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{204010,
        author = {Siddhesh Ghode and Prasad Gaikwad and Harsha Dhumal and Gauri kotekar},
        title = {Automated Brain Tumor Detection from MRI Scans using Deep Learning with Django Web Deployment},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {3034-3042},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204010},
        abstract = {Brain tumors represent one of the most life-threatening neurological conditions, and their early and accurate classification plays a vital role in improving patient survival rates. Manual diagnosis from MRI scans is a time-consuming, error-prone, and highly expertise-dependent process. This paper presents TumorSense AI, a deep learning-powered web application designed to automatically classify brain tumors from MRI images into four categories: Glioma, Meningioma, Pituitary Tumor, and No Tumor. The proposed system employs transfer learning by leveraging pre-trained convolutional neural network (CNN) architectures, namely EfficientNetB3, VGG16, and ResNet50, fine-tuned on the Brain Tumor MRI Dataset from Kaggle comprising over 7,000 labeled MRI images. The backend is developed using Django REST Framework, the frontend as a single-page application in HTML/CSS/JavaScript, and model inference is served through a REST API. The system achieves a test accuracy of 97.2% using EfficientNetB3, outperforming VGG16 (95.1%) and ResNet50 (72.2%). Results demonstrate that TumorSense AI provides a reliable, fast, and accessible solution for preliminary brain tumor screening, with potential integration into clinical decision support systems. A PDF diagnostic report with per-class confidence scores is generated for each prediction, enabling clinicians to review AI-assisted findings.},
        keywords = {Brain Tumor Classification, MRI Analysis, Transfer Learning, EfficientNetB3, VGG16, ResNet50, Convolutional Neural Networks, Django REST Framework, Medical Image Processing, Deep Learning, Clinical Decision Support.},
        month = {June},
        }