Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{187326,
        author = {Preeti P Mulge and Savitha Patil},
        title = {Automated Diagnosis of Pneumonia from Chest X-Ray Images Using Convolutional Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4509-4516},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187326},
        abstract = {Abstract—Pneumonia is a severe infectious disease that usually results from a bacterial infection within the alveoli of the lung. The infection can cause the lung to become inflamed with pus, which makes breathing difficult and can have other serious health consequences. Medical practitioners commonly utilize imaging such as chest X-ray, ultrasound, or biopsy of lung tissue to properly diagnose pneumonia; however, improper diagnosis can lead to the incorrect course of treatment, potential worsening of a patient's condition, and in extreme cases, death.
With the rising advances in deep learning and more specifically deep learning approaches using Convolutional Neural Networks (CNNs), we can now potentially help clinical practitioners accurately diagnose pneumonia more efficiently through the use of a deep learning method that automatically detects and classifies patients as being healthy or affected using chest X-ray images. In this study, we discussed the proposed deep learning method, implemented using CNNs, to automatically detect the patients as healthy or affected based on the chest X-ray images. The dataset consisted of 20,000 chest X-ray images resized to 256x256 pixels and loaded in batches of 32 until all images were loaded. The trained model achieved a performance evaluation of 95% accuracy.
The results of the study show that the proposed CNN model can quickly and accurately determine the presence and distinction between COVID-19, bacterial pneumonia, and viral pneumonia using chest X-ray images. This study demonstrates the clinical feasibility of the model and its potential to quickly identify pneumonia type for appropriate treatment.},
        keywords = {pneumonia detection; Chest X-ray; deep learning; CNN (Convolutional Neural Network); medical imaging; COVID-19 classification},
        month = {November},
        }