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{201560,
        author = {Naga Dinesh and Balaji and Praneeth and Jasmitha},
        title = {Brain Tumor Detection & Segmentation using BraTs Dataset (U-Net)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10025-10042},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201560},
        abstract = {Brain tumor detection is one of the most important tasks in medical image analysis because early detection can help doctors provide proper treatment and improve patient survival. Manual examination of MRI scans takes more time and may sometimes lead to incorrect diagnosis due to human error. To overcome these problems, deep learning techniques are widely used for automatic tumor detection and segmentation.
This project presents a brain tumor detection and segmentation system using the BraTS2020 MRI dataset. The proposed system uses image preprocessing techniques such as cropping, resizing, and normalization to improve image quality before training. A Lightweight 2D Attention U-Net model is used for tumor segmentation, and a CNN with VGG19 and CBAM attention mechanism is used for tumor classification.
The model is trained on MRI images and predicts whether a tumor is present or not. Attention mechanisms help the model focus more on important tumor regions and improve feature extraction. The performance of the model is evaluated using metrics such as Accuracy, Precision, Recall, F1-Score, Dice Score, IoU, and HD95.
The experimental results show that the proposed system can effectively detect brain tumors and generate segmentation masks with good performance. The developed system reduces manual effort and supports doctors in medical diagnosis. This project demonstrates the importance of deep learning in healthcare applications and medical imaging systems.},
        keywords = {},
        month = {May},
        }