PneumaScan: A Two-Phase Fine-Tuning Framework using DenseNet121 for Pneumonia Detection

Lower respiratory tract infections, primarily pneumonia, are the leading infectious cause of death worldwide, accounting for almost 2.2 million deaths every year, including more than 700,000 children below five years old. Although these conditions are preventable and treatable, they affect approximately 450 million people globally each year, with most of those dying belonging to disadvantaged groups or living in places with few healthcare resources. A key issue in tackling this crisis involves getting accurate and prompt diagnostic evaluations, which is still largely reliant on expert readings of chest X-rays, which is a complicated method due to the enormous number of cases and the extreme lack of radiologists. Overcoming this obstacle requires the incorporation of intelligent automated solutions to help clinicians make better decisions. This paper proposes an improved artificial intelligence (AI)-driven system using deep learning-based convolutional neural networks to identify pneumonia from chest X-ray images. DenseNet121, a connectivity-heavy convolutional model allowing smooth transmission and gathering of layered features due to its specialized weaving design, is used in this study. After undergoing strict training and verification steps using a carefully sorted collection of X-ray images, the model showed impressive skill in identifying lung abnormalities versus regular structures. The performance assessments showed outstanding outcomes, with a macroaverage precision of 93.72% and an overall accuracy of 93.42% on separate test inputs. These scores indicate the solid real-world applicability of the system for practical application in mechanical pneumonia screening setups. The proposed model holds major promise for streamlining diagnostic procedures, speeding up case discovery, and aiding quicker treatment steps, especially in medical areas where specialists remain scarce.

Deep learning; DenseNet; Feature extraction; Image processing; Pneumonia detection

Ali, M., Shahroz, M., Akram, U., Mushtaq, M. F., Carvajal Altamiranda, S., Aparicio Obregon, S., De La Torre Díez, I., & Ashraf, I. (2024). Pneumonia detection using chest radiographs with novel EfficientNetV2L model. IEEE Access, 12, 34691–34707. https://doi.org/10.1109/ACCESS.2024.3372588

Aly, S., & Almotairi, S. (2020). Deep convolutional self-organizing map network for robust handwritten digit recognition. IEEE Access, 8, 107035–107045. https://doi.org/10.1109/ACCESS.2020.3000829

An, Q., Chen, W., & Shao, W. (2024). A deep convolutional neural network for pneumonia detection in X-ray images with attention ensemble. Diagnostics, 14 (4), 390. https://doi.org/10.3390/diagnostics14040390

Das, R., Nayak, D. S. K., Rout, C. P., Jena, L., & Swarnkar, T. (2024). Deep learning techniques for identification of pneumonia: A CNN approach. Proceedings of the International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC), 1–5. https://doi.org/10.1109/ASSIC60049.2024.10507933

Dash, S. K., Nanda, B., Dash, K. C., Mishra, P. K., & Pattnaik, S. (2026). PneumoNet: A VGG16 based CNN model for pneumonia prediction. SN Computer Science, 7 (1), 33. https://doi.org/10.1007/s42979-025-04630-w

Faouzi, J., & Colliot, O. (2023). Classic machine learning methods. In O. Colliot (Ed.), Machine learning for brain disorders (pp. 25–75, Vol. 197). Springer. https://doi.org/10.1007/978-1-0716-3195-9 2

Fu, M., Tantithamthavorn, C., & Le, T. (2025). DAViT: A domain-adapted vision transformer for automated pneumonia detection and explanation using chest X-ray images. IEEE Access, 13, 103033–103044. https://doi.org/10.1109/ACCESS.2025.3579314

Ghanim, T. M., Khalil, M. I., & Abbas, H. M. (2020). Comparative study on deep convolution neural networks (DCNN)-based offline Arabic handwriting recognition. IEEE Access, 8, 95465–95482. https://doi.org/10.1109/ACCESS.2020.2995499

Guddati, P., Dash, S., & Tripathy, R. K. (2024). FPGA implementation of the proposed DCNN model for detection of tuberculosis and pneumonia using CXR images. IEEE Embedded Systems Letters, 16 (4), 445–448. https://doi.org/10.1109/LES.2024.3370833

Hasan, M. R., Ullah, S. M. A., & Islam, S. M. R. (2024). Recent advancement of deep learning techniques for pneumonia prediction from chest X-ray image. Medical Reports, 7, 100106. https://doi.org/10.1016/j.hmedic.2024.100106

Hofmeister, J., Garin, N., Montet, X., Scheffler, M., Platon, A., Poletti, P.-A., Stirnemann, J., Debray, M.-P., Claessens, Y.-E., Duval, X., & Prendki, V. (2024). Validating the accuracy of deep learning for the diagnosis of pneumonia on chest x-ray against a robust multimodal reference diagnosis: A post hoc analysis of two prospective studies. European Radiology Experimental, 8, 14. https://doi.org/10.1186/s41747-023-00416-y

Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4700–4708. https://doi.org/10.1109/CVPR.2017.243

Jiang, Z.-P., Liu, Y.-Y., Shao, Z.-E., & Huang, K.-W. (2021). An improved VGG16 model for pneumonia image classification. Applied Sciences, 11 (23), 11185. https://doi.org/10.3390/app112311185

Jung, T., & Kim, J. (2023). A new support vector machine for categorical features. Expert Systems with Applications, 229, 120449. https://doi.org/10.1016/j.eswa.2023.120449

Kakarla, S., Gangula, P., Rahul, M. S., Singh, C. S. C., & Sarma, T. H. (2020). Smart attendance management system based on face recognition using CNN. Proceedings of IEEE-HYDCON, 1–5. https://doi.org/10.1109/HYDCON48903.2020.9242847

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30, 3146–3154.

Khan, A. I., & Al-Habsi, S. (2020). Machine learning in computer vision. Procedia Computer Science, 167, 1444–1451. https://doi.org/10.1016/j.procs.2020.03.355

Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88. https://doi.org/10.1016/j.media.2017.07.005

McLuckie, A. (2009). Respiratory disease and its management (1st ed.). Springer London. https://doi.org/10.1007/978-1-84882-095-1

Misra, S., & Laskar, R. H. (2019). Development of a hierarchical dynamic keyboard character recognition system using trajectory features and scale-invariant holistic modeling of characters. Journal of Ambient Intelligence and Humanized Computing, 10 (4), 4305–4319. https://doi.org/10.1007/s12652-019-01189-2

Mooney, P. T. (2018). Chest X-ray images (pneumonia). Retrieved August 28, 2026, from https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia

Munir, K., Tanveer, M. U., Alyamani, H. J., Bermak, A., & Rehman, A. U. (2025). PneuX-Net: An enhanced feature extraction and transformation approach for pneumonia detection in X-ray images. IEEE Access, 13, 84024–84037. https://doi.org/10.1109/ACCESS.2025.3568885

O’Shea, K., & Nash, R. (2015). An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458. https://doi.org/10.48550/arXiv.1511.08458

Ouyang, H., Liu, D., Li, S., Ding, W., & Zhan, Z.-H. (2025). Two-stage deep feature selection method using voting differential evolution algorithm for pneumonia detection from chest X-ray images. IEEE Transactions on Emerging Topics in Computational Intelligence, 9, 918–932. https://doi.org/10.1109/TETCI.2024.3425285

Prakash, R. M., Thenmoezhi, N., & Gayathri, M. (2019). Face recognition with convolutional neural network and transfer learning. Proceedings of the International Conference on Smart Systems and Inventive Technology (ICSSIT), 861–864. https://doi.org/10.1109/ICSSIT46314.2019.8987899

Ren, H., Wong, A. B., Lian, W., Cheng, W., Zhang, Y., He, J., Liu, Q., Yang, J., Zhang, C. J., Wu, K., & Zhang, H. (2021). Interpretable pneumonia detection by combining deep learning and explainable models with multisource data. IEEE Access, 9, 95872–95883. https://doi.org/10.1109/ACCESS.2021.3090215

Schulz, H., & Behnke, S. (2012). Deep learning. KI – Künstliche Intelligenz, 26 (4), 357–363. https://doi.org/10.1007/s13218-012-0198-z

Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 60. https://doi.org/10.1186/s40537-019-0197-0

Siddiqi, R., & Javaid, S. (2024). Deep learning for pneumonia detection in chest X-ray images: A comprehensive survey. Journal of Imaging, 10 (8), 176. https://doi.org/10.3390/jimaging10080176

Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations (ICLR), 1–14. Retrieved August 28, 2026, from https://arxiv.org/abs/1409.1556

Szepesi, P., & Szilágyi, L. (2022). Detection of pneumonia using convolutional neural networks and deep learning. Biocybernetics and Biomedical Engineering, 42 (3), 1012–1022. https://doi.org/10.1016/j.bbe.2022.08.001

Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2016). Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE Transactions on Medical Imaging, 35 (5), 1299–1312. https://doi.org/10.1109/TMI.2016.2535302

Vashist, P. C., Pandey, A., & Tripathi, A. (2020). A comparative study of handwriting recognition techniques. Proceedings of the International Conference on Computation, Automation and Knowledge Management (ICCAKM), 456–461. https://doi.org/10.1109/ICCAKM46823.2020.9051464

World Health Organization. (2008). WHO/Health Canada consultation on serological criteria for evaluation and licensing of new pneumococcal vaccines (Report). World Health Organization. Geneva, Switzerland. Retrieved August 28, 2026, from https://www.who.int/publications/m/item/who-consultation-on-new-pneumococcal-vaccines

Zhang, Z. (2016). Introduction to machine learning: K-nearest neighbors. Annals of Translational Medicine, 4 (11), 218. https://doi.org/10.21037/atm.2016.03.37

Zhou, Y., Ni, H., Ren, F., & Kang, X. (2019). Face and gender recognition system based on convolutional neural networks. Proceedings of the IEEE International Conference on Mechatronics and Automation (ICMA), 1091–1095. https://doi.org/10.1109/ICMA.2019.8816275