{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T21:43:46Z","timestamp":1792014226857,"version":"4.4.0"},"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:00:00Z","timestamp":1744675200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["733174"],"award-info":[{"award-number":["733174"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000200","name":"United States Agency for International Development","doi-asserted-by":"publisher","award":["72044020FA00001"],"award-info":[{"award-number":["72044020FA00001"]}],"id":[{"id":"10.13039\/100000200","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Stop TB Partnership \/ TB REACH","award":["STBP\/TBREACH\/GSA\/W6-42"],"award-info":[{"award-number":["STBP\/TBREACH\/GSA\/W6-42"]}]},{"name":"Stop TB Partnership \/ TB REACH","award":["STBP\/TBREACH\/GSA\/W6SU-09"],"award-info":[{"award-number":["STBP\/TBREACH\/GSA\/W6SU-09"]}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>New versions of computer-aided detection (CAD) software for chest X-ray (CXR) interpretation during tuberculosis (TB) screening are regularly released which purport to have incremental performance gains. No studies have independently assessed differences in software performance between the World Health Organization recommended INSIGHT CXR software (Lunit, South Korea). A well-characterized Digital Imaging and Communications in Medicine (DICOM) test library was compiled using data from a community-based TB screening initiative in Ho Chi Minh City, Viet Nam. The performance of Lunit CAD software versions 3.1.0.0 and 3.9.0.1 (newer version) were compared by measuring the area under the receiver operating characteristic curve (AUC), stratified by key clinical and demographic variables and using Xpert MTB\/RIF Ultra (Ultra) test results as the reference standard. Median abnormality scores were compared using the Wilcoxon signed-rank test and performance characteristics were compared at clinically-relevant cut-off thresholds (e.g., 90% sensitivity) between the versions. The DICOM test library contained 2,708 participants, of whom 10.3% had a <jats:italic>Mycobacterium tuberculosis<\/jats:italic> (MTB) positive Ultra test result. The newer software version had a significantly higher AUC than its predecessor (AUC 0.76 vs 0.78, p = 0.029), and performed significantly better among people with a past history of TB (AUC 0.67 vs 0.73, p = 0.003), older individuals (0.75 vs 0.77, p = 0.040) and males (0.73 vs 0.76, p = 0.008). When using an cut-off threshold optimized for the older software version, the newer software was significantly less accurate than its predecessors. However, when the cut-off threshold was re-calibrated, there were no significant differences in sensitivity and specificity between the software versions. Although INSIGHT CXR v3.9.0.1 has some significantly improved performance characteristics compared to its predecessor, further studies should assess how these performance differences translate into real-world improvements during TB screening. As new CAD software versions are rolled out, cut-off thresholds must be re-calibrated to ensure the continued accuracy of CXR interpretation.<\/jats:p>","DOI":"10.1371\/journal.pdig.0000813","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T17:21:23Z","timestamp":1744737683000},"page":"e0000813","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["Comparison of different Lunit INSIGHT CXR software versions when reading chest radiographs for tuberculosis"],"prefix":"10.1371","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1380-8300","authenticated-orcid":true,"given":"Andrew J.","family":"Codlin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luan N. Q.","family":"Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thang P.","family":"Dao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachel J.","family":"Forse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ha T. M.","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan H.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hoa B.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luong V.","family":"Dinh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristi","family":"Sidney Annerstedt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2681-4139","authenticated-orcid":true,"given":"Johan","family":"Lundin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Knut","family":"L\u00f6nnroth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,15]]},"reference":[{"issue":"11","key":"pdig.0000813.ref001","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1111\/tmi.13485","article-title":"National tuberculosis prevalence surveys in Africa, 2008-2016: an overview of results and lessons learned","volume":"25","author":"I Law","year":"2020","journal-title":"Trop Med Int Health"},{"issue":"9","key":"pdig.0000813.ref002","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1111\/tmi.12534","article-title":"National tuberculosis prevalence surveys in Asia, 1990-2012: an overview of results and lessons learned","volume":"20","author":"I Onozaki","year":"2015","journal-title":"Trop Med Int Health"},{"issue":"5","key":"pdig.0000813.ref003","doi-asserted-by":"crossref","first-page":"1700364","DOI":"10.1183\/13993003.00364-2017","article-title":"The long and winding road of chest radiography for tuberculosis detection","volume":"49","author":"C Miller","year":"2017","journal-title":"Eur Respir J"},{"issue":"3","key":"pdig.0000813.ref004","doi-asserted-by":"crossref","first-page":"163","DOI":"10.3390\/tropicalmed6030163","article-title":"Early evaluation of an ultra-portable X-ray system for tuberculosis active case finding","volume":"6","author":"LNQ Vo","year":"2021","journal-title":"Trop Med Infect Dis"},{"issue":"6","key":"pdig.0000813.ref005","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1183\/13993003.01064-2015","article-title":"Use of chest radiography in the 22 highest tuberculosis burden countries","volume":"46","author":"T Pande","year":"2015","journal-title":"Eur Respir J"},{"issue":"4","key":"pdig.0000813.ref006","doi-asserted-by":"crossref","first-page":"e136","DOI":"10.1016\/S1470-2045(20)30751-8","article-title":"Medical imaging and nuclear medicine: a Lancet Oncology Commission","volume":"22","author":"H Hricak","year":"2021","journal-title":"Lancet Oncol"},{"key":"pdig.0000813.ref007","volume-title":"WHO consolidated guidelines on tuberculosis. Module 2: screening \u2013 systematic screening for tuberculosis disease","year":"2021"},{"issue":"12","key":"pdig.0000813.ref008","doi-asserted-by":"crossref","first-page":"e0000404","DOI":"10.1371\/journal.pdig.0000404","article-title":"Implementing a chest X-ray artificial intelligence tool to enhance tuberculosis screening in India: lessons learned","volume":"2","author":"S Vijayan","year":"2023","journal-title":"PLOS Digit Health"},{"issue":"11","key":"pdig.0000813.ref009","doi-asserted-by":"crossref","first-page":"488","DOI":"10.3390\/tropicalmed8110488","article-title":"Computer-aided detection for chest radiography to improve the quality of tuberculosis diagnosis in Vietnam\u2019s district health facilities: an implementation study","volume":"8","author":"AL Innes","year":"2023","journal-title":"Trop Med Infect Dis"},{"issue":"4","key":"pdig.0000813.ref010","first-page":"1","article-title":"Active case finding to detect symptomatic and subclinical pulmonary tuberculosis disease: implementation of computer-aided detection for chest radiography in Viet Nam","volume":"15","author":"AL Innes","year":"2024","journal-title":"Western Pac Surveill Response J"},{"issue":"3","key":"pdig.0000813.ref011","doi-asserted-by":"crossref","first-page":"e2400024","DOI":"10.9745\/GHSP-D-24-00024","article-title":"An effective health system approach to end TB: implementing the double X strategy in Vietnam","volume":"12","author":"AL Innes","year":"2024","journal-title":"Glob Health Sci Pract"},{"issue":"1","key":"pdig.0000813.ref012","doi-asserted-by":"crossref","first-page":"23895","DOI":"10.1038\/s41598-021-03265-0","article-title":"Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis","volume":"11","author":"AJ Codlin","year":"2021","journal-title":"Sci Rep"},{"issue":"1","key":"pdig.0000813.ref013","doi-asserted-by":"crossref","first-page":"15000","DOI":"10.1038\/s41598-019-51503-3","article-title":"Using artificial intelligence to read chest radiographs for tuberculosis detection: a multi-site evaluation of the diagnostic accuracy of three deep learning systems","volume":"9","author":"ZZ Qin","year":"2019","journal-title":"Sci Rep"},{"issue":"9","key":"pdig.0000813.ref014","doi-asserted-by":"crossref","first-page":"e543","DOI":"10.1016\/S2589-7500(21)00116-3","article-title":"Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms","volume":"3","author":"ZZ Qin","year":"2021","journal-title":"Lancet Digit Health"},{"issue":"7","key":"pdig.0000813.ref015","doi-asserted-by":"crossref","first-page":"e0000402","DOI":"10.1371\/journal.pgph.0000402","article-title":"Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: analysis of an international, multicenter migrants screening study","volume":"3","author":"SM Gelaw","year":"2023","journal-title":"PLOS Glob Public Health"},{"key":"pdig.0000813.ref016","doi-asserted-by":"crossref","first-page":"105159","DOI":"10.1016\/j.ijmedinf.2023.105159","article-title":"Benchmarking the diagnostic test accuracy of certified AI products for screening pulmonary tuberculosis in digital chest radiographs: preliminary evidence from a rapid review and meta-analysis","volume":"177","author":"D Hua","year":"2023","journal-title":"Int J Med Inform"},{"key":"pdig.0000813.ref017","first-page":"100388","article-title":"Evaluation of chest X-ray with automated interpretation algorithms for mass tuberculosis screening in prisons: a cross-sectional study","volume":"17","author":"TR Soares","year":"2022","journal-title":"Lancet Reg Health Am"},{"key":"pdig.0000813.ref018","article-title":"Computer-aided detection (CAD) software versus radiologists from multiple countries: a comparison of tuberculosis detection from chest X-rays","author":"ZZ Qin","year":"2025","journal-title":"Research Square"},{"issue":"1","key":"pdig.0000813.ref019","doi-asserted-by":"crossref","first-page":"5492","DOI":"10.1038\/s41598-020-62148-y","article-title":"Computer aided detection of tuberculosis on chest radiographs: an evaluation of the CAD4TB v6 system","volume":"10","author":"K Murphy","year":"2020","journal-title":"Sci Rep"},{"issue":"6","key":"pdig.0000813.ref020","doi-asserted-by":"crossref","first-page":"e0000067","DOI":"10.1371\/journal.pdig.0000067","article-title":"Comparing different versions of computer-aided detection products when reading chest X-rays for tuberculosis","volume":"1","author":"ZZ Qin","year":"2022","journal-title":"PLOS Digit Health"},{"issue":"2","key":"pdig.0000813.ref021","doi-asserted-by":"crossref","first-page":"157","DOI":"10.5588\/ijtld.22.0437","article-title":"CAD4TB software updates: different triaging thresholds require caution by users and regulation by authorities","volume":"27","author":"J Fehr","year":"2023","journal-title":"Int J Tuberc Lung Dis"},{"issue":"1","key":"pdig.0000813.ref022","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1186\/s44263-023-00033-2","article-title":"Early user perspectives on using computer-aided detection software for interpreting chest X-ray images to enhance access and quality of care for persons with tuberculosis","volume":"1","author":"J Creswell","year":"2023","journal-title":"BMC Glob Public Health"},{"key":"pdig.0000813.ref023","volume-title":"Determining the local calibration of computer-assisted detection (CAD) thresholds and other parameters: A toolkit to support the effective use of CAD for TB screening","year":"2021"},{"key":"pdig.0000813.ref024","volume-title":"Screening and triage for TB using computer-aided detection (CAD) technology and ultra-portable X-Ray systems: a practical guide","year":"2019"},{"key":"pdig.0000813.ref025","volume-title":"High-priority target product profiles for new tuberculosis diagnostics: report of a consensus meeting","year":"2014"},{"issue":"3","key":"pdig.0000813.ref026","doi-asserted-by":"crossref","first-page":"2000343","DOI":"10.1183\/13993003.00343-2020","article-title":"Effect of history of tuberculosis on specificity of Xpert MTB\/RIF","volume":"56","author":"F Haraka","year":"2020","journal-title":"Eur Respir J"},{"key":"pdig.0000813.ref027","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.ijid.2022.05.037","article-title":"Diagnostic accuracy of a commercially available, deep learning-based chest X-ray interpretation software for detecting culture-confirmed pulmonary tuberculosis","volume":"122","author":"G Tavaziva","year":"2022","journal-title":"Int J Infect Dis"},{"issue":"1","key":"pdig.0000813.ref028","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1186\/s12889-020-09042-4","article-title":"A comparative impact evaluation of two human resource models for community-based active tuberculosis case finding in Ho Chi Minh City, Viet Nam","volume":"20","author":"LNQ Vo","year":"2020","journal-title":"BMC Public Health"},{"issue":"4","key":"pdig.0000813.ref029","doi-asserted-by":"crossref","first-page":"185","DOI":"10.3390\/tropicalmed5040185","article-title":"An evaluation of programmatic community-based chest X-ray screening for tuberculosis in Ho Chi Minh City, Vietnam","volume":"5","author":"LH Nguyen","year":"2020","journal-title":"Trop Med Infect Dis"},{"issue":"3","key":"pdig.0000813.ref030","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1177\/1536867X0200200307","article-title":"From the help desk: comparing areas under receiver operating characteristic curves from two or more probit or logit models","volume":"2","author":"MA Cleves","year":"2002","journal-title":"Stata J"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T17:21:34Z","timestamp":1744737694000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000813"}},"subtitle":[],"editor":[{"given":"Peter H","family":"Charlton","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,15]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0000813","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,15]]}}}