DenseNet121 and Transfer Learning for Lung Disease Classification from Chest X-Ray Images
Abstract views: 8 , PDF downloads: 18Abstract
Lung-related disorders, including pneumonia, are still among the primary causes of death and illness worldwide, particularly in areas where medical imaging facilities and trained radiologists are scarce. The manual assessment of chest X-ray (CXR) images demands significant time and is prone to subjective interpretation, limiting its scalability for mass screening and early disease identification. To overcome these challenges, this study introduces an automated classification approach utilizing the DenseNet121 convolutional neural network through transfer learning for the detection of lung diseases from CXR scans. The pretrained ImageNet weights were adopted to capture hierarchical visual features efficiently, while overfitting was mitigated using dropout and batch normalization layers. The dataset employed consisted of 1,880 training images and 235 testing images, equally distributed between Normal and Viral Pneumonia categories. Experimental evaluation revealed an overall classification accuracy of 97%, alongside precision, recall, and F1-score metrics of 0.97 each, indicating reliable and balanced model performance. These outcomes suggest that DenseNet121 offers a highly effective foundation for computer-aided diagnostic systems capable of differentiating between healthy and infected lungs with high precision. The proposed framework provides a scalable diagnostic tool suitable for healthcare environments with limited radiological expertise. Future improvements will include expanding toward multi-class disease classification, incorporating explainable artificial intelligence (XAI) techniques to enhance interpretability, and validating the system on larger, more diverse clinical datasets.
Downloads
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[2] A. B. Rashid et al., “Pneumonia image classification using DenseNet architecture,” Information, vol. 15, no. 10, p. 611, 2024.
[3] A. M. Q. Farhan and S. Yang, “Automatic lung disease classification from chest X-ray images using a hybrid deep learning algorithm,” Multimedia Tools and Applications, Mar. 2023.
[4] Y. Liu et al., “Deep learning in multi-class lung diseases classification on chest X-ray images,” Sensors, vol. 22, no. 13, p. 4972, 2022.
[5] M. Jain et al., “A comparative study of multiple neural networks for detection of COVID-19 and pneumonia from chest X-ray images,” EURASIP Journal on Advances in Signal Processing, vol. 2021, no. 1, p. 155, 2021.
[6] A. El Asnaoui et al., “Classification of lung diseases using an attention-based modified DenseNet,” Applied Sciences, vol. 13, no. 2, p. 812, 2023.
[7] R. Mitchell et al., “Transfer learning for the detection and diagnosis of pneumonia types from chest X-ray images,” Computational and Mathematical Methods in Medicine, vol. 2021, p. 9936598, 2021.
[8] F. Zhu et al., “Deep learning-based classification of chest diseases using X-ray images,” Diagnostics, vol. 13, no. 17, p. 2786, 2023.
[9] R. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning,” Nature Medicine, vol. 24, no. 8, pp. 1204–1212, 2018.
[10] H. Azemin et al., “Efficient pneumonia detection in chest X-ray images using deep learning,” MDPI Applied Sciences, vol. 10, no. 7, p. 2430, 2020.
[11] M. Barreto et al., “Pattern recognition in lung X-ray images using texture and edge descriptors,” Biomedical Engineering Online, vol. 17, no. 1, pp. 1–13, 2018.
[12] S. S. Kumar et al., “An efficient approach for lung disease detection using SVM classifier,” Procedia Computer Science, vol. 167, pp. 2404–2411, 2019.
[13] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
[14] P. Lakhani and B. Sundaram, “Deep learning at chest radiography: Automated classification of pulmonary tuberculosis by using convolutional neural networks,” Radiology, vol. 284, no. 2, pp. 574–582, 2017.
[15] P. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning,” arXiv preprint arXiv:1711.05225, 2017.
[16] L. Yao et al., “Learning to diagnose multiple diseases from chest radiographs using deep learning,” Medical Image Analysis, vol. 64, p. 101716, 2020.
[17] X. Wang et al., “ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 3462–3471.
[18] O. Stephen et al., “Deep learning for COVID-19 and pneumonia detection in chest X-rays using transfer learning,” IEEE Access, vol. 7, pp. 195–203, 2019.
[19] G. Liang and L. Zheng, “A transfer learning method with deep residual networks for pediatric pneumonia diagnosis,” Computer Methods and Programs in Biomedicine, vol. 187, p. 104964, 2020.
[20] M. Islam et al., “Combining DenseNet121 and SqueezeNet for COVID-19 and pneumonia detection,” PLoS ONE, vol. 15, no. 12, e0243169, 2020.
[21] H. Xu et al., “Data augmentation using GANs for improved chest disease classification,” Computers in Biology and Medicine, vol. 115, p. 103849, 2019.
[22] T. Gabruseva et al., “Preprocessing and enhancement techniques for improving chest X-ray pneumonia detection,” Journal of Digital Imaging, vol. 32, no. 4, pp. 620–630, 2019.
[23] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 4700–4708.
[24] M. Aasem and M. J. Iqbal, “Toward explainable AI in radiology: Ensemble-CAM for effective thoracic disease localization in chest X-ray images using weakly supervised learning,” Frontiers in Big Data, vol. 7, p. 1366415, May 2024.
[25] M. Ali et al., “Enhanced tuberculosis detection using Vision Transformers and Grad-CAM from chest X-rays,” BMC Medical Imaging, vol. 25, no. 1, p. 1630-3, 2025.
