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{190942,
        author = {Dr.Jesalkumari Varolia and Dr. Manisha Gopala Krishnan},
        title = {Brain Tumor Detection, Localization and Segmentation from MRI Scans Using ResNet},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {4070-4076},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190942},
        abstract = {Brain tumour detection and localization play a crucial role in medical diagnostics, aiding in early intervention and treatment planning. This project focuses on developing two deep learning models for brain MRI scan analysis. The first model is a classification model using a Residual Network (ResNet) through transfer learning. While leveraging the feature extraction capabilities of ResNet, additional fully connected layers will be trained to classify MRI images. The second model aims to localize tumours in MRI scans that were classified as having a tumour. For this, a ResUNet architecture will be used, which is well-suited for medical image segmentation. Unlike the classification model, this segmentation model will be trained to accurately identify tumour regions within MRI scans, aiming to improve the accuracy of the model. Together, these models provide an end-to-end deep learning pipeline for brain tumour detection and localization, enhancing the accuracy and efficiency of medical diagnosis.},
        keywords = {Magnetic Resource Imaging (MRI), Convolutional Neural Network (CNN), Residual Network (ResNet), Intersection Over Union (IoU) Low Grade Glioma (LGG)},
        month = {January},
        }