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{170478,
        author = {Shaik Neelofar and Dr.N Lakshmi Prasanna and Dr. Ramachandran Vedantam},
        title = {Efficient Lossless Medical Image Encryption with Adaptive QCNN and Secure ROI Management for Real-Time Applications},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {7},
        pages = {1365-1371},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=170478},
        abstract = {Medical images, which often contain highly sensitive patient data, require effective encryption methods to safeguard against unauthorized access, tampering, or theft. A key challenge in this area is protecting the Region of Interest (ROI)—which holds critical diagnostic data—without degrading the image quality or revealing the location of the ROI during transmission. Many existing encryption techniques struggle to find an optimal balance between security and computational efficiency, especially when handling large medical datasets in real-time environments, such as hospitals. Moreover, ensuring accurate ROI detection and securely managing its position are essential to provide comprehensive protection. Recent methods have leveraged Quantum Cell Neural Network (QCNN) hyperchaotic systems and game theory to encrypt medical images. These approaches focus on pixel-level transformations of the ROI to enable lossless recovery and conceal the ROI’s position to prevent exposure. While these methods improve security and accuracy, they introduce substantial computational complexity, making them difficult to deploy in time-sensitive, real-time settings. Additionally, the reliance on precise ROI detection increases the risk of misidentifying critical regions, and the need to conceal the ROI's position further increases data overhead, which can affect transmission efficiency. In response to these challenges, we propose a solution that combines lightweight encryption for non-sensitive regions of the image with adaptive QCNN-based encryption for the ROI, significantly reducing computational load. To improve ROI detection accuracy and reliability, we incorporate machine learning-based techniques and multi-modal image fusion. To manage the hidden position of the ROI, we employ lossless data embedding and differential privacy methods, minimizing overhead and securing the position data without compromising the efficiency of transmission. This integrated approach offers an optimal trade-off between encryption speed, security, and accuracy, making it well-suited for real-time medical applications. This novel encryption scheme ensures the privacy of medical images while enabling their lossless recovery after decryption, providing a comprehensive and secure solution for the protection of sensitive patient information in medical imaging systems.},
        keywords = {Medical Image Encryption, Region of Interest (ROI) Protection, Quantum Cell Neural Network (QCNN), Lossless Encryption, Sensitive Patient Data, Real-Time Medical Applications, Game Theory Optimization, Machine Learning-Based ROI Detection},
        month = {December},
        }