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{185840,
        author = {Devalla Hitesh Sri Sai},
        title = {Enhancing Brain Tumor Segmentation Interpretability Using CNN-Based Pseudocolor Mapping},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {3257-3259},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185840},
        abstract = {This study proposes an advanced deep learning framework aimed at identifying and segmenting brain tumors in Magnetic Resonance Imaging (MRI) scans. The proposed system employs U-Net architecture based on Convolutional Neural Networks (CNN) along with OpenCV. preprocessing methods to automatically define tumor subregions. A pseudocolor visualization module improves interpretability by attributing unique color codes — Red for Enhancing Tumor, Green for Necrotic Core, and Yellow for Peritumoral Edema. Experimental verification on the BRATS 2021 dataset achieved higher segmentation accuracy, with Dice, Jaccard, SSIM and FID outperforming traditional methods. The system presents a clinically interpretable quantitative and reproducible solution for tumor analysis and treatment planning.},
        keywords = {Brain Tumor Detection, Deep Learning Methods, segmentation of MRI images, Convolutional Neural Networks, Explainable AI, Technologies in Medical Imaging.},
        month = {October},
        }