{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:02:39Z","timestamp":1780534959054,"version":"3.54.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049803","type":"print"},{"value":"9783032049810","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04981-0_56","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T05:09:51Z","timestamp":1758258591000},"page":"594-604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SPEC-CXR: Advancing Clinical Safety Through Entity-Level Performance Evaluation of\u00a0Chest X-ray Report Generation"],"prefix":"10.1007","author":[{"given":"Jung Oh","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwoo","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junha","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurent","family":"Dillard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"van Sonsbeek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnaud A. A.","family":"Setio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeonsoo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donggeun","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taesoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"56_CR1","unstructured":"Bannur, S., et\u00a0al.: Maira-2: grounded radiology report generation. arXiv preprint arXiv:2406.04449 (2024)"},{"key":"56_CR2","doi-asserted-by":"publisher","unstructured":"Bodenreider, O.: The unified medical language system (UMLs): integrating biomedical terminology. Nucleic Acids Res. 32(Database issue), D267\u2013D270 (2004). https:\/\/doi.org\/10.1093\/nar\/gkh061","DOI":"10.1093\/nar\/gkh061"},{"key":"56_CR3","doi-asserted-by":"crossref","unstructured":"Bu, S., Li, T., Yang, Y., Dai, Z.: Instance-level expert knowledge and aggregate discriminative attention for radiology report generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14194\u201314204 (2024)","DOI":"10.1109\/CVPR52733.2024.01346"},{"key":"56_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797","volume":"66","author":"A Bustos","year":"2020","unstructured":"Bustos, A., Pertusa, A., Salinas, J.M., Iglesia-Vay\u00e1, M.: Padchest: a large chest x-ray image dataset with multi-label annotated reports. Med. Image Anal. 66, 101797 (2020)","journal-title":"Med. Image Anal."},{"key":"56_CR5","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":"56_CR6","unstructured":"Colvin, S., et al.: Pydantic (2025). https:\/\/github.com\/pydantic\/pydantic"},{"key":"56_CR7","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"56_CR8","unstructured":"Huang, A., Banerjee, O., Wu, K., Reis, E.P., Rajpurkar, P.: Fineradscore: a radiology report line-by-line evaluation technique generating corrections with severity scores. arXiv preprint arXiv:2405.20613 (2024)"},{"key":"56_CR9","doi-asserted-by":"crossref","unstructured":"Irvin, J., et\u00a0al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"56_CR10","unstructured":"Jain, S., et\u00a0al.: Radgraph: extracting clinical entities and relations from radiology reports. arXiv preprint arXiv:2106.14463 (2021)"},{"key":"56_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et\u00a0al.: Clear: a clinically-grounded tabular framework for radiology report evaluation. arXiv preprint arXiv:2505.16325 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.862"},{"key":"56_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"56_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Z., Liu, Y., Wang, L., Liu, L., Zhou, L.: Kargen: knowledge-enhanced automated radiology report generation using large language models. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 382\u2013392. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72086-4_36"},{"key":"56_CR14","unstructured":"Liu, J.: Instructor: structured outputs for LLMs (2024). https:\/\/github.com\/instructor-ai\/instructor"},{"key":"56_CR15","unstructured":"Liu, Y., et al.: Er2score: LLM-based explainable and customizable metric for assessing radiology reports with reward-control loss. arXiv preprint arXiv:2411.17301 (2024)"},{"key":"56_CR16","unstructured":"Liu, Y., et al.: Mrscore: evaluating radiology report generation with LLM-based reward system. arXiv preprint arXiv:2404.17778 (2024)"},{"key":"56_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhu, Z., Zheng, S., Zhao, Y., He, K., Zhao, Y.: From observation to concept: a flexible multi-view paradigm for medical report generation. IEEE Trans. Multimed. (2023)","DOI":"10.1109\/TMM.2023.3342691"},{"key":"56_CR18","unstructured":"Microsoft: Cxrreportgen: grounded report generation model for chest x-rays (2025). https:\/\/ai.azure.com\/catalog\/models\/CxrReportGen"},{"key":"56_CR19","doi-asserted-by":"crossref","unstructured":"Ostmeier, S., et\u00a0al.: Green: generative radiology report evaluation and error notation. arXiv preprint arXiv:2405.03595 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.21"},{"key":"56_CR20","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"},{"issue":"11","key":"56_CR21","doi-asserted-by":"publisher","first-page":"1678","DOI":"10.1038\/s41587-023-02079-x","volume":"42","author":"Z Piran","year":"2024","unstructured":"Piran, Z., Cohen, N., Hoshen, Y., Nitzan, M.: Disentanglement of single-cell data with biolord. Nat. Biotechnol. 42(11), 1678\u20131683 (2024)","journal-title":"Nat. Biotechnol."},{"key":"56_CR22","unstructured":"Saab, K., et\u00a0al.: Capabilities of Gemini models in medicine. arXiv preprint arXiv:2404.18416 (2024)"},{"key":"56_CR23","doi-asserted-by":"crossref","unstructured":"Tagawa, Y., et al.: Finding-centric structuring of Japanese radiology reports and analysis of performance gaps for multiple facilities. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track), pp. 70\u201385 (2025)","DOI":"10.18653\/v1\/2025.naacl-industry.7"},{"key":"56_CR24","unstructured":"Willard, B.T., Louf, R.: Efficient guided generation for LLMs. arXiv preprint arXiv:2307.09702 (2023)"},{"issue":"6","key":"56_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40555-y","volume":"18","author":"D Xu","year":"2024","unstructured":"Xu, D., et al.: Large language models for generative information extraction: A survey. Front. Comput. Sci. 18(6), 186357 (2024)","journal-title":"Front. Comput. Sci."},{"key":"56_CR26","doi-asserted-by":"crossref","unstructured":"Yu, F., et\u00a0al.: Evaluating progress in automatic chest x-ray radiology report generation. Patterns 4(9) (2023)","DOI":"10.1016\/j.patter.2023.100802"},{"key":"56_CR27","unstructured":"Yu, F., et\u00a0al.: Radiology report expert evaluation (rexval) dataset (2023)"},{"key":"56_CR28","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with BERT. arXiv preprint arXiv:1904.09675 (2019)"},{"key":"56_CR29","unstructured":"Zhang, X., et al.: Rexrank: a public leaderboard for AI-powered radiology report generation. arXiv preprint arXiv:2411.15122 (2024)"},{"key":"56_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Ratescore: a metric for radiology report generation. arXiv preprint arXiv:2406.16845 (2024)","DOI":"10.1101\/2024.06.24.24309405"},{"key":"56_CR31","unstructured":"Zhou, H.Y., Adithan, S., Acosta, J.N., Topol, E.J., Rajpurkar, P.: A generalist learner for multifaceted medical image interpretation. arXiv preprint arXiv:2405.07988 (2024)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04981-0_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:33:40Z","timestamp":1767418420000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04981-0_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049803","9783032049810"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04981-0_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}