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{202202,
        author = {Amay Verma and Anuradha Misra},
        title = {BRAIN TUMOR DETECTION FROM MRI IMAGES USING DUAL MODEL DEEP LEARNING APPROACH},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {5843-5850},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202202},
        abstract = {Brain tumors are a severe neurological condition, the survival rates of which determine the timeliness of their diagnosis. Even though the field of medical imaging has demonstrated a remarkable potential of artificial intelligence, a wide gap is still present between theoretical model accuracy and the practical real-world application of AI in clinical practice. The proposed work introduces an end-to-end, deployable two-model framework that is the first framework that combines the traditional feature-based machine learning (Random Forest) model with a Convolutional Neural Network (CNN) to avert MRI diagnostic assistance. The dual-model ensemble tested on a 4,089image test set scored 99.29% accuracy, which was superior to that of single models, and minimized false positives and false negatives. Most importantly, the study is not just confined to developing a model but also involves the development of a production-ready application that is deployed to the Railway cloud platform and relies on a React frontend and a Flask API. The system, which has an average inference time of 2.8 seconds and highly efficient resource utilization, is a clinical triage tool. The framework shows the feasibility of incorporating AI into time-sensitive neuroradiology workflow by enabling an effective, automated "human-in-the-loop" safety mechanism by automatically alerting human experts to discordant model predictions.},
        keywords = {Brain tumor detection, convolutional neural networks, deep learning, MRI classification, ensemble learning, clinical deployment, medical diagnostic software, cloud computing.},
        month = {May},
        }