{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T20:29:20Z","timestamp":1786566560065,"version":"build-2736575974"},"reference-count":68,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T00:00:00Z","timestamp":1785024000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T00:00:00Z","timestamp":1785024000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2026,9]]},"abstract":"ABSTRACT<\/jats:title>\n \n Background<\/jats:title>\n Nasopharyngeal carcinoma (NPC) can be detected early on MRI, but adoption for screening is limited by a shortage of experienced specialists. MRI artificial intelligence (AI) algorithms for diagnosing NPC in the literature may address this, but most studies focus on routine clinical care, and their applicability in screening requires close examination.<\/jats:p>\n <\/jats:sec>\n \n Purpose<\/jats:title>\n To (i) evaluate the diagnostic performance of AI for NPC detection, (ii) analyze the impact of study protocols, and (iii) assess the applicability of existing studies to NPC screening.<\/jats:p>\n <\/jats:sec>\n \n Study Type<\/jats:title>\n Systematic review.<\/jats:p>\n <\/jats:sec>\n \n Population<\/jats:title>\n Thirty\u2010eight studies were included, including a total of 23,398 patients (20,693 NPC and 2705 non\u2010NPC).<\/jats:p>\n <\/jats:sec>\n \n Fieldstrength<\/jats:title>\n 1.5\u2009T to 3.0\u2009T.<\/jats:p>\n <\/jats:sec>\n \n Assessment<\/jats:title>\n Following PRISMA guidelines, PubMed, Scopus, and Embase records from January 1, 2009 to August 16, 2025 were screened by two independent reviewers for studies on NPC detection, localization, and\/or diagnosis using MRI. Included studies were reviewed for applicability and risk of bias. Lesion\u2010localization performance (Dice similarity score [DSC]) and NPC vs. non\u2010NPC discrimination (sensitivity\/specificity) were extracted and summarized. Subgroup analyses assessed the impact of intravenous contrast on AI performance.<\/jats:p>\n <\/jats:sec>\n \n Statistical Tests<\/jats:title>\n \n Meta\u2010analysis used standard random\u2010effects univariate restricted maximum likelihood model and hierarchical summary receiver operator characteristics for performance pooling and subgroup analysis, taking\n p<\/jats:italic>\n value <\u20090.05 as significance.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Pooled performance from 30 localization and 6 discrimination studies was DSC\u2009=\u20090.80 (CI: 0.78\u20130.82) and sensitivity\/specificity\u2009=\u200997.1% (CI: 88.0%\u201399.3%)\/87.8% (CI: 78.9%\u201393.2%), respectively. Intravenous contrast did not significantly affect AI performance for either task (\n p<\/jats:italic>\n \u2009>\u20090.05). Only seven studies were fully applicable to screening.\n <\/jats:p>\n <\/jats:sec>\n \n Data Conclusion<\/jats:title>\n AI\u2010driven NPC screening using MRI is feasible at high sensitivity. Using non\u2010contrast MRI did not significantly impact AIs' performance. However, applicability and the suboptimal ratio of NPC: non\u2010NPC patients remain the weaknesses of existing studies, warranting further investigation with cohorts that better reflect the screening scenario.<\/jats:p>\n <\/jats:sec>\n \n Systematic Review Registration<\/jats:title>\n The systematic review protocol of this system is registered with the Inplasy registry (Ref. INPLASY202570076).<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/jmri.70445","type":"journal-article","created":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T20:40:11Z","timestamp":1785098411000},"page":"593-615","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Systematic Review of\n AI<\/scp>\n \u2010Driven Applications for Screening Nasopharyngeal Carcinoma Using\n MRI<\/scp>"],"prefix":"10.1002","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6047-4609","authenticated-orcid":false,"given":"Lun M.","family":"Wong","sequence":"first","affiliation":[{"name":"Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"},{"name":"The CU Lab of AI in Radiology, Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0503-8510","authenticated-orcid":false,"given":"Ho Sang","family":"Leung","sequence":"additional","affiliation":[{"name":"Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"},{"name":"Department of Imaging and Interventional Radiology Prince of Wales Hospital, Hospital Authority Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2386-2431","authenticated-orcid":false,"given":"Zuyao","family":"Yang","sequence":"additional","affiliation":[{"name":"JC School of Public Health and Primary Care, The Chinese University of Hong Kong Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1250-9070","authenticated-orcid":false,"given":"Yip Man","family":"Tsang","sequence":"additional","affiliation":[{"name":"Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuet Ting","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiffany Y.","family":"So","sequence":"additional","affiliation":[{"name":"Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5280-8349","authenticated-orcid":false,"given":"Ann D.","family":"King","sequence":"additional","affiliation":[{"name":"Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1155-4389","authenticated-orcid":false,"given":"Qi Yong H.","family":"Ai","sequence":"additional","affiliation":[{"name":"Department of Imaging and Interventional Radiology Faculty of Medicine, The Chinese University of Hong Kong, Prince of Wales Hospital Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,26]]},"reference":[{"key":"e_1_2_10_2_1","unstructured":"Authority H \u201cTop Five Cancers By Age \u201d 2024 accessed May 28 2024 https:\/\/www3.ha.org.hk\/cancereg\/topfive.html."},{"key":"e_1_2_10_3_1","volume-title":"Singapore Cancer Registry Annual Report 2021","author":"Cheong K.","year":"2023"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.3747\/co.20.1456"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1701717"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2301496"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1056\/EVIDoa2200309"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdz231"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djad012"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.10101241"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A4456"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdz106"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.33552"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djad260"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2020.104862"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-021-01092-x"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-020-07451-y"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(22)00186-8"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11091523"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12093077"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11050504"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2023.3269776"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-155-8-201110180-00009"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200029"},{"key":"e_1_2_10_25_1","first-page":"295","volume-title":"The Handbook of Research Synthesis and Meta\u2010Analysis","author":"Raudenbush S. W.","year":"2009"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-055336"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1080\/03610918.2018.1489553"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-135"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v036.i03"},{"key":"e_1_2_10_30_1","unstructured":"P.Doebler \u201cmada: Meta\u2010Analysis of Diagnostic Accuracy \u201d 2022. accessed June 12 2024 https:\/\/CRAN.R\u2010project.org\/package=mada."},{"key":"e_1_2_10_31_1","first-page":"2825","article-title":"Scikit\u2010Learn: Machine Learning in Python","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28112"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106702"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12102478"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14143433"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-024-01544-0"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019182012"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.00166"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims-21-196"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102381"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108368"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2023.109480"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1377366"},{"issue":"3","key":"e_1_2_10_44_1","first-page":"2511","article-title":"Automated Nasopharyngeal Carcinoma Segmentation in Magnetic Resonance Images by Combination of Convolutional Neural Networks and Graph Cut","volume":"16","author":"Ma Z.","year":"2018","journal-title":"Experimental and Therapeutic Medicine"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-020-04708-y"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.816672"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e30763"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/jcmm.18355"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2022.1068713"},{"issue":"4","key":"e_1_2_10_50_1","first-page":"151","article-title":"MRF\u2010RFS: A Modified Random Forest Recursive Feature Selection Algorithm for Nasopharyngeal Carcinoma Segmentation","volume":"59","author":"Fei Y.","year":"2020","journal-title":"Methods of Information in Medicine"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/9128527"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104053"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12061352"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2022.03.031"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3144274"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21237877"},{"key":"e_1_2_10_57_1","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/7562140"},{"key":"e_1_2_10_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.002"},{"key":"e_1_2_10_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102525"},{"key":"e_1_2_10_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.11.064"},{"key":"e_1_2_10_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3411099"},{"key":"e_1_2_10_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.085"},{"key":"e_1_2_10_63_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1190075"},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22155875"},{"key":"e_1_2_10_65_1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3790269"},{"key":"e_1_2_10_66_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/2033806"},{"key":"e_1_2_10_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102471"},{"key":"e_1_2_10_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-022-02941-w"},{"key":"e_1_2_10_69_1","doi-asserted-by":"publisher","DOI":"10.1177\/01945998211029617"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70445","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.70445","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T19:49:33Z","timestamp":1786564173000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.70445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,26]]},"references-count":68,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/jmri.70445"],"URL":"https:\/\/doi.org\/10.1002\/jmri.70445","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,26]]},"assertion":[{"value":"2026-03-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}