{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T03:28:19Z","timestamp":1793935699018,"version":"4.8.0"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.media.2026.104304","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T15:18:00Z","timestamp":1789226280000},"page":"104304","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A review of longitudinal radiology report generation: Dataset composition, methods, and performance evaluation"],"prefix":"10.1016","volume":"115","author":[{"given":"Shaoyang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingshu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-2424","authenticated-orcid":false,"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.104304_b1","series-title":"Understanding and appreciating burnout in radiologists","author":"Bailey","year":"2022"},{"key":"10.1016\/j.media.2026.104304_b2","unstructured":"Banerjee, S., Lavie, A., 2005. 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."},{"key":"10.1016\/j.media.2026.104304_b3","series-title":"Maira-2: Grounded radiology report generation","author":"Bannur","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b4","doi-asserted-by":"crossref","unstructured":"Bannur, S., Hyland, S., Liu, Q., Perez-Garcia, F., Ilse, M., Castro, D.C., Boecking, B., Sharma, H., Bouzid, K., Thieme, A., et al., 2023. Learning to exploit temporal structure for biomedical vision-language processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15016\u201315027.","DOI":"10.1109\/CVPR52729.2023.01442"},{"issue":"1","key":"10.1016\/j.media.2026.104304_b5","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/08465371221117282","article-title":"Current status of burnout in Canadian radiology","volume":"74","author":"Cao","year":"2023","journal-title":"Can. Assoc. Radiol. J."},{"key":"10.1016\/j.media.2026.104304_b6","series-title":"Chexpert plus: Augmenting a large chest x-ray dataset with text radiology reports, patient demographics and additional image formats","author":"Chambon","year":"2024"},{"issue":"1","key":"10.1016\/j.media.2026.104304_b7","first-page":"22","article-title":"Word association norms, mutual information, and lexicography","volume":"16","author":"Church","year":"1990","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.media.2026.104304_b8","series-title":"Improving the factual correctness of radiology report generation with semantic rewards","author":"Delbrouck","year":"2022"},{"issue":"2","key":"10.1016\/j.media.2026.104304_b9","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. Informatics Assoc."},{"key":"10.1016\/j.media.2026.104304_b10","series-title":"RADAR: Enhancing radiology report generation with supplementary knowledge injection","author":"Hou","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b11","series-title":"RECAP: Towards precise radiology report generation via dynamic disease progression reasoning","author":"Hou","year":"2023"},{"key":"10.1016\/j.media.2026.104304_b12","series-title":"Fineradscore: A radiology report line-by-line evaluation technique generating corrections with severity scores","author":"Huang","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b13","series-title":"HIST-AID: Leveraging historical patient reports for enhanced multi-modal automatic diagnosis","author":"Huang","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b14","series-title":"Maira-1: A specialised large multimodal model for radiology report generation","author":"Hyland","year":"2023"},{"key":"10.1016\/j.media.2026.104304_b15","first-page":"590","article-title":"Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison","volume":"vol. 33","author":"Irvin","year":"2019"},{"key":"10.1016\/j.media.2026.104304_b16","series-title":"International Conference on Machine Learning","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","author":"Jaegle","year":"2021"},{"key":"10.1016\/j.media.2026.104304_b17","series-title":"Radgraph: Extracting clinical entities and relations from radiology reports","author":"Jain","year":"2021"},{"key":"10.1016\/j.media.2026.104304_b18","series-title":"CLEAR: A clinically-grounded tabular framework for radiology report evaluation","author":"Jiang","year":"2025"},{"issue":"1","key":"10.1016\/j.media.2026.104304_b19","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"},{"issue":"3","key":"10.1016\/j.media.2026.104304_b20","first-page":"143","article-title":"The chest radiograph","volume":"81","author":"Kelly","year":"2012","journal-title":"Ulst. Med. J."},{"key":"10.1016\/j.media.2026.104304_b21","first-page":"1","article-title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","author":"Lee","year":"2025","journal-title":"Eur. Radiol."},{"key":"10.1016\/j.media.2026.104304_b22","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.media.2026.104304_b23","series-title":"RadReason: Radiology report evaluation metric with reasons and sub-scores","author":"Li","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b24","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"382","article-title":"KARGEN: Knowledge-enhanced automated radiology report generation using large language models","author":"Li","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b25","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.media.2026.104304_b26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B., 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.media.2026.104304_b27","series-title":"Priorrg: Prior-guided contrastive pre-training and coarse-to-fine decoding for chest x-ray report generation","author":"Liu","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b28","doi-asserted-by":"crossref","unstructured":"Liu, K., Ma, Z., Kang, X., Li, Y., Xie, K., Jiao, Z., Miao, Q., 2025b. Enhanced contrastive learning with multi-view longitudinal data for chest x-ray report generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 10348\u201310359.","DOI":"10.1109\/CVPR52734.2025.00968"},{"key":"10.1016\/j.media.2026.104304_b29","first-page":"5595","article-title":"HC-LLM: Historical-constrained large language models for radiology report generation","volume":"vol. 39","author":"Liu","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b30","series-title":"Mrscore: Evaluating radiology report generation with llm-based reward system","author":"Liu","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b31","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhu, L., Shi, B., Zhang, Z., Lou, Y., Yang, S., Xi, H., Cao, S., Gu, Y., Li, D., et al., 2025. Nvila: Efficient frontier visual language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 4122\u20134134.","DOI":"10.1109\/CVPR52734.2025.00390"},{"issue":"7","key":"10.1016\/j.media.2026.104304_b32","doi-asserted-by":"crossref","first-page":"693","DOI":"10.3390\/bioengineering12070693","article-title":"Advancements in radiology report generation: A comprehensive analysis","volume":"12","author":"Mamdouh","year":"2025","journal-title":"Bioengineering"},{"key":"10.1016\/j.media.2026.104304_b33","series-title":"EVOKE: Elevating chest X-ray report generation via multi-view contrastive learning and patient-specific knowledge","author":"Miao","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b34","series-title":"Automating radiology report generation: A systematic review of deep learning methods","author":"Min","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b35","series-title":"Lunguage: A benchmark for structured and sequential chest X-ray interpretation","author":"Moon","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102603","article-title":"Uncertainty-aware report generation for chest X-rays by variational topic inference","volume":"82","author":"Najdenkoska","year":"2022","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104304_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2024.101585","article-title":"Longitudinal data and a semantic similarity reward for chest X-ray report generation","volume":"50","author":"Nicolson","year":"2024","journal-title":"Informatics Med. Unlocked"},{"key":"10.1016\/j.media.2026.104304_b38","series-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"10.1016\/j.media.2026.104304_b39","series-title":"Green: Generative radiology report evaluation and error notation","author":"Ostmeier","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b40","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J., 2002. 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.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.media.2026.104304_b41","series-title":"M4cxr: Exploring multi-task potentials of multi-modal large language models for chest x-ray interpretation","author":"Park","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b42","series-title":"Rad-dino: Exploring scalable medical image encoders beyond text supervision","author":"P\u00e9rez-Garc\u00eda","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b43","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"6","key":"10.1016\/j.media.2026.104304_b44","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104304_b45","series-title":"MICCAI Workshop on Deep Generative Models","first-page":"169","article-title":"Tibix: Leveraging temporal information for bidirectional x-ray and report generation","author":"Sanjeev","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b46","unstructured":"Santiesteban, S.S., Awais, M., Song, Y.-Z., Kittler, J., 2024. Enhancing radiology report generation: the impact of locally grounded vision and language training. In: 35th British Machine Vision Conference. Glasgow, UK: BMVA."},{"key":"10.1016\/j.media.2026.104304_b47","series-title":"Controllable chest X-ray report generation from longitudinal representations","author":"Serra","year":"2023"},{"key":"10.1016\/j.media.2026.104304_b48","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"111","article-title":"Contrastive knowledge-guided large language models for medical report generation","author":"Sha","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b49","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1109\/RBME.2024.3408456","article-title":"Automated radiology report generation: A review of recent advances","volume":"18","author":"Sloan","year":"2024","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"10.1016\/j.media.2026.104304_b50","series-title":"CheXbert: combining automatic labelers and expert annotations for accurate radiology report labeling using BERT","author":"Smit","year":"2020"},{"key":"10.1016\/j.media.2026.104304_b51","series-title":"DDaTR: Dynamic difference-aware temporal residual network for longitudinal radiology report generation","author":"Song","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b52","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., Faghri, F., Li, C.-L., Koc, C., True, N., Antony, A., Santhanam, G., Gabriel, J., Grasch, P., Tuzel, O., et al., 2025. Fastvlm: Efficient vision encoding for vision language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 19769\u201319780.","DOI":"10.1109\/CVPR52734.2025.01841"},{"key":"10.1016\/j.media.2026.104304_b53","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104304_b54","series-title":"European Conference on Computer Vision","first-page":"183","article-title":"Hergen: Elevating radiology report generation with longitudinal data","author":"Wang","year":"2024"},{"issue":"3","key":"10.1016\/j.media.2026.104304_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2023.100033","article-title":"R2gengpt: Radiology report generation with frozen llms","volume":"1","author":"Wang","year":"2023","journal-title":"Meta-Radiology"},{"key":"10.1016\/j.media.2026.104304_b56","first-page":"8250","article-title":"Llm-rg4: Flexible and factual radiology report generation across diverse input contexts","volume":"vol. 39","author":"Wang","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b57","unstructured":"Wu, J.T., Agu, N.N., Lourentzou, I., Sharma, A., Paguio, J.A., Yao, J.S., Dee, E.C., Mitchell, W., Kashyap, S., Giovannini, A., et al., 2021. Chest imagenome dataset for clinical reasoning. arXiv preprint arXiv:2108.00316."},{"key":"10.1016\/j.media.2026.104304_b58","doi-asserted-by":"crossref","unstructured":"Xue, L., Shu, M., Awadalla, A., Wang, J., Yan, A., Purushwalkam, S., Zhou, H., Prabhu, V., Dai, Y., Ryoo, M.S., et al., 2024. xgen-mm (blip-3): A family of open large multimodal models. arXiv preprint arXiv:2408.08872.","DOI":"10.1109\/ICCVW69036.2025.00644"},{"key":"10.1016\/j.media.2026.104304_b59","article-title":"Spatio-temporal and retrieval-augmented modelling for chest X-Ray report generation","author":"Yang","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"9","key":"10.1016\/j.media.2026.104304_b60","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2023.100802","article-title":"Evaluating progress in automatic chest x-ray radiology report generation","volume":"4","author":"Yu","year":"2023","journal-title":"Patterns"},{"key":"10.1016\/j.media.2026.104304_b61","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"152","article-title":"Diff-RRG: Longitudinal disease-wise patch difference as guidance for LLM-based radiology report generation","author":"Yun","year":"2025"},{"key":"10.1016\/j.media.2026.104304_b62","series-title":"Libra: Leveraging temporal images for biomedical radiology analysis","author":"Zhang","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b63","series-title":"MedVersa: A generalist foundation model for medical image interpretation","author":"Zhou","year":"2024"},{"key":"10.1016\/j.media.2026.104304_b64","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"189","article-title":"Utilizing longitudinal chest x-rays and reports to pre-fill radiology reports","author":"Zhu","year":"2023"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003737?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526003737?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T03:07:45Z","timestamp":1793934465000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526003737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":64,"alternative-id":["S1361841526003737"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104304","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A review of longitudinal radiology report generation: Dataset composition, methods, and performance evaluation","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104304","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104304"}}