Ensemble deep learning architectures for detecting pulmonary tuberculosis in chest X-rays.
Authors
Affiliations (8)
Affiliations (8)
- UNED, Madrid, Spain. [email protected].
- Department of Surgery & Cancer, Faculty of Medicine, Imperial College London, London, UK.
- Department of Clinical Research and Medical Data Science, Faculty of Medicine, Prince of Songkla University, Songkhla, Thailand.
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK. [email protected].
- School of Technology and Maritime Industries, Southampton Solent University, Southampton, UK.
- Department of Biomedical Sciences and Biomedical Engineering, Faculty of Medicine, Prince of Songkla University, Songkhla, Thailand.
- Roche Diagnostics, Sant Cugat del Vallès, Spain.
- Department of Family and Preventive Medicine, Faculty of Medicine, Prince of Songkla University, Songkhla, Thailand.
Abstract
Tuberculosis (TB) remains a major global health challenge, causing approximately 1.4 million deaths annually. In many high-burden regions, limited access to expert radiological interpretation leads to delayed or missed diagnoses. To address this, we propose a cost-effective, automated TB screening method suitable for under-resourced settings. Our method integrates a Convolutional Autoencoder Neural Network and a Multi-Scale Convolutional Neural Network with deep layer aggregation into an ensemble learning architecture for robust TB detection from chest radiographs. The framework was evaluated on two public datasets and one private dataset, achieving 99% sensitivity and 94% specificity on the Shenzhen dataset, and consistently high accuracy across all datasets. Expert radiologists reviewed a subset of the predictions, confirming the clinical relevance and diagnostic reliability of the model. The ensemble approach demonstrated strong generalisability, effectively identifying active pulmonary TB in chest X-rays from a globally representative cohort. It also outperformed existing classifiers, achieving a state-of-the-art Area Under the Receiver Operating Characteristic of 0.98. These results highlight the potential of our approach as a practical and scalable tool for TB screening, particularly in low- and middle-income countries where radiological resources are limited.