{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T00:40:39Z","timestamp":1792197639836,"version":"4.4.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T00:00:00Z","timestamp":1792108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T00:00:00Z","timestamp":1792108800000},"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":["J Digit Imaging. Inform. med."],"DOI":"10.1007\/s10278-026-02403-2","type":"journal-article","created":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T23:56:06Z","timestamp":1792194966000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Building and Validating a Data-Governance Workflow for Artificial Intelligence\u2013Based Tuberculosis Detection from Chest Radiographs, and Quantifying the Impact of Data Leakage"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9508-9613","authenticated-orcid":false,"given":"Nhat An","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,16]]},"reference":[{"key":"2403_CR1","doi-asserted-by":"crossref","unstructured":"Kaufman S, Rosset S, Perlich C, Stitelman O: Leakage in data mining: formulation, detection, and avoidance. ACM Trans Knowl Discov Data 6:1-21, 2012","DOI":"10.1145\/2382577.2382579"},{"key":"2403_CR2","doi-asserted-by":"crossref","unstructured":"Tampu IE, Eklund A, Haj-Hosseini N: Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images. Sci Data 9:580, 2022","DOI":"10.1038\/s41597-022-01618-6"},{"key":"2403_CR3","doi-asserted-by":"crossref","unstructured":"Packh\u00e4user K, G\u00fcndel S, M\u00fcnster N, Syben C, Christlein V, Maier A: Deep learning-based patient re-identification is able to exploit the biometric nature of medical chest X-ray data. Sci Rep 12:14851, 2022","DOI":"10.1038\/s41598-022-19045-3"},{"key":"2403_CR4","doi-asserted-by":"publisher","unstructured":"Ivchenko A: CTSCAN: evaluation leakage in chest CT segmentation and a reproducible patient-disjoint benchmark. arXiv (preprint), https:\/\/doi.org\/10.48550\/arXiv.2604.15561, April 16, 2026","DOI":"10.48550\/arXiv.2604.15561"},{"key":"2403_CR5","doi-asserted-by":"crossref","unstructured":"Moassefi M, Rouzrokh P, Conte GM, Vahdati S, Fu T, Tahmasebi A, Younis M, Farahani K, Gentili A, Kline T, Kitamura FC, Huo Y, Kuanar S, Younis K, Erickson BJ, Faghani S: Reproducibility of deep learning algorithms developed for medical imaging analysis: a systematic review. J Digit Imaging 36:2306-2312, 2023","DOI":"10.1007\/s10278-023-00870-5"},{"key":"2403_CR6","doi-asserted-by":"crossref","unstructured":"Yu AC, Mohajer B, Eng J: External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol Artif Intell 4:e210064, 2022","DOI":"10.1148\/ryai.210064"},{"key":"2403_CR7","doi-asserted-by":"crossref","unstructured":"Hansun S, Argha A, Bakhshayeshi I, Wicaksana A, Alinejad-Rokny H, Fox GJ, Liaw ST, Celler BG, Marks GB: Diagnostic performance of artificial intelligence-based methods for tuberculosis detection: systematic review. J Med Internet Res 27:e69068, 2025","DOI":"10.2196\/69068"},{"key":"2403_CR8","doi-asserted-by":"publisher","unstructured":"Devasia J, Goswami H, Lakshminarayanan S, Rajaram M, Adithan S, Bharanidharan A: Deep learning classification of active tuberculosis using chest X-rays: efficacy of transfer learning and generalization performance of cross-population datasets. Research Square (preprint), https:\/\/doi.org\/10.21203\/rs.3.rs-1235165\/v1, January 14, 2022","DOI":"10.21203\/rs.3.rs-1235165\/v1"},{"key":"2403_CR9","doi-asserted-by":"crossref","unstructured":"Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK: Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med 15:e1002683, 2018","DOI":"10.1371\/journal.pmed.1002683"},{"key":"2403_CR10","doi-asserted-by":"crossref","unstructured":"Codlin AJ, Dao TP, Vo LNQ, Forse RJ, Van Truong V, Dang HM, Nguyen LH, Nguyen HB, Nguyen NV, Sidney-Annerstedt K, Squire B, L\u00f6nnroth K, Caws M: Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. Sci Rep 11:23895, 2021","DOI":"10.1038\/s41598-021-03265-0"},{"key":"2403_CR11","doi-asserted-by":"crossref","unstructured":"Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, Ghassemi M, Liu X, Reitsma JB, van Smeden M, Boulesteix AL, Camaradou JC, Celi LA, Denaxas S, Denniston AK, Glocker B, Golub RM, Harvey H, Heinze G, Hoffman MM, Kengne AP, Lam E, Lee N, Loder EW, Maier-Hein L, Mateen BA, McCradden MD, Oakden-Rayner L, Ordish J, Parnell R, Rose S, Singh K, Wynants L, Logullo P: TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385:e078378, 2024","DOI":"10.1136\/bmj-2023-078378"},{"key":"2403_CR12","unstructured":"Tejani AS, Klontzas ME, Gatti AA, Mongan JT, Moy L, Park SH, Kahn CE, CLAIM 2024 Update Panel: Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 update. Radiol Artif Intell 6:e240300, 2024"},{"key":"2403_CR13","doi-asserted-by":"crossref","unstructured":"Sounderajah V, Guni A, Liu X, Collins GS, Karthikesalingam A, Markar SR, Golub RM, Denniston AK, Shetty S, Moher D, Bossuyt PM, Darzi A, Ashrafian H, STARD-AI Steering Committee, STARD-AI Consensus Group: The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence. Nat Med 31:3283-3289, 2025","DOI":"10.1038\/s41591-025-03953-8"},{"key":"2403_CR14","unstructured":"Jaeger S, Candemir S, Antani S, W\u00e1ng YXJ, Lu PX, Thoma G: Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quant Imaging Med Surg 4:475-477, 2014"},{"key":"2403_CR15","doi-asserted-by":"crossref","unstructured":"Rahman T, Khandakar A, Kadir MA, Islam KR, Islam KF, Mazhar R, Hamid T, Islam MT, Kashem S, Mahbub ZB, Ayari MA, Chowdhury MEH: Reliable tuberculosis detection using chest X-ray with deep learning, segmentation and visualization. IEEE Access 8:191586-191601, 2020","DOI":"10.1109\/ACCESS.2020.3031384"},{"key":"2403_CR16","doi-asserted-by":"crossref","unstructured":"Liu Y, Wu YH, Ban Y, Wang H, Cheng MM: Rethinking computer-aided tuberculosis diagnosis. Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR):2646\u20132655, 2020","DOI":"10.1109\/CVPR42600.2020.00272"},{"key":"2403_CR17","doi-asserted-by":"crossref","unstructured":"Liu Y, Wu YH, Zhang SC, Liu L, Wu M, Cheng MM: Revisiting computer-aided tuberculosis diagnosis. IEEE Trans Pattern Anal Mach Intell 46:2316-2332, 2023","DOI":"10.1109\/TPAMI.2023.3330825"},{"key":"2403_CR18","doi-asserted-by":"crossref","unstructured":"Nguyen HQ, Lam K, Le LT, Pham HH, Tran DQ, Nguyen DB, Le DD, Pham CM, Tong HTT, Dinh DH, Do CD, Doan LT, Nguyen CN, Nguyen BT, Nguyen QV, Hoang AD, Phan HN, Nguyen AT, Ho PH, Ngo DT, Nguyen NT, Nguyen NT, Dao M, Vu V: VinDr-CXR: an open dataset of chest X-rays with radiologist's annotations. Sci Data 9:429, 2022","DOI":"10.1038\/s41597-022-01498-w"},{"key":"2403_CR19","doi-asserted-by":"crossref","unstructured":"Masoomi M, Al-Kandari L, Ramzy H, Hamza MA: Externally validated deep learning analysis of chest radiographs for differentiating COVID-19 and viral pneumonia. Diagnostics (Basel) 16:995, 2026","DOI":"10.3390\/diagnostics16070995"},{"key":"2403_CR20","doi-asserted-by":"crossref","unstructured":"Baghdadi N, Maklad AS, Malki A, Deif MA: Reliable sarcoidosis detection using chest X-rays with EfficientNets and stain-normalization techniques. Sensors (Basel) 22:3846, 2022","DOI":"10.3390\/s22103846"},{"key":"2403_CR21","doi-asserted-by":"publisher","unstructured":"Cohen JP, Viviano JD, Bertin P, Morrison P, Torabian P, Guarrera M, Lungren MP, Chaudhari A, Brooks R, Hashir M, Bertrand H: TorchXRayVision: a library of chest X-ray datasets and models. arXiv (preprint), https:\/\/doi.org\/10.48550\/arXiv.2111.00595, October 31, 2021. Software available at https:\/\/github.com\/mlmed\/torchxrayvision","DOI":"10.48550\/arXiv.2111.00595"},{"key":"2403_CR22","doi-asserted-by":"crossref","unstructured":"Rajaraman S, Folio LR, Dimperio J, Alderson PO, Antani SK: Improved semantic segmentation of tuberculosis-consistent findings in chest X-rays using augmented training of modality-specific U-Net models with weak localizations. Diagnostics (Basel) 11:616, 2021","DOI":"10.3390\/diagnostics11040616"},{"key":"2403_CR23","unstructured":"NIAID TB Portals Program. Available at https:\/\/data.tbportals.niaid.nih.gov\/. Accessed March 2025."},{"key":"2403_CR24","doi-asserted-by":"publisher","unstructured":"Kermany D, Zhang K, Goldbaum M: Labeled optical coherence tomography (OCT) and chest X-ray images for classification. Mendeley Data, V2, https:\/\/doi.org\/10.17632\/rscbjbr9sj.2, January 6, 2018","DOI":"10.17632\/rscbjbr9sj.2"},{"key":"2403_CR25","doi-asserted-by":"publisher","unstructured":"Kiran S, Jabeen I: Dataset of tuberculosis chest X-rays images. Mendeley Data, V2, https:\/\/doi.org\/10.17632\/8j2g3csprk.2, May 28, 2024","DOI":"10.17632\/8j2g3csprk.2"},{"key":"2403_CR26","doi-asserted-by":"crossref","unstructured":"Johns M, Meurers T, Wirth FN, Haber AC, M\u00fcller A, Halilovic M, Balzer F, Prasser F: Data provenance in biomedical research: scoping review. J Med Internet Res 25:e42289, 2023","DOI":"10.2196\/42289"},{"key":"2403_CR27","doi-asserted-by":"crossref","unstructured":"Gierend K, Kr\u00fcger F, Genehr S, Hartmann F, Siegel F, Waltemath D, Ganslandt T, Zeleke AA: Provenance information for biomedical data and workflows: scoping review. J Med Internet Res 26:e51297, 2024","DOI":"10.2196\/51297"},{"key":"2403_CR28","unstructured":"World Health Organization: Ethics and Governance of Artificial Intelligence for Health: WHO Guidance, Geneva: World Health Organization, 2021"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02403-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02403-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02403-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T23:56:11Z","timestamp":1792194971000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02403-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,16]]},"references-count":28,"alternative-id":["2403"],"URL":"https:\/\/doi.org\/10.1007\/s10278-026-02403-2","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,16]]},"assertion":[{"value":"24 June 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study used only secondary, publicly available, de-identified datasets; no new data were collected from human subjects, no institutional patient records or images were used, and there was no interaction with patients. Ethics-committee review was therefore not required, and no application was made. The licence or data-use terms of each dataset are listed in Online Resource\n                      \n                      , Section S6.","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. The study used secondary, publicly available, de-identified data with no patient-identifying information.","order":2,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. The study used secondary, publicly available, de-identified data with no patient-identifying information.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Language-model tools were used to check grammar and formatting of the manuscript and the response letter; the author reviewed and takes responsibility for all content.","order":4,"name":"Ethics","label":"Use of Generative AI","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author declares no competing interests.","order":5,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}