Copyright © 2025 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{184373,
        author = {Akshata Jadhav},
        title = {Deep Learning for Automated Segmentation of Brain Tumor MRI Images},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {1289-1295},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184373},
        abstract = {Brain tumors pose a significant challenge in neurology and oncology, with early detection being crucial for effective treatment and improved patient outcomes. This project aims to automate the segmentation and classification of brain tumors from Magnetic Resonance Imaging (MRI) images using deep learning techniques. The proposed system leverages advanced methods such as pre-processing, feature extraction, segmentation, classification, and prediction to streamline the diagnostic process. MRI images are initially pre-processed to enhance image quality through resizing, grayscale conversion, and bilateral filtering. Statistical and texture-based features are then extracted using methods like mean standard deviation and Gray-Level Co-occurrence Matrix (GLCM). Tumor segmentation is performed using thresholding techniques and the U-Net++ architecture, while classification is carried out using deep learning models such as VGG-19, Inception, and ResNet-50. The final output predicts the presence of a tumor and classifies it based on the type of disease. The system is deployed through a user-friendly web interface, allowing users to upload MRI images, receive predictions, and access performance metrics. This automated approach aims to assist healthcare professionals in providing faster, more accurate diagnoses, ultimately improving patient care by reducing the reliance on manual interpretation and increasing the efficiency of the diagnostic process.},
        keywords = {Brain tumor, MRI, Deep Learning, U-Net++, VGG-19, ResNet-50, Inception},
        month = {September},
        }