{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:44:53Z","timestamp":1775324693242,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030871987","type":"print"},{"value":"9783030871994","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87199-4_7","type":"book-chapter","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T06:19:41Z","timestamp":1632377981000},"page":"72-82","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":103,"title":["AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation"],"prefix":"10.1007","author":[{"given":"Di","family":"You","sequence":"first","affiliation":[]},{"given":"Fenglin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shen","family":"Ge","sequence":"additional","affiliation":[]},{"given":"Xiaoxia","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xian","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"7_CR2","unstructured":"Ba, L.J., Kiros, R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"7_CR3","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: IEEvaluation@ACL (2005)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Biswal, S., Xiao, C., Glass, L., Westover, M.B., Sun, J.: CLARA: clinical report auto-completion. In: WWW (2020)","DOI":"10.1145\/3366423.3380137"},{"key":"7_CR5","first-page":"3","volume":"81","author":"A Brady","year":"2012","unstructured":"Brady, A., Laoide, R.\u00d3., Mccarthy, P., Mcdermott, R.: Discrepancy and error in radiology: concepts, causes and consequences. Ulster Med. J. 81, 3\u20139 (2012)","journal-title":"Ulster Med. J."},{"key":"7_CR6","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T., Wan, X.: Generating radiology reports via memory-driven transformer. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"7_CR9","series-title":"Medical Radiology","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-3-540-79942-9_2","volume-title":"Comparative Interpretation of CT and Standard Radiography of the Chest","author":"L Delrue","year":"2011","unstructured":"Delrue, L., Gosselin, R., Ilsen, B., Van Landeghem, A., de Mey, J., Duyck, P.: Difficulties in the interpretation of chest radiography. In: Coche, E., Ghaye, B., de Mey, J., Duyck, P. (eds.) Comparative Interpretation of CT and Standard Radiography of the Chest. Medical Radiology, pp. 27\u201349. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-540-79942-9_2"},{"issue":"2","key":"7_CR10","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."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"7_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/1754-9485.12014","volume":"57","author":"SK Goergen","year":"2013","unstructured":"Goergen, S.K., et al.: Evidence-based guideline for the written radiology report: methods, recommendations and implementation challenges. J. Med. Imaging Radiat. Oncol. 57(1), 1\u20137 (2013)","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"7_CR14","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Jing, B., Wang, Z., Xing, E.P.: Show, describe and conclude: on exploiting the structure information of chest X-ray reports. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1657"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Jing, B., Xie, P., Xing, E.P.: On the automatic generation of medical imaging reports. In: ACL (2018)","DOI":"10.18653\/v1\/P18-1240"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Johnson, A.E.W., et al.: MIMIC-CXR: a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"7_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Krause, J., Johnson, J., Krishna, R., Fei-Fei, L.: A hierarchical approach for generating descriptive image paragraphs. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.356"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Li, C.Y., Liang, X., Hu, Z., Xing, E.P.: Knowledge-driven encode, retrieve, paraphrase for medical image report generation. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"7_CR22","unstructured":"Li, Y., Liang, X., Hu, Z., Xing, E.P.: Hybrid retrieval-generation reinforced agent for medical image report generation. In: NeurIPS (2018)"},{"key":"7_CR23","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: ACL (2004)"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Liu, F., Ge, S., Wu, X.: Competence-based multimodal curriculum learning for medical report generation. In: ACL (2021)","DOI":"10.18653\/v1\/2021.acl-long.234"},{"key":"7_CR25","unstructured":"Liu, F., Liu, Y., Ren, X., He, X., Sun, X.: Aligning visual regions and textual concepts for semantic-grounded image representations. In: NeurIPS (2019)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Liu, F., Ren, X., Liu, Y., Lei, K., Sun, X.: Exploring and distilling cross-modal information for image captioning. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/708"},{"key":"7_CR27","doi-asserted-by":"crossref","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: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1013"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, X., Ge, S., Fan, W., Zou, Y.: Exploring and distilling posterior and prior knowledge for radiology report generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Liu, F., Yin, C., Wu, X., Ge, S., Zhang, P., Sun, X.: Contrastive attention for automatic chest X-ray report generation. In: ACL (Findings) (2021)","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"7_CR30","unstructured":"Liu, G., et al.: Clinically accurate chest X-ray report generation. In: MLHC (2019)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: a method for automatic evaluation of machine translation. In: ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"7_CR34","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: ICML (2013)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Shin, H., 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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.274"},{"key":"7_CR37","first-page":"1929","volume":"5","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 5, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-030-59713-9_54","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"T Syeda-Mahmood","year":"2020","unstructured":"Syeda-Mahmood, T., et al.: Chest X-ray report generation through fine-grained label learning. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 561\u2013571. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59713-9_54"},{"key":"7_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"7_CR41","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"7_CR42","series-title":"Lecture Notes in Computer Science","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 \u2013 MICCAI 2018","author":"Y Xue","year":"2018","unstructured":"Xue, Y., et al.: Multimodal recurrent model with attention for automated radiology report generation. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 457\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00928-1_52"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"7_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/978-3-030-32226-7_80","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"J Yuan","year":"2019","unstructured":"Yuan, J., Liao, H., Luo, R., Luo, J.: Automatic radiology report generation based on multi-view image fusion and medical concept enrichment. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 721\u2013729. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32226-7_80"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A.L., Xu, D.: When radiology report generation meets knowledge graph. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6989"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87199-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:31:19Z","timestamp":1673310679000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87199-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030871987","9783030871994"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87199-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccai2021.org\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1622","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":"531","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":"33% - 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":"3","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":"4","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}