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{194097,
        author = {Challa Anvitha and Gomatham Joshika Siri Chandana and Chatha Bhavani and M.Sarah Angeline},
        title = {Advanced Medical Image Diagnosis With Multi-Modal Data Integration},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {3905-3915},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194097},
        abstract = {The delay in medical diagnosis in many parts of the world is attributed to the scarcity of medical specialists and the unavailability of an integrated digital platform that brings together imaging, consultation, and pharmacy services under one umbrella. This paper presents a web-based platform for the healthcare sector developed using the Python Flask framework and the PyTorch deep learning framework, integrating six medical datasets for chest X-rays, CT scans of the chest, brain, kidneys, and bone X-rays. The proposed system integrates four CNN models, namely ConvNeXt-Tiny, RegNetY-400MF, MobileNetV3-Small, and EfficientNetV2-S, with ensemble averaging, fine-tuned using transfer learning and Grad-CAM for visual explanations, along with LLaMA 4 Scout Vision for prescription OCR and verification of scans. The proposed system demonstrated model validation accuracy ranging from 77.8% to 84.7% for the CT classification task, while the system also demonstrated the ability to extract structured medication information from handwritten prescriptions and provide real-time notifications for three user roles. The proposed system proves the possibility of unifying AI-based medical imaging, prescription OCR, teleconsultation, and medicine ordering into a single deployable system, making quality healthcare assistance accessible and feasible for real-world applications.},
        keywords = {Deep learning, medical imaging, ensemble CNN, Grad-CAM, transfer learning, prescription OCR, teleconsultation, COVID-19, lung cancer, brain CT, kidney CT, bone X-ray, Flask, PyTorch},
        month = {March},
        }