{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T02:12:38Z","timestamp":1775873558952,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376067"],"award-info":[{"award-number":["62376067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11280-024-01315-x","type":"journal-article","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T01:58:08Z","timestamp":1733536688000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A vision-language model with multi-granular knowledge fusion in medical imaging"],"prefix":"10.1007","volume":"28","author":[{"given":"Kai","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiwen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baotian","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"1315_CR1","doi-asserted-by":"publisher","unstructured":"Chen, Z., Song, Y., Chang, T.-H., Wan, X.: Generating radiology reports via memory-driven transformer. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1439\u20131449. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.112. https:\/\/aclanthology.org\/2020.emnlp-main.112","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"1315_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Z., Shen, Y., Song, Y., Wan, X.: Cross-modal memory networks for radiology report generation. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) 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, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.459. https:\/\/aclanthology.org\/2021.acl-long.459","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"1315_CR3","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.-M., Xu, L., Ma, L., Yang, Y., Wu, X.-M.: Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654 (2021). IEEE","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"1315_CR4","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., Tan, L., Liao, J., Zhong, S.: Self-supervised vision-language pretraining for medial visual question answering. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp. 1\u20135 (2023). IEEE","DOI":"10.1109\/ISBI53787.2023.10230743"},{"issue":"1","key":"1315_CR5","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/JBHI.2019.2912659","volume":"24","author":"F Gao","year":"2019","unstructured":"Gao, F., Wu, T., Chu, X., Yoon, H., Xu, Y., Patel, B.: Deep residual inception encoder-decoder network for medical imaging synthesis. IEEE J. Biomed. Health Inf. 24(1), 39\u201349 (2019)","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"1315_CR6","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1109\/TIP.2019.2919937","volume":"29","author":"S Zhou","year":"2019","unstructured":"Zhou, S., Nie, D., Adeli, E., Yin, J., Lian, J., Shen, D.: High-resolution encoder-decoder networks for low-contrast medical image segmentation. IEEE Trans. Image Process. 29, 461\u2013475 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"1315_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Guo, X., Yang, W., Shi, Y., Zhou, L., Wang, L., Yang, M.: Cross-modal attention-guided convolutional network for multi-modal cardiac segmentation. In: Machine Learning in Medical Imaging: 10th International Workshop, MLMI 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedings 10, pp. 601\u2013610 (2019). Springer","DOI":"10.1007\/978-3-030-32692-0_69"},{"issue":"1","key":"1315_CR8","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/TBME.2021.3087612","volume":"69","author":"T Shi","year":"2021","unstructured":"Shi, T., Jiang, H., Zheng, B.: C 2 ma-net: Cross-modal cross-attention network for acute ischemic stroke lesion segmentation based on ct perfusion scans. IEEE Trans. Biomed. Eng. 69(1), 108\u2013118 (2021)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"1315_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., Hu, B., Chen, X., Ma, L., Xu, Y., Zhang, M.: Lmeye: An interactive perception network for large language models. IEEE Trans. Multimed. (2024)","DOI":"10.1109\/TMM.2024.3428317"},{"key":"1315_CR10","doi-asserted-by":"crossref","unstructured":"Wang, M., Wang, H., Qi, G., Zheng, Q.: Richpedia: a large-scale, comprehensive multi-modal knowledge graph. Big Data Res. 22, 100159 (2020)","DOI":"10.1016\/j.bdr.2020.100159"},{"key":"1315_CR11","doi-asserted-by":"crossref","unstructured":"Van\u00a0Sonsbeek, T., Derakhshani, M.M., Najdenkoska, I., Snoek, C.G., Worring, M.: Open-ended medical visual question answering through prefix tuning of language models. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 726\u2013736 (2023). Springer","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"1315_CR12","doi-asserted-by":"crossref","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: A review. arXiv:2403.02469 (2024)","DOI":"10.3389\/frai.2024.1430984"},{"key":"1315_CR13","doi-asserted-by":"crossref","unstructured":"Jing, B., Xie, P., Xing, E.: On the automatic generation of medical imaging reports. arXiv:1711.08195 (2017)","DOI":"10.18653\/v1\/P18-1240"},{"key":"1315_CR14","doi-asserted-by":"crossref","unstructured":"Yuan, J., Liao, H., Luo, R., Luo, J.: Automatic radiology report generation based on multi-view image fusion and medical concept enrichment. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part VI 22, pp. 721\u2013729 (2019). Springer","DOI":"10.1007\/978-3-030-32226-7_80"},{"key":"1315_CR15","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":"1315_CR16","doi-asserted-by":"crossref","unstructured":"Nooralahzadeh, F., Gonzalez, N.P., Frauenfelder, T., Fujimoto, K., Krauthammer, M.: Progressive transformer-based generation of radiology reports. arXiv:2102.09777 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"1315_CR17","doi-asserted-by":"crossref","unstructured":"Wang, J., Bhalerao, A., He, Y.: Cross-modal prototype driven network for radiology report generation. In: European Conference on Computer Vision, pp. 563\u2013579 (2022). Springer","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"1315_CR18","doi-asserted-by":"crossref","unstructured":"Yan, A., He, Z., Lu, X., Du, J., Chang, E., Gentili, A., McAuley, J., Hsu, C.-N.: Weakly supervised contrastive learning for chest x-ray report generation. arXiv:2109.12242 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.336"},{"key":"1315_CR19","unstructured":"Zhai, Y., Tong, S., Li, X., Cai, M., Qu, Q., Lee, Y.J., Ma, Y.: Investigating the catastrophic forgetting in multimodal large language models. arXiv:2309.10313 (2023)"},{"key":"1315_CR20","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":"1315_CR21","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015). PMLR"},{"key":"1315_CR22","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":"1315_CR23","doi-asserted-by":"crossref","unstructured":"Xue, Y., Huang, X.: Improved disease classification in chest x-rays with transferred features from report generation. In: Information Processing in Medical Imaging: 26th International Conference, IPMI 2019, Hong Kong, China, June 2\u20137, 2019, Proceedings 26, pp. 125\u2013138 (2019). Springer","DOI":"10.1007\/978-3-030-20351-1_10"},{"key":"1315_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, X., Hu, B., Shi, H., Zhang, M.: Cognitive visual-language mapper: Advancing multimodal comprehension with enhanced visual knowledge alignment. arXiv:2402.13561 (2024)","DOI":"10.18653\/v1\/2024.acl-long.411"},{"key":"1315_CR25","unstructured":"Li, Y., Hu, B., Shi, H., Wang, W., Wang, L., Zhang, M.: Visiongraph: Leveraging large multimodal models for graph theory problems in visual context. arXiv:2405.04950 (2024)"},{"key":"1315_CR26","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: Evaluating text generation with bert. In: International Conference on Learning Representations"},{"key":"1315_CR27","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: Pubmedclip: How much does clip benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics: EACL 2023, pp. 1181\u20131193 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"1315_CR28","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537.v1"},{"key":"1315_CR29","unstructured":"Zhang, S., Xu, Y., Usuyama, N., Bagga, J., Tinn, R., Preston, S., Rao, R., Wei, M., Valluri, N., Wong, C., et al.: Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv:2303.00915 2(3), 6 (2023)"},{"issue":"3","key":"1315_CR30","doi-asserted-by":"publisher","first-page":"380","DOI":"10.3390\/bioengineering10030380","volume":"10","author":"Y Bazi","year":"2023","unstructured":"Bazi, Y., Rahhal, M.M.A., Bashmal, L., Zuair, M.: Vision-language model for visual question answering in medical imagery. Bioengineering 10(3), 380 (2023)","journal-title":"Bioengineering"},{"key":"1315_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Z., Xu, D., Zhou, L.: Q2atransformer: Improving medical vqa via an answer querying decoder. In: International Conference on Information Processing in Medical Imaging, pp. 445\u2013456 (2023). Springer","DOI":"10.1007\/978-3-031-34048-2_34"},{"key":"1315_CR32","doi-asserted-by":"crossref","unstructured":"Wang, H., Fang, Z., Zhang, L., Pan, J.Z., Ruan, T.: Effective online knowledge graph fusion. In: International Semantic Web Conference, pp. 286\u2013302 (2015). Springer","DOI":"10.1007\/978-3-319-25007-6_17"},{"key":"1315_CR33","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, A., Du, H., Wang, H., Zhang, W.: Knowledge-enhanced visual question answering with multi-modal joint guidance. In: Proceedings of the 11th International Joint Conference on Knowledge Graphs, pp. 115\u2013120 (2022)","DOI":"10.1145\/3579051.3579073"},{"key":"1315_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, S., Du, H., Qin, Y., Wang, H., Zhang, W.: Mhkd-mvqa: Multimodal hierarchical knowledge distillation for medical visual question answering. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 567\u2013574 (2022). IEEE","DOI":"10.1109\/BIBM55620.2022.9995473"},{"key":"1315_CR35","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. Adv. Neural Inf Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inf Process. Syst."},{"key":"1315_CR36","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"1315_CR37","doi-asserted-by":"crossref","unstructured":"Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., Gao, J.: Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"1315_CR38","unstructured":"Zhang, K., Yu, J., Yan, Z., Liu, Y., Adhikarla, E., Fu, S., Chen, X., Chen, C., Zhou, Y., Li, X., et al.: Biomedgpt: a unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks. arXiv:2305.17100 (2023)"},{"key":"1315_CR39","unstructured":"Yang, X., Chen, A., PourNejatian, N., Shin, H.C., Smith, K.E., Parisien, C., Compas, C., Martin, C., Flores, M.G., Zhang, Y., et al.: Gatortron: A large clinical language model to unlock patient information from unstructured electronic health records. arXiv:2203.03540 (2022)"},{"key":"1315_CR40","unstructured":"Shu, C., Chen, B., Liu, F., Fu, Z., Shareghi, E., Collier, N.: Visual med-alpaca: A parameter-efficient biomedical llm with visual capabilities (2023)"},{"key":"1315_CR41","unstructured":"Wan, F., Huang, X., Cai, D., Quan, X., Bi, W., Shi, S.: Knowledge fusion of large language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"1315_CR42","doi-asserted-by":"crossref","unstructured":"Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying large language models and knowledge graphs: A roadmap. IEEE Trans. Knowl. Data Eng. (2024)","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"1315_CR43","unstructured":"Liu, W., Xue, Y., Lin, C., Boumaraf, S.: Dynamic multi-domain knowledge networks for chest x-ray report generation. arXiv:2310.05119 (2023)"},{"key":"1315_CR44","doi-asserted-by":"crossref","unstructured":"Nazi, Z.A., Peng, W.: Large language models in healthcare and medical domain: A review. In: Informatics, vol. 11, p. 57 (2024). MDPI","DOI":"10.3390\/informatics11030057"},{"key":"1315_CR45","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Z., Zhang, K., Dan, R., Jiang, S., Zhang, Y.: Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge. Cureus 15(6) (2023)","DOI":"10.7759\/cureus.40895"},{"key":"1315_CR46","unstructured":"Han, T., Adams, L.C., Papaioannou, J.-M., Grundmann, P., Oberhauser, T., L\u00f6ser, A., Truhn, D., Bressem, K.K.: Medalpaca\u2013an open-source collection of medical conversational ai models and training data. arXiv:2304.08247 (2023)"},{"key":"1315_CR47","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":"1315_CR48","unstructured":"Lin, C.-Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"1315_CR49","unstructured":"Banerjee, S., Lavie, A.: 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, pp. 65\u201372 (2005)"},{"key":"1315_CR50","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"1315_CR51","unstructured":"Dina, D.F., Kohli, M.D., Rosenman, M.B., Shooshan, S.E., Laritza, R., Sameer, A., Thoma, G.R., Mcdonald, C.J.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inf. Assoc. Jamia (2), 2 (2015)"},{"key":"1315_CR52","unstructured":"Johnson, A.E.W., Pollard, T.J., Greenbaum, N.R., Lungren, M.P., Deng, C.Y., Peng, Y., Lu, Z., Mark, R.G., Berkowitz, S.J., Horng, S.: Mimic-cxr: A large publicly available database of labeled chest radiographs. arXiv:1901.07042. (2019)"},{"issue":"1","key":"1315_CR53","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1038\/s41597-024-03496-6","volume":"11","author":"J R\u00fcckert","year":"2024","unstructured":"R\u00fcckert, J., Bloch, L., Br\u00fcngel, R., Idrissi-Yaghir, A., Sch\u00e4fer, H., Schmidt, C.S., Koitka, S., Pelka, O., Abacha, A.B., Herrera, A., et al.: Rocov2: Radiology objects in context version 2, an updated multimodal image dataset. Scientific Data 11(1), 688 (2024)","journal-title":"Scientific Data"},{"key":"1315_CR54","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zhu, C., Zheng, S., Zhang, K., Sun, L., Shui, Z., Zhang, Y., Li, H., Yang, L.: Pathasst: A generative foundation ai assistant towards artificial general intelligence of pathology. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 5034\u20135042 (2024)","DOI":"10.1609\/aaai.v38i5.28308"},{"issue":"1","key":"1315_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Scientific Data 5(1), 1\u201310 (2018)","journal-title":"Scientific Data"},{"key":"1315_CR56","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: Vqa-med: Overview of the medical visual question answering task at imageclef 2019. In: Proceedings of CLEF (Conference and Labs of the Evaluation Forum) 2019 Working Notes (2019). 9-12 September 2019"},{"key":"1315_CR57","unstructured":"Wang, X., Li, Y., Wang, F., Wang, S., Li, C., Jiang, B.: R2gencsr: Retrieving context samples for large language model based x-ray medical report generation. arXiv:2408.09743 (2024)"},{"key":"1315_CR58","unstructured":"Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Neural Information Processing Systems (2017). https:\/\/api.semanticscholar.org\/CorpusID:13756489"},{"key":"1315_CR59","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"1315_CR60","unstructured":"R\u00fcckert, J., Ben\u00a0Abacha, A., Herrera, A.G., Bloch, L., Br\u00fcngel, R., Idrissi-Yaghir, A., Sch\u00e4fer, H., M\u00fcller, H., Friedrich, C.M.: Overview of imageclefmedical 2023\u2013caption prediction and concept detection. In: Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2023), vol. 3497, pp. 1328\u20131346 (2023)"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-024-01315-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-024-01315-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-024-01315-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T10:03:03Z","timestamp":1740218583000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-024-01315-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"references-count":60,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["1315"],"URL":"https:\/\/doi.org\/10.1007\/s11280-024-01315-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4950362\/v1","asserted-by":"object"}]},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"21 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2024","order":4,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This declaration is not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"5"}}