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{195841,
        author = {Chanchal Rudraprasad},
        title = {Tumor Segmentation and Multi-Head Classification with XAI Journal},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {766-772},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195841},
        abstract = {This project introduces a transparent and high-performance framework for automated brain tumor analysis, integrating Tumor Segmentation and Multi-Head Classification with Explainable Artificial Intelligence (XAI). By combining advanced Convolution Neural Networks (CNNs) with reinforcement learning and interpretable techniques, the system aims to provide clinicians with reliable, human-understandable diagnostic support through MRI imaging. The core methodology involves the integration of Convolution Neural Networks (CNNs) with the XAI (Grad-CAM), aiming to provide reliable and interpretable diagnostic tool for the tumor segmentation and hence detecting Tumor.
The model architecture is optimized for robust performance on medical imaging data, utilizing convolution, pooling, dense, and dropout layers. A central focus of this work is establishing interpretable, which is critical for clinical applications. This allows healthcare providers to understand, trust, and validate AI-assisted decisions in diagnostics. The final output of the system will be in the form of a clinical report, presenting details about the tumor in a human-understandable format to support clinicians.},
        keywords = {},
        month = {April},
        }