• B V Yashaswini
• Sanal
• Jithesh B
• Ajay Prinston Pinto

This work focuses on building a deep learning-powered platform utilizing Convolutional Neural Networks (CNN) to effectively recognize pneumonia from chest X-ray scans. The platform incorporates current techniques in image preprocessing, training of neural models, evaluation metrics, and classification accuracy. Using a publicly available labeled dataset from Kaggle, the proposed model is intended to function as a dependable diagnostic aid for the timely detection of pneumonia. Featuring a clean and interactive user interface, the application is developed using Flask and can be accessed in both web-based and offline modes. This approach aims to streamline the diagnostic workflow, empowering users to make better-informed medical decisions based on predictive outcomes from the model.

Pneumonia diagnosis, Chest radiographs, CNN architecture, Healthcare imaging, Neural networks, Medical image classification, AI-based diagnostic system, Training models, Web-based deployment

"PNEUMONIA DETECTION USING DEEP LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.798-801, July-2025, Available :http://www.jetir.org/papers/JETIRGX06150.pdf

"PNEUMONIA DETECTION USING DEEP LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp798-801, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06150.pdf