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{197777,
        author = {Kanish Shandilya and Devansh Dhingra and Komal Kashyap and Pooja Singh},
        title = {Automated Medical Image Analysis for Disease Diagnosis Using Deep Learning: A Web-Based System Implementation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {8157-8163},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197777},
        abstract = {Deep learning-based medical image analysis has shown strong potential in improving diagnostic accuracy across various clinical tasks. However, many existing works remain limited to model development and lack practical deployment frameworks. This paper presents a web-based implementation of an automated medical image analysis system that integrates multiple deep learning models into a unified platform.
Building upon previously developed convolutional neural network (CNN) models for pneumonia detection [3] and cardiac disease classification [4], and a U-Net-based model for atrium segmentation [1], this work focuses on bridging the gap between model development and deployment. The models, trained using PyTorch in a Jupyter Notebook environment, are exported as checkpoint files and integrated into a Flask-based backend for real-time inference.
The system supports multiple diagnostic workflows and provides functionalities such as user authentication, image upload, dynamic model selection, and result visualization through confidence scores, activation heatmaps, and segmentation overlays. A database system is also incorporated to store user activity and analysis history.
The results demonstrate that deep learning models can be effectively deployed within a structured web-based environment, improving accessibility and practical usability. This work highlights the importance of system-level integration in translating machine learning models into real-world diagnostic tools.},
        keywords = {Deep Learning, Medical Image Analysis, Web-Based System, Flask, Convolutional Neural Network, U-Net, Image Segmentation, Model Deployment},
        month = {April},
        }