Comparative Analysis of Deep Learning Models for Pneumonia Detection
DOI:
https://doi.org/10.29194/NJES.28040639Keywords:
Deep Learning, Pneumonia Detection, Densenet-121, Model Efficiency, Chest X-Rays, Dataset Augmentation, Statistical SignificanceAbstract
This study evaluates the performance and efficiency of four deep learning models—VGG-16, ResNet-50, Inception-V3, and DenseNet-121—in detecting pneumonia from chest X-rays, addressing the critical need for balanced accuracy and computational efficiency in clinical diagnostics. Methods: A dataset of 5,234 chest X-rays (3,875 pneumonia, 1,341 normal) was augmented via rotation, flipping, and zooming to mitigate class imbalance. Models were trained on an RTX 2060 GPU for 40 epochs, with performance assessed using accuracy, F1 score, sensitivity, specificity, precision, and computational metrics (training time, memory usage). Statistical significance was validated via paired t-tests (p < 0.05). Results: DenseNet-121 achieved the highest accuracy (95.2% ± 0.8), F1 score (95.1% ± 0.7), and throughput (400 images/sec) with minimal memory usage (33MB). ResNet-50 and Inception-V3 showed moderate performance, while VGG-16 exhibited overfitting tendencies. In conclusion, DenseNet-121 showed strong performance compared to other models, both in terms of accuracy and processing speed, which is essential for use in real-time clinical settings. However, the small size of the validation set and limited population diversity are important limitations that should be addressed in future studies. Moreover, more testing on larger datasets is needed to confirm the stability of the model and see how the model will work in different settings. Future work should address ethical considerations in AI-driven diagnostics and validate findings across multi-institutional datasets.
Downloads
References
W. Sabbagh, A. Al-Mashhadani, R. Al-Khalidi, M. Al-Saadi, and H. Al-Taie, "Perspective of pneumonia in the health-care setting," J. Pharm. Res. Int., vol. 36, pp. 51-58, 2024. https://doi.org/10.9734/jpri/2024/v36i77538 DOI: https://doi.org/10.9734/jpri/2024/v36i77538
O. Olatunde, O. Adewale, and O. Daramola, "Unlocking pneumonia severity diagnosis with deep learning," Int. J. Comput. Sci. Mobile Comput., vol. 13, pp. 59-67, 2024. https://doi.org/10.47760/ijcsmc.2024.v13i04.007 DOI: https://doi.org/10.47760/ijcsmc.2024.v13i04.007
I. Shahzad, M. Khan, A. Rauf, S. Ali, and H. Ahmed, "Enhancing ASD classification through hybrid attention-based learning of facial features," Signal Image Video Process., pp. 1-14, 2024. https://doi.org/10.1007/s11760-024-03167-4 DOI: https://doi.org/10.1007/s11760-024-03167-4
A. S. Al-Waisy, M. A. Mohammed, S. Al-Fahdawi, A. Z. Al-Saadi, M. T. Al-Khateeb, and D. N. Al-Jumeily, "COVID-CheXNet: Hybrid deep learning framework for identifying COVID-19 in chest X-rays," Soft Comput., vol. 27, pp. 2657-2672, 2023. https://doi.org/10.1007/s00500-020-05424-3 DOI: https://doi.org/10.1007/s00500-020-05424-3
P. Kaushik, R. Sharma, A. Verma, S. Gupta, and N. Singh, "PneumoAI: Redefining accuracy in pneumonia detection using advanced machine learning," in Proc. IEEE Int. Conf. Interdiscip. Approaches Technol. Manag. Social Innov., Gwalior, India, 2024, pp. 1-6. https://doi.org/10.1109/IATMSI60426.2024.10503052 DOI: https://doi.org/10.1109/IATMSI60426.2024.10503052
B.-D. Dinh, T.-H. Nguyen, Q.-M. Tran, and H.-T. Pham, "1M parameters are enough? A lightweight CNN-based model for medical image segmentation," in Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf., 2023, pp. 1-6. https://doi.org/10.1109/APSIPAASC58517.2023.10317244 DOI: https://doi.org/10.1109/APSIPAASC58517.2023.10317244
M. A. Mohammed, A. S. Al-Waisy, H. Al-Taie, R. Sekhar, and K. Potter, "Deep learning for pneumonia detection: A systematic review of architectural innovations," IEEE Trans. Med. Imaging, vol. 42, no. 5, pp. 1234-1248, 2023.
J. Zhang, L. Chen, Y. Zhao, and F. Li, "Robust pneumonia diagnosis using multi-scale CNNs with attention mechanisms," in Proc. IEEE Int. Conf. Image Process., 2022, pp. 456-460.
S. K. Jha and R. K. Singh, "Efficient data augmentation strategies for chest X-ray analysis," IEEE J. Biomed. Health Inform., vol. 27, no. 3, pp. 1023-1032, 2023.
L. Wang, Y. Xu, H. Zhang, and J. Liu, "Transfer learning in medical imaging: A case study on pneumonia detection," IEEE Access, vol. 10, pp. 87654-87665, 2022. https://doi.org/10.1109/ACCESS.2022.3199372 DOI: https://doi.org/10.1109/ACCESS.2022.3199372
A. Gupta, P. Sharma, R. Mehta, and S. Kumar, "Lightweight CNNs for real-time pneumonia detection on edge devices," in Proc. IEEE Int. Conf. Edge Comput., 2023, pp. 112-117.
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 770-778. https://doi.org/10.1109/CVPR.2016.90 DOI: https://doi.org/10.1109/CVPR.2016.90
G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2017, pp. 4700-4708. https://doi.org/10.1109/CVPR.2017.243 DOI: https://doi.org/10.1109/CVPR.2017.243
A. Esteva, B. Kuprel, J. Novoa, J. Ko, S. Swetter, H. Blau, and S. Thrun, "Deep learning for medical image analysis: A comprehensive review," IEEE Trans. Med. Imaging, vol. 41, no. 12, pp. 3245-3262, 2022.
S. Rajendran, P. Kumar, R. Sharma, and A. Singh, "Vision transformers outperform CNNs in pneumonia detection: A comparative study," IEEE J. Transl. Eng. Health Med., vol. 11, pp. 1-10, 2023.
R. Sekhar, P. Shah, H. R. Penubadi, and G. Omran, "Ethical challenges in AI-driven radiology: Bias, transparency, and accountability," IEEE Trans. Technol. Soc., vol. 4, no. 2, pp. 189-197, 2023.
P. Rajpurkar, J. Irvin, K. Zhu, B. Yang, H. Mehta, T. Duan, D. Ding, A. Bagul, C. Langlotz, K. Shpanskaya, M. P. Lungren, and A. Y. Ng, "CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning," https://doi.org/10.48550/arXiv.1711.05225
F. Olaoye and K. Potter, "Deep learning algorithms in medical diagnostics: A survey," Dissolution Technol., vol. 29, no. 4, pp. 23-31, 2022.
D. S. Kermany, M. Goldbaum, W. Cai, C. C. S. Valentim, H. Liang, S. L. Baxter, A. McKeown, G. Yang, X. Wu, F. Yan, J. Dong, M. K. Prasadha, J. Pei, M. Y. L. Ting, J. Zhu, C. Li, S. Hewett, J. Dong, I. Ziyar, A. Shi, R. Zhang, L. Zheng, R. Hou, W. Shi, X. Fu, Y. Duan, V. A. N. Huu, C. Wen, E. D. Zhang, C. L. Zhang, O. Li, X. Wang, M. A. Singer, X. Sun, J. Xu, A. Tafreshi, M. A. Lewis, H. Xia, and K. Zhang, "Identifying medical diagnoses and treatable diseases by image-based deep learning," Cell, vol. 172, no. 5, pp. 1122-1131, 2018. https://doi.org/10.1016/j.cell.2018.02.010 DOI: https://doi.org/10.1016/j.cell.2018.02.010
G. A. Omran, W. S. A. Hayale, A. A. AlRababah, I. I. Al-Barazanchi, R. Sekhar, P. Shah, S. Parihar, and H. R. Penubadi, "Utilizing a novel deep learning method for scene categorization in remote sensing data," Math. Model. Eng. Probl., vol. 12, no. 2, pp. 657-668, 2025. https://doi.org/10.18280/mmep.120229 DOI: https://doi.org/10.18280/mmep.120229
X.-H. Zhou, N. A. Obuchowski, and D. K. McClish, Statistical Methods in Diagnostic Medicine, 2nd ed. Hoboken, NJ: Wiley, 2011. https://doi.org/10.1002/9780470906514 DOI: https://doi.org/10.1002/9780470906514
D. G. Altman and J. M. Bland, "Diagnostic tests 1: Sensitivity and specificity," BMJ, vol. 308, no. 6943, p. 1552, 1994. https://doi.org/10.1136/bmj.308.6943.1552 DOI: https://doi.org/10.1136/bmj.308.6943.1552
T. Saito and M. Rehmsmeier, "The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets," PLoS One, vol. 10, no. 3, p. e0118432, 2015. https://doi.org/10.1371/journal.pone.0118432 DOI: https://doi.org/10.1371/journal.pone.0118432
D. M. Powers, "Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation," J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37-63, 2011.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Commun. ACM, vol. 60, no. 6, pp. 84-90, 2017. https://doi.org/10.1145/3065386 DOI: https://doi.org/10.1145/3065386
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Eelaf Ayyed Jebur
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The authors retain the copyright of their manuscript by submitting the work to this journal, and all open access articles are distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC-BY-NC 4.0), which permits use for any non-commercial purpose, distribution, and reproduction in any medium, provided that the original work is properly cited.
How to Cite
