International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

Pneumonia Detection and Severity Classification in Chest X-Rays through Region Based Isolation and Optimized CNN Architectures

Kandyala Yaswanth SaiDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science, Madanapalle, AP, IndiaChinta SwathiDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science, Madanapalle, AP, IndiaChakali Yeswanth KumarDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science, Madanapalle, AP, IndiaVeliginti VedavyasDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science, Madanapalle, AP, India

Vol 9 No 2025 (2025): Volume 9, Special Issue of ICCIS-2025 May 2025 | Pages: 25-32

International Research Journal of Innovations in Engineering and Technology

OPEN ACCESS | Research Article | Published Date: 11-06-2025

doi Logo doi.org/10.47001/IRJIET/2025.ICCIS-202504

pdf iconFull Text PDF
Abstract

Globally, pneumonia is still a major health concern, particularly in areas with poor diagnostic facilities. This paper compares two CNN architectures, ConvXNet and a CustomCNN, for deep learning-based pneumonia identification using chest X-ray pictures. Preprocessing methods were used, including data augmentation, contrast enhancement, normalization, and grayscale conversion. A segmentation framework based on U-Net and ResNet32 was also implemented in order to separate lung regions and extract information unique to each region.

CustomCNN demonstrated strong generalization capabilities with a high training accuracy of 96.04%, while ConvXNet excelled in validation and test performance, achieving 88.94% validation accuracy and 90.75% test accuracy. Notably, CustomCNN showcased superior recall 98.5%, making it highly effective in minimizing missed pneumonia cases, whereas ConvXNet achieved slightly better precision 86.4%, ensuring fewer false positives. These findings highlight the complementary strengths of both architectures, emphasizing their potential in supporting accurate and reliable pneumonia detection and severity classification, especially in resource-constrained healthcare settings.

Keywords

Pneumonia Detection, Severity Classification, Chest X-ray Analysis, Deep Learning, Convolutional Neural Networks (CNN), U-Net, ResNet34, Lung Segmentation


Citation of this Article

Kandyala Yaswanth Sai, Chinta Swathi, Chakali Yeswanth Kumar, & Veliginti Vedavyas. (2025). Pneumonia Detection and Severity Classification in Chest X-Rays through Region Based Isolation and Optimized CNN Architectures. In proceeding of Second International Conference on Computing and Intelligent Systems (ICCIS-2025), published in IRJIET, Volume 9, Special Issue ICCIS-2025, pp 25-32. Article DOI https://doi.org/10.47001/IRJIET/2025.ICCIS-202504

Licence Copyright (c) 2026 International Research Journal of Innovations in Engineering and Technology creative common licence This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
References
  1. M. Ali, M. Shahroz, U. Akram, M. F. Mushtaq, and S. C. Altamiranda, "Pneumonia Detection Using Chest Radiographs With Novel EfficientNetV2L Model," IEEE Access, vol. 12, pp. 12345–12356, 2024.
  2. S. Shrimali, "Optimizing Chest X-ray Analysis for Pneumonia Detection Through Comparative Evaluation of Transfer Learning CNN Architectures," in Proceedings of the International Conference on Medical Imaging, 2024, pp. 78–85.
  3. J. Colin and N. Surantha, "Interpretable Deep Learning for Pneumonia Detection Using ChestX-Rays," Computers in Biology and Medicine, vol. 145, pp. 105–112, 2025.
  4. A.Mabrouk, M. El-Hag, and S. Omar, "Pneumonia Detection on Chest X-ray Images Using Ensemble of Deep Convolutional Neural Networks," in Proceedings of the International Conference on AI in Medicine, 2022, pp. 234–241.
  5. P. Gupta, R. Sharma, and M. K. Tiwari, "Pneumonia Detection in Chest X-ray Images Using Efficient and Lightweight Convolutional Neural Networks," in Proceedings of the IEEE International Symposium on Biomedical Imaging, 2024, pp. 512– 515.
  6. N. Shilpa, V. K. Raj, and R. Das, "Revolutionizing Pneumonia Diagnosis: AI-Driven Deep Learning Framework for Automated Detection from Chest X-Rays," in Proceedings of the ACM Conference on Health Informatics, 2024, pp. 89–96.
  7. M. Bundea and G. M. Danciu, "Pneumonia Image Classification Using DenseNet Architecture," Journal of Medical Imaging, vol. 11, no. 3, pp. 345–352, 2024.
  8. S. S. Khan, F. Rahman, and H. Ahmed, “Advances in Medical Imaging: Deep Learning Strategies for Pneumonia Identification in Chest X-rays.” Computers in Medical Imaging and Graphics, vol.89, pp. 56-63, 2024.
  9. M. R. Kumar and B. G. Vani, "Implementation of Deep Learning Mechanisms for Detection and Classification of Pneumonia on Chest X-Ray Dataset," in Proceedings of the IEEE International Conference on Signal Processing, 2024, pp. 102– 109.
  10. J. M. Dudala, "Automated Pneumonia Detection Using a Custom Convolutional Neural Network: A Balanced Approach," Expert Systems with Applications, vol. 205, pp. 117–125, 2024.
  11. V. Tanwar, "Transforming Pneumonia Classification through Deep Learning: A CNN-Based Approach," in Proceedings of the IEEE International Conference on Computer Vision, 2024, pp. 456–463.
  12. M. Beri, S. Jain, and R. Agarwal, "AI-Powered Pneumonia Detection: Enhanced Chest X-ray Interpretation with CNNs," Neural Computing and Applications, vol. 36, no. 2, pp. 789–798, 2024.
  13. F. E. Muchina, T. K. Ndlovu, and A. J. Botha, "Enhancing Interpretability in Pneumonia Detection and Classification: Optimized Deep Neural Networks with Lime Segmentation," in Proceedings of Medical Image Computing and Computer-Assisted Intervention, 2024, pp. 321–328.
  14. T. Babu, J.P. Singh, and A. Mishra, "A Robust Convolutional Neural Network Architecture for Automated Pneumonia Detection," in Proceedings of the IEEE International Conference on Biomedical Engineering, 2024, pp. 215–222.
  15. V. K. Sharma and A. Patel, "Analysis of Prediction of Pneumonia from Chest X-Ray Images Using CNN and Transfer Learning," Computer Methods and Programs in Biomedicine, vol. 230, pp. 106–113, 2024.
  16. Y. Wang, L. Liu, and H. Zhang, "Explainable AI-Based Pneumonia Detection Using Attention-Enhanced CNNs on Chest X-Rays," IEEE Transactions on Biomedical Engineering, vol. 72, no. 1, pp. 112–120, 2024.
  17. R. Mehta, K. Suresh, and A. Jain, "Hybrid Deep Learning Framework for Early Pneumonia Detection Integrating LSTM and CNN Models," Pattern Recognition Letters, vol. 180, pp. 54–61, 2024.
  18. F. A. Siddiqui, M. Alvi, and A. Rehman, "Deep Learning- Based Multi-View Ensemble Strategy for Pneumonia Classification from Chest Radiographs," Journal of Healthcare Engineering, vol. 2024, Article ID 8397024, 2024.
  19. L. Chen, X. Yu, and B. Wang, "Self-Supervised Learning Approaches for Pneumonia Detection from Limited X-Ray Datasets," Artificial Intelligence in Medicine, vol.146, pp.102559, 2024.
  20. D. P. Rao and A. Thakur, "Integrating Clinical Metadata and Radiographic Imaging for Enhanced Pneumonia Detection Using Fusion Deep Learning Models," Computer Methods and Programs in Biomedicine, vol. 239, pp. 107505, 2024.

Copyright @ 2026 IRJIET. All Right Reserved.

Licensed underCreative Commons Attribution 4.0 International License.