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{175098,
        author = {Gone Gnanesh and Boddu Naga Sai Kavya and Pothunuri Murali Raghavendra Rao and Ramanoju Bhuvaneswari and Ms. Thommandru Lavanya},
        title = {Classification and Detection of Pneumonia and COVID-19 in X-Ray Images using Deep Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {2562-2568},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175098},
        abstract = {The detection of pneumonia and COVID -19 through chest X-ray image analysis using deep learning presents a critical advancement in medical diagnostics. This study offers a nuanced comparative investigation of two distinctive machine learning approaches: a foundational Convolutional Neural Network (CNN) model entirely from first principles and an innovative hybrid model that integrates sophisticated neural network architectures. While the traditional CNN model, constructed without leveraging pre- existing architectures, establishes a crucial baseline for understanding inherent challenges in medical image classification, the proposed hybrid model strategically employs state-of-art pre-trained networks – ResNet50 and MobileNetV2 – to extract and refine feature representation through advanced transfer learning techniques. The hybrid framework’s distinctive contribution lies in its multifaced neural network integration, methodically combining a Long Short – Term memory (LSTM) network for capturing intricate temporal dependencies with an Artificial Neural Network (ANN) classification layer. This architecture approach enables precise pathological differentiation between pneumonia, COVID – 19, and normal chest radiographic presentations by synthesizing spatial, sequential, and structural analytical dimensions. Rigorous performance evaluation substances the hybrid model’s superior diagnostic capabilities, demonstrating significant improvements across critical performance metrics including accuracy, precision, recall, and F1-score. The research not only illuminates the potential solution for expeditious and accurate respiratory condition detection, particularly valuable in healthcare settings with constrained computational resources.},
        keywords = {},
        month = {April},
        }