Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comparative Study
. 2025 Jul 2;15(1):22540.
doi: 10.1038/s41598-025-06164-w.

Comparing the accuracy of computer-aided detection (CAD) software and radiologists from multiple countries for tuberculosis detection in chest X-Rays

Zhi Zhen Qin  1   2   3 , Martie Van der Walt  4 , Sizulu Moyo  5 , Farzana Ismail  6 , Phaleng Maribe  5 , Claudia M Denkinger  7 , Sarah Zaidi  8 , Rachael Barrett  8   9 , Lindiwe Mvusi  10 , Yolisa Tsibolane  10 , Nkateko Mkhondo  11 , Khangelani Zuma  5 , Samuel Manda  4 , Lisa Koeppel  7 , Thuli Mthiyane  4 , Jacob Creswell  8
Affiliations
Comparative Study

Comparing the accuracy of computer-aided detection (CAD) software and radiologists from multiple countries for tuberculosis detection in chest X-Rays

Zhi Zhen Qin et al. Sci Rep. .

Abstract

Nearly a third of TB cases go undetected annually. WHO recommends computer-aided detection (CAD) to enhance TB screening, with studies showing comparable performance to local radiologists. Using 774 chest X-rays from the South African National TB Prevalence Survey, we compared 12 CAD software with 11 radiologists from Nigeria, India, the UK, and the US, against a composite microbiological reference standard. Sensitivity, specificity and Cohen's kappa were calculated. Receiver-operating characteristic curves were developed for CAD and Euclidean distance assessed radiologists' alignment with the best-performing software. Binomial regression tested the impact of radiologists' characteristics on accuracy. Radiologist performance varied. On the restricted read, British radiologists had the highest sensitivity (78.7% [73.2-83.5%]) and Indian radiologists the lowest (67.1% [61.0-72.8%]). Specificity ranged from 75.8% (71.8-79.4%, Nigeria) to 84.3% (80.9-87.3%, the US). Radiologist performance was significantly impacted by HIV, prior TB, and age. The top CAD outperformed all except Indian radiologists when matching specificity. CAD with Conformité Européenne generally matched or surpassed radiologists. British radiologists' sensitivity was closest to the top CAD, while American radiologists were closest in specificity and overall. Experience, TB reads, and country had no significant impact on accuracy. CAD performed well against radiologists globally, highlighting potential to enhance access to care.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Ethical approval: Anonymized CXR data was obtained via a data-sharing request to the South African Medical Research Council (SAMRC) that was approved by the National Department of Health, South Africa. The CXR data provided had undergone automatic anonymization and hashing, ensuring no manual data handling, and was securely stored on Stop TB Partnership’s server using Secure File Transfer Protocol (SFTP). All data on the server was only accessible to co-investigators. Ethical approval was obtained from the SAMRC (EC002-3/2020) and Heidelberg (S-488/2021). During the prevalence survey, informed consent was obtained from all participants, with additional assent and parental consent for those aged 15-18 years. The study was carried out in accordance with the relevant guidelines and regulations.

Figures

Fig. 1
Fig. 1
Sensitivity and specificity of radiologists from each country disaggregated by HIV status, Prior TB History, and Age group.
Fig. 2
Fig. 2
Receiver operating characteristic (ROC) curve plotting human reader performance against CAD; (A) Restricted reading, (B) Inclusive reading.
Fig. 3
Fig. 3
ROC of the best-performing CAD compared to (A) Restricted reading, (B) Inclusive reading.
See this image and copyright information in PMC

References

    1. World Health Organization. Global Tuberculosis Report. (2024). https://www.who.int/publications/i/item/9789240101531
    1. Stop, T. B. & Partnership Global Plan to End TB 2023–2030. (2022). https://www.stoptb.org/what-we-do/advocate-endtb/global-plan-end-tb/glob...
    1. World Health Organization. Essential Diagnostic Imaging. (2012). https://web.archive.org/web/20121023154427/http://www.who.int/eht/en/Dia....
    1. Graham, S. et al. Chest radiography abnormalities associated with tuberculosis: Reproducibility and yield of active cases. Int. J. Tuberc Lung Dis.6, 137–142 (2002). - PubMed
    1. Pinto, L. M. et al. Scoring systems using chest radiographic features for the diagnosis of pulmonary tuberculosis in adults: A systematic review. Eur. Respir J.42, 480–494. 10.1183/09031936.00107412 (2013). - DOI - PubMed

Publication types

MeSH terms