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{182889,
        author = {Ramya c k and Dr. Padmaja devi and Mr. Vijaykumar},
        title = {VisionDx: Automated COVID-19Detection using VGG16, ResNet50, and Custom CNNs on Chest XRays},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {3659-3665},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182889},
        abstract = {Controlling COVID-19 requires early detection. It’s dissemination, particularly in environments with limited resources. These Convolutional neural networks (CNNs) are outlined in this study-based model for categorizing X-ray pictures of the chest COVID-19 favorable or typical. The suggested architecture consists of dense, pooling, and convolutional lay-trained on a preprocessed dataset with enhanced images to enhance generalization. Making use of binary cross-checking and the Adam optimizer 25 epochs were used to train the model for entropy loss reaching 92% validation and 96% training accuracy, precision. Results demonstrate strong performance on unseen data, highlighting the potential of CNNs as accessible tools for supporting early COVID-19 diagnosis. Future work will explore larger datasets and advanced or quantum CNN architectures.},
        keywords = {Classical CNN, VGG16, AlexNET and ResNet50.},
        month = {July},
        }