{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:10:47Z","timestamp":1783926647590,"version":"3.55.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81860318"],"award-info":[{"award-number":["81860318"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007301","name":"Kunming University of Science and Technology","doi-asserted-by":"publisher","award":["KKZ3202203020"],"award-info":[{"award-number":["KKZ3202203020"]}],"id":[{"id":"10.13039\/501100007301","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115620","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T06:38:36Z","timestamp":1783751916000},"page":"115620","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P5","title":["Cross-modal Orthogonal Adaptive Contrastive Learning for robust chest radiology report generation"],"prefix":"10.1016","volume":"181","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7419-7227","authenticated-orcid":false,"given":"Qian","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4543-0111","authenticated-orcid":false,"given":"LiJun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaman","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9685-6599","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115620_b1","article-title":"Automated radiology report generation using conditioned transformers","volume":"24","author":"Alfarghaly","year":"2021","journal-title":"Inform. Med. Unlocked"},{"key":"10.1016\/j.engappai.2026.115620_b2","series-title":"International Conference on Database Systems for Advanced Applications","first-page":"117","article-title":"Kdtnet: medical image report generation via knowledge-driven transformer","author":"Cao","year":"2022"},{"key":"10.1016\/j.engappai.2026.115620_b3","doi-asserted-by":"crossref","unstructured":"Cao, Y., Cui, L., Zhang, L., Yu, F., Li, Z., Xu, Y., 2023. MMTN: multi-modal memory transformer network for image-report consistent medical report generation. In: Proceedings of the AAAI Conference on Artificial Intelligence. 37, pp. 277\u2013285.","DOI":"10.1609\/aaai.v37i1.25100"},{"key":"10.1016\/j.engappai.2026.115620_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102698","article-title":"Orthogonal latent space learning with feature weighting and graph learning for multimodal Alzheimer\u2019s disease diagnosis","volume":"84","author":"Chen","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.engappai.2026.115620_b5","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","first-page":"1439","article-title":"Generating radiology reports via memory-driven transformer","author":"Chen","year":"2020"},{"issue":"2","key":"10.1016\/j.engappai.2026.115620_b6","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jamia\/ocv080","article-title":"Preparing a collection of radiology examinations for distribution and retrieval","volume":"23","author":"Demner-Fushman","year":"2016","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"5","key":"10.1016\/j.engappai.2026.115620_b7","doi-asserted-by":"crossref","first-page":"3079","DOI":"10.1109\/JBHI.2024.3371894","article-title":"Memory guided transformer with spatio-semantic visual extractor for medical report generation","volume":"28","author":"Divya","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.engappai.2026.115620_b8","article-title":"Devise: A deep visual-semantic embedding model","volume":"26","author":"Frome","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115620_b9","series-title":"Computer Vision and Image Processing: 4th International Conference, CVIP 2019, Jaipur, India, September 27\u201329, 2019, Revised Selected Papers, Part I 4","first-page":"174","article-title":"Automatic report generation for chest x-ray images: a multilevel multi-attention approach","author":"Gajbhiye","year":"2020"},{"key":"10.1016\/j.engappai.2026.115620_b10","series-title":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)","first-page":"1275","article-title":"Producing radiologist-quality reports for interpretable deep learning","author":"Gale","year":"2019"},{"key":"10.1016\/j.engappai.2026.115620_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113538","article-title":"Abnormal-region-aware Multi-modal Feature Fusion for medical report generation","volume":"318","author":"Gao","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2026.115620_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104496","article-title":"MKCL: medical knowledge with contrastive learning model for radiology report generation","volume":"146","author":"Hou","year":"2023","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.engappai.2026.115620_b13","doi-asserted-by":"crossref","unstructured":"Huynh, T., Kornblith, S., Walter, M.R., Maire, M., Khademi, M., 2022. Boosting contrastive self-supervised learning with false negative cancellation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 2785\u20132795.","DOI":"10.1109\/WACV51458.2022.00106"},{"key":"10.1016\/j.engappai.2026.115620_b14","series-title":"Medical Imaging with Deep Learning","first-page":"978","article-title":"Multimodal image-text matching improves retrieval-based chest x-ray report generation","author":"Jeong","year":"2024"},{"issue":"1","key":"10.1016\/j.engappai.2026.115620_b15","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"key":"10.1016\/j.engappai.2026.115620_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103377","article-title":"DACG: Dual Attention and Context Guidance model for radiology report generation","volume":"99","author":"Lang","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.engappai.2026.115620_b17","doi-asserted-by":"crossref","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X., 2018. Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 201\u2013216.","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"10.1016\/j.engappai.2026.115620_b18","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume":"31","author":"Li","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115620_b19","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, B., Chen, Z., Lin, H., Liang, X., Chang, X., 2023. 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.","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"10.1016\/j.engappai.2026.115620_b20","doi-asserted-by":"crossref","unstructured":"Liang, X., Hu, Z., Zhang, H., Gan, C., Xing, E.P., 2017. Recurrent topic-transition gan for visual paragraph generation. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3362\u20133371.","DOI":"10.1109\/ICCV.2017.364"},{"issue":"7","key":"10.1016\/j.engappai.2026.115620_b21","doi-asserted-by":"crossref","first-page":"2657","DOI":"10.1109\/TMI.2024.3372638","article-title":"Multi-grained radiology report generation with sentence-level image-language contrastive learning","volume":"43","author":"Liu","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.engappai.2026.115620_b22","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, X., Ge, S., Fan, W., Zou, Y., 2021. 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.","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"10.1016\/j.engappai.2026.115620_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2024.108482","article-title":"Label correlated contrastive learning for medical report generation","volume":"258","author":"Liu","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.engappai.2026.115620_b24","series-title":"Findings of the Association for Computational Linguistics: ACL 2022","first-page":"448","article-title":"Reinforced cross-modal alignment for radiology report generation","author":"Qin","year":"2022"},{"key":"10.1016\/j.engappai.2026.115620_b25","unstructured":"Song, X., Zhang, X., Ji, J., Liu, Y., Wei, P., 2022. Cross-modal contrastive attention model for medical report generation. In: Proceedings of the 29th International Conference on Computational Linguistics. pp. 2388\u20132397."},{"key":"10.1016\/j.engappai.2026.115620_b26","doi-asserted-by":"crossref","unstructured":"Srinivasan, P., Thapar, D., Bhavsar, A., Nigam, A., 2021. Hierarchical X-ray report generation via pathology tags and multi head attention. In: Computer Vision \u2013 ACCV 2020. pp. 600\u2013616.","DOI":"10.1007\/978-3-030-69541-5_36"},{"issue":"7","key":"10.1016\/j.engappai.2026.115620_b27","doi-asserted-by":"crossref","first-page":"4145","DOI":"10.1109\/JBHI.2024.3393018","article-title":"Memory-based cross-modal semantic alignment network for radiology report generation","volume":"28","author":"Tao","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.engappai.2026.115620_b28","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115620_b29","series-title":"ECAI 2023","first-page":"2427","article-title":"Automatic radiology report generation by learning with increasingly hard negatives","author":"Voutharoja","year":"2023"},{"issue":"10","key":"10.1016\/j.engappai.2026.115620_b30","doi-asserted-by":"crossref","first-page":"2803","DOI":"10.1109\/TMI.2022.3171661","article-title":"Automated radiographic report generation purely on transformer: A multicriteria supervised approach","volume":"41","author":"Wang","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.engappai.2026.115620_b31","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"655","article-title":"A medical semantic-assisted transformer for radiographic report generation","author":"Wang","year":"2022"},{"issue":"1","key":"10.1016\/j.engappai.2026.115620_b32","first-page":"21","article-title":"Tmrgm: A template-based multi-attention model for x-ray imaging report generation","volume":"2","author":"Wang","year":"2021","journal-title":"J. Artif. Intell. Med. Sci."},{"key":"10.1016\/j.engappai.2026.115620_b33","doi-asserted-by":"crossref","first-page":"33536","DOI":"10.52202\/068431-2430","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115620_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101817","article-title":"Vision-knowledge fusion model for multi-domain medical report generation","volume":"97","author":"Xu","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.115620_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121260","article-title":"Generating radiology reports via auxiliary signal guidance and a memory-driven network","volume":"237","author":"Xue","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"11","key":"10.1016\/j.engappai.2026.115620_b36","doi-asserted-by":"crossref","first-page":"5631","DOI":"10.1109\/JBHI.2022.3197162","article-title":"Prior guided transformer for accurate radiology reports generation","volume":"26","author":"Yan","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"1","key":"10.1016\/j.engappai.2026.115620_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3374754","article-title":"Learning shared semantic space with correlation alignment for cross-modal event retrieval","volume":"16","author":"Yang","year":"2020","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"10.1016\/j.engappai.2026.115620_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102798","article-title":"Radiology report generation with a learned knowledge base and multi-modal alignment","volume":"86","author":"Yang","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.engappai.2026.115620_b39","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part III 24","first-page":"72","article-title":"Aligntransformer: Hierarchical alignment of visual regions and disease tags for medical report generation","author":"You","year":"2021"},{"key":"10.1016\/j.engappai.2026.115620_b40","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.patrec.2021.02.016","article-title":"CHOP: An orthogonal hashing method for zero-shot cross-modal retrieval","volume":"145","author":"Yuan","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.engappai.2026.115620_b41","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1109\/TMM.2023.3273390","article-title":"Semi-supervised medical report generation via graph-guided hybrid feature consistency","volume":"26","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115620_b42","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A., Xu, D., 2020. When radiology report generation meets knowledge graph. In: Proceedings of the AAAI Conference on Artificial Intelligence. 34, pp. 12910\u201312917.","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"10.1016\/j.engappai.2026.115620_b43","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, Y., Xing, F., McGough, M., Yang, L., 2017. Mdnet: A semantically and visually interpretable medical image diagnosis network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6428\u20136436.","DOI":"10.1109\/CVPR.2017.378"},{"key":"10.1016\/j.engappai.2026.115620_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107522","article-title":"Visual prior-based cross-modal alignment network for radiology report generation","volume":"166","author":"Zhang","year":"2023","journal-title":"Comput. Biol. Med."},{"issue":"1","key":"10.1016\/j.engappai.2026.115620_b45","doi-asserted-by":"crossref","DOI":"10.3390\/app15010343","article-title":"Automated chest X-Ray diagnosis report generation with cross-attention mechanism.","volume":"15","author":"Zhao","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.engappai.2026.115620_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102714","article-title":"Radiology report generation with medical knowledge and multilevel image-report alignment: A new method and its verification","volume":"146","author":"Zhao","year":"2023","journal-title":"Artif. Intell. Med."},{"issue":"5","key":"10.1016\/j.engappai.2026.115620_b47","doi-asserted-by":"crossref","first-page":"2646","DOI":"10.1007\/s10278-025-01422-9","article-title":"Denoising multi-level cross-attention and contrastive learning for chest radiology report generation","volume":"38","author":"Zhu","year":"2025","journal-title":"J. Imaging Inform. Med."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626019044?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626019044?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T06:48:23Z","timestamp":1783925303000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626019044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":47,"alternative-id":["S0952197626019044"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115620","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Cross-modal Orthogonal Adaptive Contrastive Learning for robust chest radiology report generation","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115620","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115620"}}