Abstract—Pneumonia remains a critical global health con cern, necessitating rapid and accurate diagnostic strategies to improve patient outcomes. This study evaluates lightweight deep learning models and ensemble learning techniques for pneu monia detection from chest X-ray images. Five fine-tuned con volutional neural networks (CNNs)—MobileNet, EfficientNetB0, DenseNet121, NASNetMobile, and ResNet—were optimized using a curated dataset. A soft voting ensemble was also employed to combine model predictions. However, the best-performing individual models, MobileNet and EfficientNetB0, outperformed the ensemble across key metrics, achieving accuracies of 95.1% and an AUC of 99.7%, respectively. These results highlight the robustness of lightweight CNNs as standalone diagnostic tools, with ensemble learning providing limited added value. This study offers practical insights into model selection for early and accurate pneumonia diagnosis in medical imaging.

Conference Title

13th International Conference on Bioinformatics and Computational Biology (ICBCB 2025)

Conference Country

South Korea

Conference Date

Feb. 27, 2025 - March 2, 2025

Conference Sponsor

IEEE

Additional Info

Conference Website