{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T20:10:25Z","timestamp":1780776625703,"version":"3.54.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276112"],"award-info":[{"award-number":["62276112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276112"],"award-info":[{"award-number":["62276112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276112"],"award-info":[{"award-number":["62276112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276112"],"award-info":[{"award-number":["62276112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276112"],"award-info":[{"award-number":["62276112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["20210101167JC"],"award-info":[{"award-number":["20210101167JC"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["20210101167JC"],"award-info":[{"award-number":["20210101167JC"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["20210101167JC"],"award-info":[{"award-number":["20210101167JC"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["20210101167JC"],"award-info":[{"award-number":["20210101167JC"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","award":["20210101167JC"],"award-info":[{"award-number":["20210101167JC"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jilin Province Science and Technology Development Plan Key R&D Project","award":["20230201088GX"],"award-info":[{"award-number":["20230201088GX"]}]},{"name":"Jilin Province Science and Technology Development Plan Key R&D Project","award":["20230201088GX"],"award-info":[{"award-number":["20230201088GX"]}]},{"name":"Jilin Province Science and Technology Development Plan Key R&D Project","award":["20230201088GX"],"award-info":[{"award-number":["20230201088GX"]}]},{"name":"Jilin Province Science and Technology Development Plan Key R&D Project","award":["20230201088GX"],"award-info":[{"award-number":["20230201088GX"]}]},{"name":"Jilin Province Science and Technology Development Plan Key R&D Project","award":["20230201088GX"],"award-info":[{"award-number":["20230201088GX"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00530-024-01504-8","type":"journal-article","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T11:01:22Z","timestamp":1727607682000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Reinforced visual interaction fusion radiology report generation"],"prefix":"10.1007","volume":"30","author":[{"given":"Liya","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haipeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingda","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"issue":"5","key":"1504_CR1","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1016\/j.media.2012.02.005","volume":"16","author":"S Wang","year":"2012","unstructured":"Wang, S., Summers, R.M.: Machine learning and radiology. Med. Image Anal. 16(5), 933\u2013951 (2012)","journal-title":"Med. Image Anal."},{"key":"1504_CR2","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":"1504_CR3","first-page":"714","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"AK Tanwani","year":"2022","unstructured":"Tanwani, A.K., Barral, J., Freedman, D.: Repsnet: combining vision with language for automated medical reports. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 714\u2013724. Springer, Cham (2022)"},{"issue":"1","key":"1504_CR4","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. Sci Data 5(1), 1\u201310 (2018)","journal-title":"Sci Data"},{"key":"1504_CR5","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":"1504_CR6","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)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1504_CR7","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"},{"key":"1504_CR8","first-page":"563","volume-title":"European Conference on Computer Vision","author":"J Wang","year":"2022","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. Springer, Cham (2022)"},{"key":"1504_CR9","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, B., Chen, Z., Lin, H., Liang, X., Chang, X.: Dynamic graph enhanced contrastive learning for chest x-ray report generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3334\u20133343 (2023)","DOI":"10.1109\/CVPR52729.2023.00325"},{"issue":"2","key":"1504_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00530-024-01289-w","volume":"30","author":"Y Shi","year":"2024","unstructured":"Shi, Y., Ji, J., Zhang, X., Liu, Y., Wang, Z., Xu, H.: Prior tissue knowledge-driven contrastive learning for brain CT report generation. Multimedia Syst. 30(2), 1\u201314 (2024)","journal-title":"Multimedia Syst."},{"key":"1504_CR11","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"1504_CR12","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":"1504_CR13","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)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"1504_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.-H., Wan, X.: Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"1504_CR15","doi-asserted-by":"crossref","unstructured":"Qin, H., Song, Y.: Reinforced cross-modal alignment for radiology report generation. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 448\u2013458 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"1504_CR16","doi-asserted-by":"crossref","unstructured":"Tanida, T., M\u00fcller, P., Kaissis, G., Rueckert, D.: Interactive and explainable region-guided radiology report generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7433\u20137442 (2023)","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"1504_CR17","doi-asserted-by":"crossref","unstructured":"Gu, T., Liu, D., Li, Z., Cai, W.: Complex organ mask guided radiology report generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7995\u20138004 (2024)","DOI":"10.1109\/WACV57701.2024.00781"},{"key":"1504_CR18","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: 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"},{"issue":"8","key":"1504_CR19","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":"1504_CR20","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-rnn). arXiv preprint arXiv:1412.6632 (2014)"},{"key":"1504_CR21","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":"1504_CR22","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"1504_CR23","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.patrec.2023.07.013","volume":"173","author":"JH Lim","year":"2023","unstructured":"Lim, J.H., Chan, C.S.: Mask-guided network for image captioning. Pattern Recogn. Lett. 173, 79\u201386 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"1504_CR24","doi-asserted-by":"publisher","first-page":"150560","DOI":"10.1109\/ACCESS.2021.3124564","volume":"9","author":"H Park","year":"2021","unstructured":"Park, H., Kim, K., Park, S., Choi, J.: Medical image captioning model to convey more details: Methodological comparison of feature difference generation. IEEE Access 9, 150560\u2013150568 (2021)","journal-title":"IEEE Access"},{"key":"1504_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107856","volume":"114","author":"H Ayesha","year":"2021","unstructured":"Ayesha, H., Iqbal, S., Tariq, M., Abrar, M., Sanaullah, M., Abbas, I., Rehman, A., Niazi, M.F.K., Hussain, S.: Automatic medical image interpretation: State of the art and future directions. Pattern Recogn. 114, 107856 (2021)","journal-title":"Pattern Recogn."},{"key":"1504_CR26","doi-asserted-by":"crossref","unstructured":"Tao, Y., Ma, L., Yu, J., Zhang, H.: Memory-based cross-modal semantic alignment network for radiology report generation. IEEE Journal of Biomedical and Health Informatics (2024)","DOI":"10.1109\/JBHI.2024.3393018"},{"key":"1504_CR27","doi-asserted-by":"crossref","unstructured":"Chen, Z., Shen, Y., Song, Y., Wan, X.: Cross-modal memory networks for radiology report generation. arXiv preprint arXiv:2204.13258 (2022)","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"1504_CR28","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900 (2022). PMLR"},{"key":"1504_CR29","unstructured":"Huang, G., Liu, Z., Maaten, L., Weinberger, K.: Deep convolutional networks for large-scale image recognition. In: ICLR. (2017)"},{"key":"1504_CR30","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":"1504_CR31","unstructured":"Liu, F., Ge, S., Zou, Y., Wu, X.: Competence-based multimodal curriculum learning for medical report generation. arXiv preprint arXiv:2206.14579 (2022)"},{"key":"1504_CR32","doi-asserted-by":"crossref","unstructured":"Guo, K., Zheng, S., Huang, R., Gao, R.: Multi-task learning for lung disease classification and report generation via prior graph structure and contrastive learning. IEEE Access (2023)","DOI":"10.1109\/ACCESS.2023.3322425"},{"key":"1504_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A., Xu, D.: When radiology report generation meets knowledge graph. In: Proceedings of the AAAI Conference on Artificial Intelligence. 34: 12910\u201312917 (2020)","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"1504_CR34","first-page":"655","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Tang, M., Wang, L., Li, X., Zhou, L.: A medical semantic-assisted transformer for radiographic report generation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 655\u2013664. Springer, Cham (2022)"},{"key":"1504_CR35","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":"1504_CR36","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":"1504_CR37","unstructured":"Lin, C.-Y.: Rouge: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"1504_CR38","doi-asserted-by":"crossref","unstructured":"Pahwa, E., Mehta, D., Kapadia, S., Jain, D., Luthra, A.: Medskip: Medical report generation using skip connections and integrated attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3409\u20133415 (2021)","DOI":"10.1109\/ICCVW54120.2021.00380"},{"key":"1504_CR39","doi-asserted-by":"crossref","unstructured":"Voutharoja, B.P., Wang, L., Zhou, L.: Automatic radiology report generation by learning with increasingly hard negatives. arXiv preprint arXiv:2305.07176 (2023)","DOI":"10.3233\/FAIA230545"},{"key":"1504_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107979","volume":"244","author":"X Zeng","year":"2024","unstructured":"Zeng, X., Liao, T., Xu, L., Wang, Z.: Aermnet: attention-enhanced relational memory network for medical image report generation. Comput. Methods Programs Biomed. 244, 107979 (2024)","journal-title":"Comput. Methods Programs Biomed."},{"key":"1504_CR41","doi-asserted-by":"crossref","unstructured":"Liu, F., Yin, C., Wu, X., Ge, S., Zou, Y., Zhang, P., Sun, X.: Contrastive attention for automatic chest x-ray report generation. arXiv preprint arXiv:2106.06965 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"1504_CR42","unstructured":"Kingma DP.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"1504_CR43","doi-asserted-by":"crossref","unstructured":"Cao, Y., Cui, L., Zhang, L., Yu, F., Li, Z., Xu, Y.: Mmtn: multi-modal memory transformer network for image-report consistent medical report generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 277\u2013285 (2023)","DOI":"10.1609\/aaai.v37i1.25100"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01504-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01504-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01504-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T14:18:31Z","timestamp":1730125111000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01504-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1504"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01504-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4576817\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"13 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no association with any entity or organization with any financial or non-financial interest in the content discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"299"}}