{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:08Z","timestamp":1781538848416,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"the Open Fund of Nansha Islands Coral Reef Ecosystem National Observation and Research Station","award":["NO.NSICR25101"],"award-info":[{"award-number":["NO.NSICR25101"]}]},{"name":"the Ministry of Education Humanities and Social Science Research Planning Fund Project","award":["23YJAZ-H079"],"award-info":[{"award-number":["23YJAZ-H079"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810644","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2477-2485","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MMG-RAG: Multimodal Graph RAG for Medical Report Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7032-8429","authenticated-orcid":false,"given":"Gang","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China and Nansha Islands Coral Reef Ecosystem National Observation and Research Station, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0648-6434","authenticated-orcid":false,"given":"Xiaotian","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9905-3229","authenticated-orcid":false,"given":"Jiacheng","family":"Gan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7215-3129","authenticated-orcid":false,"given":"Tianyu","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0604-4918","authenticated-orcid":false,"given":"Tingyao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6542-649X","authenticated-orcid":false,"given":"Shenjun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Monash Biomedical Imaging, Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"Introducing Claude 4","year":"2025","unstructured":"Anthropic. 2025. Introducing Claude 4. Retrieved October 27, 2025 from https:\/\/www.anthropic.com\/news\/claude-4"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.19538"},{"key":"e_1_3_3_1_4_2","first-page":"85","volume-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation","author":"Denkowski Michael","year":"2011","unstructured":"Michael Denkowski and Alon Lavie. 2011. METEOR 1.3: Automatic Metric for Reliable Optimization and Evaluation of Machine Translation Systems. In Proceedings of the Sixth Workshop on Statistical Machine Translation. Association for Computational Linguistics, Edinburgh, Scotland, 85\u201391. https:\/\/aclanthology.org\/W11-2107\/"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Patrick Ernst Amy Siu and Gerhard Weikum. 2015. KnowLife: A Versatile Approach for Constructing a Large Knowledge Graph for Biomedical Sciences. BMC Bioinformatics 16 1 (May 2015) 157. 10.1186\/s12859-015-0549-5","DOI":"10.1186\/s12859-015-0549-5"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Samuel\u00a0G Finlayson Paea LePendu and Nigam\u00a0H Shah. 2014. Building the graph of medicine from millions of clinical narratives. Scientific Data 1 1 (Sept. 2014) 1\u20139. 10.1038\/sdata.2014.32","DOI":"10.1038\/sdata.2014.32"},{"key":"e_1_3_3_1_7_2","volume-title":"Gemini 2.5 Flash","year":"2025","unstructured":"Google. 2025. Gemini 2.5 Flash. Retrieved October 27, 2025 from https:\/\/ai.google.dev\/gemini-api\/docs\/models\/gemini-2.5-flash"},{"key":"e_1_3_3_1_8_2","first-page":"8546","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Huang Xiyang","year":"2025","unstructured":"Xiyang Huang, Yingjie Han, Yaoxu Li, Runzhi Li, Pengcheng Wu, and Kunli Zhang. 2025. CmEAA: Cross-modal Enhancement and Alignment Adapter for Radiology Report Generation. In Proceedings of the 31st International Conference on Computational Linguistics. Association for Computational Linguistics, Abu Dhabi, UAE, 8546\u20138556. https:\/\/aclanthology.org\/2025.coling-main.571\/"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Alistair\u00a0EW Johnson Tom\u00a0J Pollard Seth\u00a0J Berkowitz Nathaniel\u00a0R Greenbaum Matthew\u00a0P Lungren Chih-ying Deng Roger\u00a0G Mark and Steven Horng. 2019. MIMIC-CXR a de-identified publicly available database of chest radiographs with free-text reports. Scientific Data 6 1 (2019) 317. 10.1038\/s41597-019-0322-0","DOI":"10.1038\/s41597-019-0322-0"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2511.06738"},{"key":"e_1_3_3_1_13_2","first-page":"9459","volume-title":"Advances in Neural Information Processing Systems","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et\u00a0al. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems , Vol.\u00a033. 9459\u20139474. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Linfeng Li Peng Wang Jun Yan Yao Wang Simin Li Jinpeng Jiang Zhe Sun Buzhou Tang Tsung-Hui Chang Shenghui Wang et\u00a0al. 2020. Real-world data medical knowledge graph: construction and applications. Artificial Intelligence in Medicine 103 (Feb. 2020) 101817. 10.1016\/j.artmed.2020.101817","DOI":"10.1016\/j.artmed.2020.101817"},{"key":"e_1_3_3_1_15_2","first-page":"74","volume-title":"Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74\u201381. https:\/\/aclanthology.org\/W04-1013\/"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29826"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00968"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Aaron Nicolson Jason Dowling and Bevan Koopman. 2023. Improving Chest X-ray Report Generation by Leveraging Warm Starting. Artificial Intelligence in Medicine 144 (Oct. 2023) 102633. 10.1016\/j.artmed.2023.102633","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"e_1_3_3_1_19_2","volume-title":"Introducing GPT-4.1 in the API","year":"2025","unstructured":"OpenAI. 2025. Introducing GPT-4.1 in the API. Retrieved October 27, 2025 from https:\/\/openai.com\/index\/gpt-4-1\/"},{"key":"e_1_3_3_1_20_2","volume-title":"Introducing GPT-5","year":"2025","unstructured":"OpenAI. 2025. Introducing GPT-5. Retrieved October 26, 2025 from https:\/\/openai.com\/index\/introducing-gpt-5\/"},{"key":"e_1_3_3_1_21_2","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, 311\u2013318. https:\/\/aclanthology.org\/P02-1040\/"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/AIxSET62544.2024.00030"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","unstructured":"Maya Rotmensch Yoni Halpern Abdulhakim Tlimat Steven Horng and David Sontag. 2017. Learning a health knowledge graph from electronic medical records. Scientific Reports 7 1 (2017) 5994. 10.1038\/s41598-017-05778-z","DOI":"10.1038\/s41598-017-05778-z"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28279"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Jun Wang Abhir Bhalerao Terry Yin Simon See and Yulan He. 2024. CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation. IEEE Journal of Biomedical and Health Informatics 28 4 (April 2024) 2199\u20132210. 10.1109\/JBHI.2024.3354712","DOI":"10.1109\/JBHI.2024.3354712"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00483"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Zhanyu Wang Lingqiao Liu Lei Wang and Luping Zhou. 2023. R2GenGPT: Radiology Report Generation with Frozen LLMs. Meta-Radiology 1 3 (2023) 100033. 10.1016\/j.metrad.2023.100033","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1381"},{"key":"e_1_3_3_1_32_2","first-page":"140334","volume-title":"Advances in Neural Information Processing Systems","author":"Xia Peng","year":"2024","unstructured":"Peng Xia, Ze Chen, Juanxi Tian, Yangrui Gong, Ruibo Hou, Yue Xu, Zhenbang Wu, Zhiyuan Fan, Yiyang Zhou, Kangyu Zhu, et\u00a0al. 2024. CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models. In Advances in Neural Information Processing Systems , Vol.\u00a037. 140334\u2013140365. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/hash\/fde7f40f8ced5735006810534dc66b33-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"e_1_3_3_1_33_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xia Peng","year":"2025","unstructured":"Peng Xia, Kangyu Zhu, Haoran Li, Tianze Wang, Weijia Shi, Sheng Wang, Linjun Zhang, James Zou, and Huaxiu Yao. 2025. MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models. In The Thirteenth International Conference on Learning Representations. Singapore. https:\/\/openreview.net\/forum?id=s5epFPdIW6"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209777"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Liming Xu Quan Tang Bochuan Zheng Jiancheng Lv Weisheng Li and Xianhua Zeng. 2024. CGFTrans: Cross-Modal Global Feature Fusion Transformer for Medical Report Generation. IEEE Journal of Biomedical and Health Informatics 28 9 (2024) 5600\u20135612. 10.1109\/JBHI.2024.3414413","DOI":"10.1109\/JBHI.2024.3414413"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","unstructured":"Youyuan Xue Yun Tan Ling Tan Jiaohua Qin and Xuyu Xiang. 2024. Generating Radiology Reports via Auxiliary Signal Guidance and a Memory-Driven Network. Expert Systems with Applications 237 (March 2024) 121260. 10.1016\/j.eswa.2023.121260","DOI":"10.1016\/j.eswa.2023.121260"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Peiru Yang Hongjun Wang Yingzhuo Huang Shuai Yang Ya Zhang Liang Huang Yuesong Zhang Guoxin Wang Shizhong Yang Liang He et\u00a0al. 2024. LMKG: A Large-Scale and Multi-Source Medical Knowledge Graph for Intelligent Medicine Applications. Knowledge-Based Systems 284 (2024) 111323. 10.1016\/j.knosys.2023.111323","DOI":"10.1016\/j.knosys.2023.111323"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Shuxin Yang Xian Wu Shen Ge Zhuozhao Zheng S\u00a0Kevin Zhou and Li Xiao. 2023. Radiology Report Generation with a Learned Knowledge Base and Multi-Modal Alignment. Medical Image Analysis 86 (May 2023) 102798. 10.1016\/j.media.2023.102798","DOI":"10.1016\/j.media.2023.102798"},{"key":"e_1_3_3_1_39_2","first-page":"90683","volume-title":"Advances in Neural Information Processing Systems","volume":"37","author":"Yang Yue","year":"2024","unstructured":"Yue Yang, Mona Gandhi, Yufei Wang, Yifan Wu, Michael Yao, Chris Callison-Burch, James Gee, and Mark Yatskar. 2024. A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis. In Advances in Neural Information Processing Systems , Vol.\u00a037. 90683\u201390713. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/hash\/a4e683f0ce6b91e7fbdae9d32642d88f-Abstract-Conference.html"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Yan Yang Jun Yu Zhenqi Fu Ke Zhang Ting Yu Xianyun Wang Hanliang Jiang Junhui Lv Qingming Huang and Weidong Han. 2024. Token-Mixer: Bind Image and Text in One Embedding Space for Medical Image Reporting. IEEE Transactions on Medical Imaging 43 11 (2024) 4017\u20134028. 10.1109\/TMI.2024.3412402","DOI":"10.1109\/TMI.2024.3412402"},{"key":"e_1_3_3_1_41_2","first-page":"4096","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Yin Heng","year":"2025","unstructured":"Heng Yin, Shanlin Zhou, Pandong Wang, Zirui Wu, and Yongtao Hao. 2025. KIA: Knowledge-Guided Implicit Vision-Language Alignment for Chest X-Ray Report Generation. In Proceedings of the 31st International Conference on Computational Linguistics. Association for Computational Linguistics, Abu Dhabi, UAE, 4096\u20134108. https:\/\/aclanthology.org\/2025.coling-main.276\/"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","unstructured":"Ting Yu Wangwen Lu Yan Yang Weidong Han Qingming Huang Jun Yu and Ke Zhang. 2025. Adapter-Enhanced Hierarchical Cross-Modal Pre-Training for Lightweight Medical Report Generation. IEEE Journal of Biomedical and Health Informatics 29 7 (2025) 5303\u20135316. 10.1109\/JBHI.2025.3535699","DOI":"10.1109\/JBHI.2025.3535699"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Chao Zhao Jingchi Jiang Zhiming Xu and Yi Guan. 2017. A Study of EMR-Based Medical Knowledge Network and Its Applications. Computer Methods and Programs in Biomedicine 143 (2017) 13\u201323. 10.1016\/j.cmpb.2017.02.016","DOI":"10.1016\/j.cmpb.2017.02.016"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.18016"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","unstructured":"XueZhong Zhou J\u00f6rg Menche Albert-L\u00e1szl\u00f3 Barab\u00e1si and Amitabh Sharma. 2014. Human symptoms\u2013disease network. Nature Communications 5 1 (2014) 4212. 10.1038\/ncomms5212","DOI":"10.1038\/ncomms5212"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:59:43Z","timestamp":1781535583000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":44,"alternative-id":["10.1145\/3805622.3810644","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810644","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}