{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T19:10:28Z","timestamp":1772219428564,"version":"3.50.1"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CAMS Innovation Fund for Medical Sciences","award":["2021-I2M-1-037"],"award-info":[{"award-number":["2021-I2M-1-037"]}]},{"name":"National High Level Hospital Clinical Research Funding","award":["2022-NHLHCRF-YS-02"],"award-info":[{"award-number":["2022-NHLHCRF-YS-02"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>China accounted for 6.8% of global TB cases, and most patients are first diagnosed in general hospitals where chest X-rays (CXR) are widely used for early TB detection. To facilitate diagnosis in resource-limited settings, our study evaluates a CNN-based AI model trained on Chinese CXR data (JF CXR-1 v2), including its experimental application to CT localizer images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>This retrospective study was conducted at China-Japan Friendship Hospital, including 290 CXR images and 433 CT localizer images from TB patients diagnosed between 2017 and 2021. The AI algorithm\u2019s diagnostic performance was assessed using sensitivity, specificity, accuracy, Kappa value, and AUC from ROC analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The AI algorithm demonstrated high diagnostic performance on CXR images, achieving an AUC of 0.960 with 91.7% sensitivity and 92.7% specificity in bacteriologically confirmed TB cases. On localizer images of the chest CT, while the performance was more modest (AUC 0.719), a significant correlation between CXR and CT predictions in 105 paired cases suggests potential for cross-modality application with further validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Discussion &amp; conclusions<\/jats:title>\n                    <jats:p>The algorithm shows decent diagnostic capability for the CXR samples in this study. This AI algorithm developed based on CXR can, to some extent, identify the imaging features of pulmonary TB when applied to localizer images of chest CT.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0338810","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T18:25:49Z","timestamp":1772216749000},"page":"e0338810","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Validating the effectiveness of an AI algorithm for pulmonary tuberculosis screening using chest X-ray: Retrospective study and test accuracy with localizer images of the chest CT"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0516-7104","authenticated-orcid":true,"given":"Yixiao","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6277-4675","authenticated-orcid":true,"given":"Xiaojing","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingtao","family":"Chong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lintao","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"pone.0338810.ref001","volume-title":"Global tuberculosis report 2024","author":"World Health Organization","year":"2024"},{"issue":"6","key":"pone.0338810.ref002","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":"3","key":"pone.0338810.ref003","first-page":"308","article-title":"Tuberculosis: common questions and answers","volume":"106","author":"H Hartman-Adams","year":"2022","journal-title":"Am Fam Physician"},{"issue":"9","key":"pone.0338810.ref004","article-title":"Identification and management of tuberculosis","volume":"61","author":"AF Jerant","year":"2000","journal-title":"Am Fam Physician"},{"issue":"5","key":"pone.0338810.ref005","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1093\/cid\/ciy967","article-title":"Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs","volume":"69","author":"EJ Hwang","year":"2019","journal-title":"Clin Infect Dis"},{"issue":"2","key":"pone.0338810.ref006","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1148\/radiol.2017162326","article-title":"Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks","volume":"284","author":"P Lakhani","year":"2017","journal-title":"Radiology"},{"issue":"8","key":"pone.0338810.ref007","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1007\/s00247-019-04408-2","article-title":"Automated semantic labeling of pediatric musculoskeletal radiographs using deep learning","volume":"49","author":"PH Yi","year":"2019","journal-title":"Pediatr Radiol"},{"issue":"11","key":"pone.0338810.ref008","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1007\/s10916-022-01870-8","article-title":"Advances in deep learning for tuberculosis screening using chest X-rays: the last 5 years review","volume":"46","author":"KC Santosh","year":"2022","journal-title":"J Med Syst"},{"key":"pone.0338810.ref009","unstructured":"World Health Organization. World Health Organization recommendations in using CAD; 2024 [cited 2025 Jan 24]; Available from: https:\/\/delft.care\/world-health-organization-recommendations-in-using-cad\/"},{"issue":"1","key":"pone.0338810.ref010","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.21037\/qims-23-1223","article-title":"Chinese expert consensus on imaging diagnosis of drug-resistant pulmonary tuberculosis","volume":"14","author":"C-J Xu","year":"2024","journal-title":"Quant Imaging Med Surg"},{"issue":"1","key":"pone.0338810.ref011","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1186\/s12879-023-08386-7","article-title":"Computed tomography findings in patients with pulmonary tuberculosis and diabetes at an infectious disease hospital in China: a retrospective cross-sectional study","volume":"23","author":"Q Yang","year":"2023","journal-title":"BMC Infect Dis"},{"issue":"6","key":"pone.0338810.ref012","doi-asserted-by":"crossref","first-page":"4082","DOI":"10.1007\/s10489-020-02051-1","article-title":"A deep learning system that generates quantitative CT reports for diagnosing pulmonary Tuberculosis","volume":"51","author":"X Li","year":"2020","journal-title":"Appl Intell"},{"key":"pone.0338810.ref013","volume-title":"WS 288-2017: diagnostic criteria for pulmonary tuberculosis","author":"National Health and Family Planning Commission of the People\u2019s Republic of China","year":"2017"},{"key":"pone.0338810.ref014","article-title":"Revisiting the timetable of tuberculosis","volume":"362","author":"MA Behr","year":"2018","journal-title":"BMJ"},{"issue":"1","key":"pone.0338810.ref015","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":"1","key":"pone.0338810.ref016","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1038\/s41746-021-00471-y","article-title":"Computer-aided interpretation of chest radiography reveals the spectrum of tuberculosis in rural South Africa","volume":"4","author":"J Fehr","year":"2021","journal-title":"NPJ Digit Med"},{"issue":"5","key":"pone.0338810.ref017","doi-asserted-by":"crossref","first-page":"367","DOI":"10.5588\/ijtld.22.0687","article-title":"The rise of artificial intelligence reading of chest X-rays for enhanced TB diagnosis and elimination","volume":"27","author":"C Geric","year":"2023","journal-title":"Int J Tuberc Lung Dis"},{"key":"pone.0338810.ref018","author":"World Health Organization","year":"2021","journal-title":"WHO operational handbook on tuberculosis, in Module 2: screening"},{"issue":"12","key":"pone.0338810.ref019","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0277393","article-title":"Economic analysis of different throughput scenarios and implementation strategies of computer-aided detection software as a screening and triage test for pulmonary TB","volume":"17","author":"S Bashir","year":"2022","journal-title":"PLoS One"},{"issue":"1","key":"pone.0338810.ref020","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"},{"issue":"6","key":"pone.0338810.ref021","doi-asserted-by":"crossref","first-page":"184","DOI":"10.3390\/diseases13060184","article-title":"Integration of AI and ML in tuberculosis (TB) management: from diagnosis to drug discovery","volume":"13","author":"S Memon","year":"2025","journal-title":"Diseases"},{"issue":"1","key":"pone.0338810.ref022","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s15010-023-02135-3","article-title":"Blazing the trail for innovative tuberculosis diagnostics","volume":"52","author":"S Yerlikaya","year":"2024","journal-title":"Infection"},{"issue":"12","key":"pone.0338810.ref023","doi-asserted-by":"crossref","first-page":"533","DOI":"10.5588\/ijtldopen.24.0428","article-title":"Detection of other pathologies when utilising computer-assisted digital solutions for TB screening","volume":"1","author":"J Sebastian","year":"2024","journal-title":"IJTLD Open"},{"issue":"9","key":"pone.0338810.ref024","article-title":"Can AI technologies close the diagnostic gap in tuberculosis?","volume":"3","author":"C Tzelios","year":"2021","journal-title":"Lancet Digit Health"},{"key":"pone.0338810.ref025","volume-title":"WHO consolidated guidelines on tuberculosis: Module 2: screening: systematic screening for tuberculosis disease","author":"World Health Organization","year":"2021"},{"key":"pone.0338810.ref026","volume-title":"High priority target product profiles for new tuberculosis diagnostics: Report of a consensus meeting","author":"World Health Organization","year":"2014"},{"issue":"9","key":"pone.0338810.ref027","article-title":"Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software","volume":"6","author":"ZZ Qin","year":"2024","journal-title":"Lancet Digit Health"},{"issue":"6","key":"pone.0338810.ref028","first-page":"559","article-title":"Limitations of the Xpert-MTB\/RIF\u00ae assay in the initial diagnosis of tuberculosis in the context of a rural hospital in Ethiopia","volume":"35","author":"B Comeche","year":"2022","journal-title":"Rev Esp Quimioter"},{"issue":"4","key":"pone.0338810.ref029","doi-asserted-by":"crossref","DOI":"10.1093\/ofid\/ofab025","article-title":"Performance of GeneXpert MTB\/RIF for diagnosing tuberculosis among symptomatic household contacts of index patients in South Africa","volume":"8","author":"K Velen","year":"2021","journal-title":"Open Forum Infect Dis"},{"issue":"4","key":"pone.0338810.ref030","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1007\/s00330-021-08365-z","article-title":"A fully automatic artificial intelligence-based CT image analysis system for accurate detection, diagnosis, and quantitative severity evaluation of pulmonary tuberculosis","volume":"32","author":"C Yan","year":"2022","journal-title":"Eur Radiol"},{"issue":"1","key":"pone.0338810.ref031","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1007\/s11547-022-01580-8","article-title":"Development and validation of a 3D-convolutional neural network model based on chest CT for differentiating active pulmonary tuberculosis from community-acquired pneumonia","volume":"128","author":"D Han","year":"2023","journal-title":"Radiol Med"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0338810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T18:25:56Z","timestamp":1772216756000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0338810"}},"subtitle":[],"editor":[{"given":"Krit","family":"Pongpirul","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0338810","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]}}}