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

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.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-10-27
DOI
https://doi.org/10.1038/s41467-025-64391-1
Citations
4
Primary Topic
Tuberculosis Research and Epidemiology
Type
article
Field-Weighted Citation Impact
5.58

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Orvalho Augusto, Hendrik Simon Schaaf, Pooneh Roshanitabrizi, María J. Ledesma‐Carbayo et al.
4 citations
Nature Communications
Tuberculosis Research and Epidemiology
5.58
article

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

Orvalho Augusto, Hendrik Simon Schaaf, Pooneh Roshanitabrizi, María J. Ledesma‐Carbayo, Daniel Capellán-Martín, Begoña Santiago, Elisa López‐Varela, Daniel Blázquez‐Gamero, Ramon Sanchez, Jose Luis Ribó, Juan J. Gómez-Valverde, Ángel Lancharro, Alberto L. García‐Basteiro, Antoni Noguera‐Julián, Lara García-Delgado, Alicia Hernanz‐Lobo, Marius George Linguraru
article en
4 citations

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.

Nature CommunicationsVol. 16(1)
Universidad Complutense de Madrid (ES), Children's National (US), Desmond Tutu HIV Foundation (ZA), George Washington University (US), University of Washington (US), Stellenbosch University (ZA), Instituto de Salud Carlos III (ES), Hospital General Universitario Gregorio Marañón (ES), Research Institute Hospital 12 de Octubre (ES), Departament de Salut (ES), Hospital Universitario 12 De Octubre (ES), Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine (ES), Centro de Investigación Biomédica en Red (ES), Manhiça Health Research Centre (MZ), Hospital General de Catalunya (ES), HM Hospitales (ES), Sant Joan de Déu Research Foundation (ES), Hospital Materno-Infantil (ES), Barcelona Institute for Global Health (ES), Centro de Investigación Biomédica en Red de Epidemiología y Salud Pública (ES), European Telecommunications Standards Institute (FR), Universitat de Barcelona (ES), Universidad Politécnica de Madrid (ES)
European Respiratory Society, European Commission, Universidad Politécnica de Madrid, Ministerio de Ciencia e Innovación, Horizon 2020 Framework Programme, Instituto de Salud Carlos III, European Regional Development Fund, Agencia Estatal de Investigación, European and Developing Countries Clinical Trials Partnership
Openalex Percentile: Top 4%
Tuberculosis Research and Epidemiology
5.58
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.