• Mrs.D.Suganya
• V.Dameshwer
• M.Guga Pradesh
• C.Suriya

In response to the global pandemic, the need for effective identification of COVID-19 and pneumonia has become crucial, especially given the similarity in symptoms between these respiratory conditions and other lung illnesses. Traditional diagnostic challenges prompted the utilization of Chest X-rays as an initial investigative tool for analyzing lung diseases. However, distinguishing between COVID-19 and pneumonia requires advanced image analysis techniques. In this context, the proposed solution employs the ResNet-101 model, a deep residual neural network architecture, implemented in Tensor Flow and Keras. Leveraging the power ofdeep learning, this model is trained on radiographic images to differentiate between COVID-19 and pneumonia, providing a more accurate and efficient diagnostic tool. The developed ResNet-101 model, identified as the best-fit after rigoroustraining and evaluation, is seamlessly integrated into the Django framework. This deployment not only enhances the model's accessibility but also ensures a user-friendly interface for both medical professionals and affected individuals. By incorporating theResNet-101- based classification system into a web application, the flask framework facilitates real-time predictions, aiding in the rapid and accurate identification of COVID-19 and pneumonia cases. This comprehensive approach, combining advanced image analysis with user-friendly deployment, represents a significant stride in improving diagnostic capabilities and addressing the challenges posed by the ongoing pandemic. Our proposed work tackles the diagnostic complexity of distinguishing COVID19 and pneumonia by leveraging Chest X-ray images and employing the ResNet-101 model developed in Tensor Flow and Keras. The integration of this model into the Django framework not only enhances user interaction but also streamlines the deployment of the classification system, offering a valuable tool for accurate and timelydisease identification.

Chest X-rays, ResNet-101

"ENHANCED CLASSIFICATION OF LUNG DISEASE USING RESNET ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 7, page no.h243-h251, July-2022, Available :http://www.jetir.org/papers/JETIR2207739.pdf

"ENHANCED CLASSIFICATION OF LUNG DISEASE USING RESNET ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 7, page no. pph243-h251, July-2022, Available at : http://www.jetir.org/papers/JETIR2207739.pdf