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{200056,
        author = {Dhruv Singh Karki and Govind tiwari and Kanhaiya jha},
        title = {AUTOMATED BRAIN TUMOR DETECTION USING EFFICIENTNET- B0 AND TRANSFER LEARNING: A FLASK-BASED WEB APPLICATION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {3586-3592},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200056},
        abstract = {Brain tumor detection from Magnetic Resonance Imaging (MRI) scans remains a critical yet time-intensive diagnostic task. This paper presents a full-stack web application that automates binary brain tumor classification using a fine-tuned EfficientNet-B0 convolutional neural network. The model, pre-trained on ImageNet and adapted via transfer learning on a composite MRI dataset (Kaggle + Br35H, ~3,200 images), achieves 98.2% classification accuracy with sub-second inference latency. The system is deployed via a lightweight Flask backend, offering a clean HTML/CSS/JavaScript interface for non-technical clinical users. Explainability is addressed through Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations. Experimental results demonstrate the system's viability as a scalable, accessible clinical decision-support tool. This paper proposes a deep learning–based automated brain tumor detection system integrated into a web-based framework. The proposed approach leverages Convolutional Neural Networks (CNNs) to automatically extract high-level features from MRI images without manual intervention. Pre-trained architectures such as Inception V3 are explored due to their robustness and computational efficiency. The system aims to provide a user-friendly web interface that enables real-time tumor detection, making advanced diagnostic assistance accessible to healthcare professionals and researchers. This work is presented as a Phase-1 proposal, outlining the system design, methodology, dataset usage, and expected outcomes.},
        keywords = {Brain Tumor Detection, EfficientNet-B0, Transfer Learning, Convolutional Neural Network, MRI Classification, Flask, Grad-CAM, Inception V3, Medical Image Analysis.},
        month = {May},
        }