{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:08Z","timestamp":1792786868793,"version":"4.5.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021ZD0111601"],"award-info":[{"award-number":["2021ZD0111601"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436009"],"award-info":[{"award-number":["62436009"]}],"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":["62322608"],"award-info":[{"award-number":["62322608"]}],"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":["62301532"],"award-info":[{"award-number":["62301532"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515011874"],"award-info":[{"award-number":["2025A1515011874"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011530"],"award-info":[{"award-number":["2023A1515011530"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3568746","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T13:47:39Z","timestamp":1747403259000},"page":"2970-2985","source":"Crossref","is-referenced-by-count":55,"title":["Cross-Modal Causal Representation Learning for Radiology Report Generation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8081-1289","authenticated-orcid":false,"given":"Weixing","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9423-9252","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1017-7972","authenticated-orcid":false,"given":"Ce","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6225-8910","authenticated-orcid":false,"given":"Jiarui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6743-4175","authenticated-orcid":false,"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3203223"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3054390"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3211467"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref7","article-title":"Cross-modal causal intervention for medical report generation","volume-title":"arXiv:2303.09117","author":"Chen","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref11","volume-title":"Causal Inference In Statistics: A Primer","author":"Pearl","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1362-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3284038"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3121705"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25253"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv:2108.10904"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3177318"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.780"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2917229"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2928144"},{"key":"ref28","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02554"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref32","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref33","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref34","first-page":"2734","article-title":"Interventional few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yue"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01959"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01242"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00308"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00197"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00148"},{"key":"ref41","first-page":"24941","article-title":"A causal lens for controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00238"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01267"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690217"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3539433"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3233547.3233555"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01505"},{"key":"ref48","article-title":"RadGraph: Extracting clinical entities and relations from radiology reports","volume-title":"arXiv:2106.14463","author":"Jain","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"ref52","article-title":"Competence-based multimodal curriculum learning for medical report generation","volume-title":"arXiv:2206.14579","author":"Liu","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3354712"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.241"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3371894"},{"key":"ref56","article-title":"Cross-modal memory networks for radiology report generation","volume-title":"arXiv:2204.13258","author":"Chen","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680760"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591721"},{"key":"ref61","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02031"},{"key":"ref64","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01150"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3357986"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","article-title":"Multimodal masked autoencoders learn transferable representations","author":"Geng","year":"2022","journal-title":"arXiv:2205.14204"},{"key":"ref69","article-title":"Advancing radiograph representation learning with masked record modeling","author":"Zhou","year":"2023","journal-title":"arXiv:2301.13155"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.14"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01087"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_59"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref77","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Dai"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25100"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3273390"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref82","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv:1901.07042"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref84","first-page":"74","article-title":"A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Rouge"},{"key":"ref85","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11005686.pdf?arnumber=11005686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T14:09:49Z","timestamp":1748268589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11005686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3568746","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}