LSE-Net: Integrated Segmentation and Ensemble Deep Learning for Enhanced Lung Disease Classification

Abstract

Accurate classification of lung diseases is vital for timely diagnosis and effective treatment of respiratory conditions such as COPD, pneumonia, asthma, and lung cancer. Traditional diagnostic approaches often suffer from limited consistency and elevated false-positive rates, highlighting the demand for more dependable automated systems. To address this challenge, we introduce LSE-Net, an end-to-end deep learning framework that combines precise lung segmentation using an optimized U-Net++ with robust classification powered by an ensemble of DenseNet121 and ResNet50. Leveraging structured hyperparameter tuning and patient-level evaluation, LSE-Net achieves 92.7% accuracy, 96.7% recall, and an F1-score of 94.0%, along with improved segmentation performance (DSC = 0.59 ± 0.01, IoU = 0.523 ± 0.07). These results demonstrate LSE-Net’s ability to reduce diagnostic uncertainty, enhance classification precision, and provide a practical, high-performing solution for real-world clinical deployment in lung disease assessment.