"5_CR24","DOI":"10.1109\/CVPR.2016.274"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"5_CR25"},{"doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","key":"5_CR26","DOI":"10.1109\/CVPR.2015.7298935"},{"unstructured":"Wang, S., Tang, L., Lin, M., Shih, G., Ding, Y., Peng, Y.: Prior knowledge enhances radiology report generation. In: AMIA Annual Symposium Proceedings, vol. 2022, p. 486. American Medical Informatics Association (2022)","key":"5_CR27"},{"doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Summers, R.M.: TieNet: text-image embedding network for common thorax disease classification and reporting in chest X-rays. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9049\u20139058 (2018)","key":"5_CR28","DOI":"10.1109\/CVPR.2018.00943"},{"unstructured":"Wu, X., et al.: DeltaNet: conditional medical report generation for COVID-19 diagnosis. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 2952\u20132961. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, October 2022. https:\/\/aclanthology.org\/2022.coling-1.261","key":"5_CR29"},{"doi-asserted-by":"crossref","unstructured":"Yin, C., et al.: Automatic generation of medical imaging diagnostic report with hierarchical recurrent neural network. In: 2019 IEEE International Conference on Data Mining (ICDM), pp. 728\u2013737. IEEE (2019)","key":"5_CR30","DOI":"10.1109\/ICDM.2019.00083"},{"doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","key":"5_CR31","DOI":"10.1109\/CVPR.2016.503"},{"doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8739\u20138748 (2018)","key":"5_CR32","DOI":"10.1109\/CVPR.2018.00911"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8076-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:13:41Z","timestamp":1710256421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8076-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,14]]},"ISBN":["9789819980758","9789819980765"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8076-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,14]]},"assertion":[{"value":"14 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"650","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.14","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.46","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}