Lightweight MobileNet-Based Deep Learning Framework for Automated Lung Infection Detection from Chest X-Ray Images
Abstract views: 19 , PDF downloads: 9Abstract
Lung infections, especially viral pneumonia, continue to pose a significant global health challenge due to their high rates of illness and death. Traditional diagnostic approaches, such as radiologists' interpretation of chest X-ray (CXR) images, are frequently slow and subject to personal bias. The swift advancement in deep learning offers great potential for automating the detection of lung infections; however, many existing convolutional neural network (CNN) models demand substantial computational resources, which restricts their use in real-time or low-resource clinical settings. This study seeks to overcome these issues by creating a lightweight and effective diagnostic system using the MobileNet architecture for automatic lung infection identification from CXR images. The core drive for this research is to deliver an accessible and precise AI tool that aids radiologists in timely disease detection, particularly in under-resourced healthcare environments. The proposed MobileNet-based model, trained through transfer learning and fine-tuning on a binary dataset of normal and viral pneumonia images, strikes an excellent balance between performance and computational efficiency. Experimental results yielded 98% accuracy, 0.98 precision, 0.98 recall, and 0.98 F1-score, validating the model's reliability and appropriateness for embedded or mobile health uses. Moving forward, efforts will concentrate on broadening the dataset to encompass various lung disease types, incorporating explainable AI methods to boost clarity, and implementing the model in live clinical or mobile diagnostic platforms to enable widespread and effective healthcare services.
Downloads
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[2] K. Yamac, M. Ahishali, A. Degerli, et al., “Detection of COVID-19 from chest X-ray images using convolutional neural networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 4, pp. 1810–1820, 2021.
[3] G. Ranjan, R. P. Mahapatra, and S. Kumar, “Deep hybrid CNN model for lung disease classification from X-ray images,” IEEE Access, vol. 9, pp. 108723–108733, 2021.
[4] R. C. Deo, P. Basha, and M. Hassan, “Improved CNN-based pneumonia detection with lightweight models,” Biomed. Signal Process. Control, vol. 70, p. 103030, 2021.
[5] D. S. Banerjee, K. K. Mishra, and T. S. Rautaray, “Enhanced transfer learning for pneumonia classification using EfficientNet,” Comput. Biol. Med., vol. 146, p. 105523, 2022.
[6] A. Tahir, M. Rehman, and F. Shah, “Transfer learning for pediatric pneumonia detection using modern CNN architectures,” Diagnostics, vol. 12, no. 5, p. 1021, 2022.
[7] M. H. Islam, N. K. Rana, and M. Chowdhury, “Deep ensemble for robust pneumonia detection,” Sensors, vol. 22, no. 14, p. 5212, 2022.
[8] S. Patel, V. Singh, A. Khamparia, and D. P. Singh, “Hybrid CNN–ViT framework for pneumonia classification in chest radiographs,” IEEE J. Biomed. Health Inform., vol. 27, no. 3, pp. 1201–1212, 2023.
[9] R. Zhang, G. Liang, and L. Zheng, “Residual attention-based CNN for pediatric pneumonia diagnosis,” Comput. Biol. Med., vol. 141, p. 105126, 2022.
[10] S. Velu, “An efficient, lightweight MobileNetV2-based fine-tuned model for COVID-19 detection using chest X-ray images,” Mathematical Biosciences and Engineering, vol. 20, no. 5, pp. 8400–8427, 2023.
[11] M. A. I. Miah, S. Paul, and S. Das, “InfLocNet: Enhanced lung infection localization and disease detection from chest X-ray images using lightweight deep learning,” arXiv preprint, arXiv:2401.01234, 2024.
[12] S. Sharma and K. Guleria, “A systematic literature review on deep learning approaches for pneumonia detection using chest X-ray images,” Multimed. Tools Appl., vol. 83, pp. 24101–24151, 2024.
[13] Y. Wang, Z. Lin, and A. Wong, “Validating the accuracy of deep learning for the diagnosis of pneumonia,” Eur. Radiol. Exp., vol. 7, no. 1, p. 23, 2023.
[14] S. Sebastian and B. Ankayarkanni, “Enhanced ResNet-50 with multi-feature fusion for robust detection of pneumonia in chest X-ray images,” Diagnostics, vol. 15, no. 16, p. 2041, 2025.
[15] M. A. I. Miah, S. Paul, and S. Das, “InfLocNet: Lightweight framework for explainable lung infection detection,” IEEE Access, vol. 12, pp. 45123–45137, 2024.
[16] S. Velu, A. S. Raj, and R. Thiyagarajan, “Hybrid MobileNet architecture with transfer learning for multi-disease chest X-ray classification,” IEEE Sensors Journal, vol. 24, no. 3, pp. 3254–3263, 2024.
[17] M. Asiful Islam, M. Rahman, and M. Chowdhury, “Edge-AI frameworks for mobile lung infection detection,” IEEE Internet of Things Journal, vol. 10, no. 4, pp. 18743–18755, 2023.
[18] N. Hassan and K. Rahman, “Federated learning for privacy-preserving medical image analysis: A review,” IEEE Rev. Biomed. Eng., vol. 17, pp. 45–63, 2024.
[19] J. Zhang, H. Li, and T. Wong, “Vision Transformers in medical imaging: Applications and challenges,” IEEE Access, vol. 12, pp. 121400–121420, 2024.
[20] M. Kim, T. Liu, and J. Wang, “Explainable AI for chest X-ray diagnosis: Visual and quantitative evaluation,” Diagnostics, vol. 13, no. 2, p. 411, 2023.
[21] P. Sun, Y. Li, and S. Chen, “Improving pneumonia detection via attention-aware lightweight CNNs,” Comput. Methods Programs Biomed., vol. 239, p. 107685, 2024.
[22] S. K. Srivastava, R. Mahajan, and P. Jain, “Deep learning for pulmonary disease detection with edge computing,” IEEE J. Transl. Eng. Health Med., vol. 12, pp. 142–153, 2024.
[23] A. Z. Ali, N. R. Khan, and F. Iqbal, “Federated transfer learning for multi-hospital chest X-ray disease prediction,” IEEE Trans. Med. Imaging, vol. 44, no. 1, pp. 88–102, 2025.
