Multi-view deep learning framework for the detection of chest X-rays compatible with pediatric pulmonary tuberculosis

Daniel Capellán-Martín, Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain. daniel.capellan@upm.es.
Juan J. Gómez-Valverde, Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain. juanjo.gomez@upm.es.
Ramón Sánchez-Jacob, Department of Diagnostic Imaging and Radiology, Children's National Hospital, Washington, DC, USA.
Alicia Hernanz-Lobo, Pediatric Infectious Diseases Department, Gregorio Marañón University Hospital, Madrid, Spain.
H Simon Schaaf, Desmond Tutu TB Centre, Department of Pediatrics and Child Health, Stellenbosch University, Cape Town, South Africa.
Lara García-Delgado, Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain.
Orvalho Augusto, Department of Global Health, University of Washington, Seattle, WA, USA.
Pooneh Roshanitabrizi, Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, USA.
Alberto L. García-Basteiro, Centro de Investigación Biomédica en Red de Enfermedades Infecciosas (CIBERINFEC), Instituto de Salud Carlos III, Madrid, Spain.
Jose Luis Ribó, Hospital Universitari General de Catalunya, Barcelona, Spain.
Ángel Lancharro, Gregorio Marañón Research Health Institute (IiSGM), Madrid, Spain.
Antoni Noguera-Julian, RITIP Translational Research Network in Pediatric Infectious Diseases, Madrid, Spain.
Daniel Blázquez-Gamero, Centro de Investigación Biomédica en Red de Enfermedades Infecciosas (CIBERINFEC), Instituto de Salud Carlos III, Madrid, Spain.

Document Type

Journal Article

Publication Date

10-27-2025

Journal

Nature communications

Volume

16

Issue

1

DOI

10.1038/s41467-025-64391-1

Abstract

Tuberculosis (TB) remains a major global health burden, particularly in low-resource, high-prevalence regions. Pediatric TB diagnosis poses challenges with non-specific symptoms and less distinct radiological manifestations than adult TB. Many affected children remain undiagnosed or untreated. The World Health Organization (WHO) recommends chest X-ray (CXR) for TB screening and triage, given its accessibility and rapid assessment of pulmonary TB-related abnormalities. We present pTBLightNet, a multi-view deep learning framework to detect pediatric pulmonary TB by identifying TB-compatible CXRs with consistent radiological findings. Leveraging both frontal and lateral CXR views, our framework is pre-trained on adult CXR datasets (N = 114,173), then fine-tuned or trained from scratch, and subsequently evaluated on CXR datasets (N = 918) from three pediatric TB cohorts. It achieves an area under the curve (AUC) of 0.903 and 0.682 on internal and external testing, respectively. External evaluation supports its effectiveness and generalizability using CXR TB compatibility, expert reading, microbiological confirmation and case definition as reference standards. Age-specific models (<5 and 5-18 years) perform competitively with those trained on larger undifferentiated populations, and adding lateral CXRs improves diagnosis in younger children. These results highlight the robustness of our approach across age groups and its potential to improve TB diagnosis, particularly in resource-limited settings.

Department

Radiology

Link to Full Text

Share

COinS