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{206666,
        author = {Dipika Paranjape and Meenal Shelar and Aachal Khodape and Sumit Borse},
        title = {An Explainable AI-Assisted Diagnosis System for Chest, Brain, and Bone Medical Imaging},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {2853-2863},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206666},
        abstract = {The concept of deep learning showed that the system implementation includes combining visual and textual explanations to improve understanding. The paper discusses supporting the disease categories among multiple medical imaging tasks. Proposed system diagnosis involves chest and bone X-rays and brain-MRIs using EfficientNet-B0 and DenseNet-like Convolutional Neural Network (CNN). The system’s unique characteristic is the use of Explainable AI (XAI) techniques like Gradient Class Activation Mapping (Grad-CAM) to output visual heatmaps by emphasizing relevant regions in medical images. The system takes medical images as the only input and passes them through CNN models based on the selected category. It then analyses images to emphasize key areas in them, while language-based clinical reasoning helps interpret the clear and meaningful insights. Moreover, the project was end-to-end implemented using a Streamlit-based web interface, which gave visual heatmap generation, confidence score, and report generation along with the correct medical references. The system also serves as a decision-support tool, which improves transparency and usability rather than being a replacement for clinical expertise.},
        keywords = {Explainable Artificial Intelligence, Deep Learning, Convolutional Neural Networks, Medical Image Analysis, Gradient Class Activation Mapping, decision support tool.},
        month = {July},
        }