{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T07:07:31Z","timestamp":1790060851406,"version":"4.0.1"},"reference-count":18,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515011252"],"award-info":[{"award-number":["2022A1515011252"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2025,12]]},"abstract":"ABSTRACT<\/jats:title>\n \n Background<\/jats:title>\n Accurate tumor staging and treatment response evaluation (TRE) are critical for nasopharyngeal carcinoma (NPC) clinical decisions. Conventional methods relying on manual imaging analysis are expertise\u2010dependent, time\u2010consuming, and prone to inter\u2010observer variability and errors.<\/jats:p>\n <\/jats:sec>\n \n Purpose<\/jats:title>\n To assess the performance of two large language models (LLMs): ChatGPT\u20104o\u2010latest and DeepSeek\u2010V3\u20100324 in automating T, N staging and TRE for NPC patients.<\/jats:p>\n <\/jats:sec>\n \n Study Type<\/jats:title>\n Retrospective.<\/jats:p>\n <\/jats:sec>\n \n Population<\/jats:title>\n Three hundred seven NPC patients from three centers (mean age: 45.5\u2009\u00b1\u200911.3\u2009years; 216 men, 91 women).<\/jats:p>\n <\/jats:sec>\n \n Field Strength\/Sequence<\/jats:title>\n All imaging was conducted using 3.0T or 1.5T scanners. The imaging sequence included axial T1\u2010weighted fast spin\u2010echo, T2\u2010weighted fast spin\u2010echo, T2\u2010weighted fat\u2010suppressed spin\u2010echo, and Contrast\u2010Enhanced T1\u2010weighted fast spin\u2010echo.<\/jats:p>\n <\/jats:sec>\n \n Assessment<\/jats:title>\n Two radiologists established the reference standards for TN staging at baseline and for TRE at two time points: post\u2010induction chemotherapy (TRE\u20101) and post\u2010concurrent chemoradiotherapy (TRE\u20102), based on the 9th version of AJCC\/UICC guidelines and the RECIST1.1 criteria. LLMs were via few\u2010shot chain\u2010of\u2010thought prompting and tested on 277 patients with 831 reports. Additionally, four radiologists independently assessed 68 cases both with and without the assistance of LLMs and compared the performance and efficiency in both conditions.<\/jats:p>\n <\/jats:sec>\n \n Statistical Tests<\/jats:title>\n \n McNemar\u2013Bowker test, Wilcoxon signed\u2013rank test.\n p<\/jats:italic>\n \u2009<\u20090.05 was considered statistically significant.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n DeepSeek\u2010V3\u20100324 significantly outperformed GPT\u20104o\u2010latest in TRE\u20101 staging (96.5% vs. 82.9%,\n p<\/jats:italic>\n \u2009<\u20090.001). For T staging (95.3% vs. 93.5%,\n p<\/jats:italic>\n \u2009=\u20090.24), N staging (93.8% vs. 89.6%,\n p<\/jats:italic>\n \u2009=\u20090.265), and TRE\u20102 (94.9% vs. 93.2%,\n p<\/jats:italic>\n \u2009=\u20090.556), the accuracy between DeepSeek\u2010V3\u20100324 and ChatGPT\u20104o\u2010latest showed no significant difference. DeepSeek\u2010V3\u20100324 also showed stronger agreement with expert annotation (\n \u03ba<\/jats:italic>\n \u2009=\u20090.85\u20130.90), compared to ChatGPT\u20104o\u2010latest (\n \u03ba<\/jats:italic>\n \u2009=\u20090.49\u20130.86). Significant improvements in time efficiency were observed across all radiologists with LLM assistance (\n p<\/jats:italic>\n \u2009<\u20090.001).\n <\/jats:p>\n <\/jats:sec>\n \n Data Conclusion<\/jats:title>\n LLMs, particularly DeepSeek\u2010V3\u20100324, can automate NPC TN staging and TRE with high accuracy, enhancing clinical efficiency. LLMs integration may improve diagnostic consistency, especially for junior clinicians.<\/jats:p>\n <\/jats:sec>\n \n Level of Evidence<\/jats:title>\n 3.<\/jats:p>\n <\/jats:sec>\n \n Technical Efficacy<\/jats:title>\n Stage 4.<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/jmri.70140","type":"journal-article","created":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T07:15:28Z","timestamp":1759562128000},"page":"1793-1801","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Application of Large Language Models in\n TN<\/scp>\n Staging and Treatment Response Evaluation for Patients With Nasopharyngeal Carcinoma: A Comparative Performance Analysis of\n ChatGPT<\/scp>\n \u20104o\u2010Latest and\n DeepSeek<\/scp>\n \u2010V3\u20100324"],"prefix":"10.1002","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7119-1417","authenticated-orcid":false,"given":"Yifan","family":"Yang","sequence":"first","affiliation":[{"name":"School of Medicine South China University of Technology Guangzhou China"},{"name":"Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China"},{"name":"Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengsheng","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Medicine South China University of Technology Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiqi","family":"Hou","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China"},{"name":"Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexin","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China"},{"name":"Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3296-9759","authenticated-orcid":false,"given":"Zaiyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8267-150X","authenticated-orcid":false,"given":"Changhong","family":"Liang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China"},{"name":"Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6391-1352","authenticated-orcid":false,"given":"Guangyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,10,4]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21881"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/cac2.12218"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2025.101942"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2008.10.026"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110367"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2017.08.005"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12510"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232640"},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16213621"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-024-01915-7"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/ksa.12628"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03727-2"},{"key":"e_1_2_6_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2025.104791"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2024.4354"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2024.101118"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aopr.2025.05.001"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231167"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T14:00:46Z","timestamp":1762869646000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.70140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,4]]},"references-count":18,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1002\/jmri.70140"],"URL":"https:\/\/doi.org\/10.1002\/jmri.70140","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,4]]},"assertion":[{"value":"2025-07-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}