Active case finding to detect symptomatic and subclinical pulmonary tuberculosis disease: implementation of computer-aided detection for chest radiography in Viet Nam.

Objective: In Viet Nam, tuberculosis (TB) prevalence surveys revealed that approximately 98% of individuals with pulmonary TB have TB-presumptive abnormalities on chest radiographs, while 32% have no TB symptoms. This prompted the adoption of the "Double X" strategy, which combines chest radiographs and computer-aided detection with GeneXpert testing to screen for and diagnose TB among vulnerable populations. The aim of this study was to describe demographic, clinical and radiographic characteristics of symptomatic and asymptomatic Double X participants and to assess multilabel radiographic abnormalities on chest radiographs, interpreted by computer-aided detection software, as a possible tool for detecting TB-presumptive abnormalities, particularly for subclinical TB. Methods: Double X participants with TB-presumptive chest radiographs and/or TB symptoms and known risks were referred for confirmatory GeneXpert testing. The demographic and clinical characteristics of all Double X participants and the subset with confirmed TB were summarized. Univariate and multivariable logistic regression modelling was used to evaluate associations between participant characteristics and subclinical TB and between computer-aided detection multilabel radiographic abnormalities and TB. Results: From 2020 to 2022, 96 631 participants received chest radiographs, with 67 881 (70.2%) reporting no TB symptoms. Among 1144 individuals with Xpert-confirmed TB, 51.0% were subclinical. Subclinical TB prevalence was higher in older age groups, non-smokers, those previously treated for TB and the northern region. Among 11 computer-aided detection multilabel radiographic abnormalities, fibrosis was associated with higher odds of subclinical TB. Discussion: In Viet Nam, Double X community case finding detected pulmonary TB, including subclinical TB. Computer-aided detection software may have the potential to identify subclinical TB on chest radiographs by classifying multilabel radiographic abnormalities, but further research is needed.

BM-BronchoLC - A rich bronchoscopy dataset for anatomical landmarks and lung cancer lesion recognition.

Flexible bronchoscopy has revolutionized respiratory disease diagnosis. It offers direct visualization and detection of airway abnormalities, including lung cancer lesions. Accurate identification of airway lesions during flexible bronchoscopy plays an important role in the lung cancer diagnosis. The application of artificial intelligence (AI) aims to support physicians in recognizing anatomical landmarks and lung cancer lesions within bronchoscopic imagery. This work described the development of BM-BronchoLC, a rich bronchoscopy dataset encompassing 106 lung cancer and 102 non-lung cancer patients. The dataset incorporates detailed localization and categorical annotations for both anatomical landmarks and lesions, meticulously conducted by senior doctors at Bach Mai Hospital, Vietnam. To assess the dataset's quality, we evaluate two prevalent AI backbone models, namely UNet++ and ESFPNet, on the image segmentation and classification tasks with single-task and multi-task learning paradigms. We present BM-BronchoLC as a reference dataset in developing AI models to assist diagnostic accuracy for anatomical landmarks and lung cancer lesions in bronchoscopy data.

Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam's District Health Facilities: An Implementation Study.

In Vietnam, chest radiography (CXR) is used to refer people for GeneXpert (Xpert) testing to diagnose tuberculosis (TB), demonstrating high yield for TB but a wide range of CXR abnormality rates. In a multi-center implementation study, computer-aided detection (CAD) was integrated into facility-based TB case finding to standardize CXR interpretation. CAD integration was guided by a programmatic framework developed for routine implementation. From April through December 2022, 24,945 CXRs from TB-vulnerable populations presenting to district health facilities were evaluated. Physicians interpreted all CXRs in parallel with CAD (qXR 3.0) software, for which the selected TB threshold score was ≥0.60. At three months, there was 47.3% concordance between physician and CAD TB-presumptive CXR results, 7.8% of individuals who received CXRs were referred for Xpert testing, and 858 people diagnosed with Xpert-confirmed TB per 100,000 CXRs. This increased at nine months to 76.1% concordant physician and CAD TB-presumptive CXRs, 9.6% referred for Xpert testing, and 2112 people with Xpert-confirmed TB per 100,000 CXRs. Our programmatic CAD-CXR framework effectively supported physicians in district facilities to improve the quality of referral for diagnostic testing and increase TB detection yield. Concordance between physician and CAD CXR results improved with training and was important to optimize Xpert testing.