{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:49:36Z","timestamp":1772909376792,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500321","type":"print"},{"value":"9789819500338","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-95-0033-8_8","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T08:01:36Z","timestamp":1753344096000},"page":"89-99","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Modality and Multi-Grained Transformer for Accurate Radiology Report Generation"],"prefix":"10.1007","author":[{"given":"Hongzhao","family":"Li","sequence":"first","affiliation":[]},{"given":"Liangzhi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiangrong","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Jingpu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shuo","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Shupan","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"8_CR1","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)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"8_CR2","unstructured":"Banerjee, S., Lavie, A.: Meteor: An automatic metric for mt evaluation with im- proved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"8_CR3","doi-asserted-by":"publisher","unstructured":"Cai, C., Wang, S., Yap, K.H., Wang, Y.: Top-down framework for weakly- supervised grounded image captioning. Knowl.-Based Syst. 287, 111433 (2024). https:\/\/doi.org\/10.1016\/j.knosys.2024.111433","DOI":"10.1016\/j.knosys.2024.111433"},{"key":"8_CR4","doi-asserted-by":"crossref","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 (2021)","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"8_CR5","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 (EMNLP), pp. 1439\u20131449 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"8_CR6","unstructured":"Chu, C., Zhmoginov, A., Sandler, M.: CycleGAN, a master of steganography. arXiv preprint arXiv:1712.02950 (2017)"},{"issue":"2","key":"8_CR7","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. Inf. Assoc. 23(2), 304\u2013310 (2016)","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, W., Ma, L., Jiang, Y.G., Liu, W., Zhang, T.: Recurrent fusion network for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 499\u2013515 (2018)","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Jin, H., Che, H., Lin, Y., Chen, H.: PromptMRG: diagnosis-driven prompts for medical report generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 2607\u20132615 (2024)","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"8_CR11","unstructured":"Jing, B., Xie, P., Xing, E.: On the automatic generation of medical imaging reports. arXiv preprint arXiv:1711.08195 (2017)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"8_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127419","volume":"279","author":"H Li","year":"2025","unstructured":"Li, H., et al.: RRGMambaFormer: a hybrid transformer-mamba architecture for radiology report generation. Expert Syst. Appl. 279, 127419 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.127419","journal-title":"Expert Syst. Appl."},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, H., Sun, X., He, H., Feng, J.: Prompt-guided generation of structured chest X-ray report using a pre-trained LLM. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2024). 10.1109\/ ICME57554.2024.10687707","DOI":"10.1109\/ICME57554.2024.10687707"},{"key":"8_CR15","doi-asserted-by":"publisher","unstructured":"Li, H., Wang, H., Sun, X., He, H., Feng, J.: Context-enhanced framework for medical image report generation using multimodal contexts. Knowl.-Based Syst. 310, 112913 (2025). https:\/\/doi.org\/10.1016\/j.knosys.2024.112913","DOI":"10.1016\/j.knosys.2024.112913"},{"key":"8_CR16","unstructured":"Li, Y., Liang, X., Hu, Z., Xing, E.P.: Hybrid retrieval-generation reinforced agent for medical image report generation. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Liang, C., Wang, W., Zhou, T., Yang, Y.: Visual abductive reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15565\u201315575 (2022)","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"8_CR18","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"8_CR19","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. arXiv preprint arXiv:1808.08732 (2018)","DOI":"10.18653\/v1\/D18-1013"},{"key":"8_CR20","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: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13753\u201313762 (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"8_CR21","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"8_CR22","doi-asserted-by":"publisher","unstructured":"Ma, Y., et al.: Style-aware two-stage learning framework for video captioning. Knowl.-Based Syst. 301, 112258 (2024). https:\/\/doi.org\/10.1016\/j.knosys.2024.112258","DOI":"10.1016\/j.knosys.2024.112258"},{"key":"8_CR23","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)","DOI":"10.3115\/1073083.1073135"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Reale-Nosei, G., Amador-Dom\u00ednguez, E., Serrano, E.: From vision to text: a comprehensive review of natural image captioning in medical diagnosis and radiology report generation. Med. Image Anal., 103264 (2024)","DOI":"10.1016\/j.media.2024.103264"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"issue":"2","key":"8_CR26","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1038\/s41591-024-03302-1","volume":"31","author":"R Tanno","year":"2025","unstructured":"Tanno, R., et al.: Collaboration between clinicians and vision \u2013 language models in radiology report generation. Nat. Med. 31(2), 599\u2013608 (2025)","journal-title":"Nat. Med."},{"key":"8_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"8_CR28","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)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"8_CR29","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, S.K., Xiao, L.: Knowledge matters: chest radiology report generation with general and specific knowledge. Med. Image Anal. 80, 102510 (2022)","journal-title":"Med. Image Anal."},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Yi, X., Fu, Y., Liu, R., Zhang, H., Hua, R.: TSGET: two-stage global enhanced transformer for automatic radiology report generation. IEEE J. Biomed. Health Inf. (2024)","DOI":"10.1109\/JBHI.2024.3350077"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0033-8_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T22:58:59Z","timestamp":1757285939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0033-8_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500321","9789819500338"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0033-8_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}