Medical Image Encryption Using an Hybrid of 2DNA Encoding and Noise-Crypt

Medical images, including CT scans, MRIs, and X-rays, contain sensitive patient information that needs to be safe-guarded from access by others. Traditional encryption methods often struggle to maintain a balance between security and quality retention of the images. This work implements and compares an hybrid encryption scheme that combines 2DNA Encoding and Noise Crypt with 2DNA encoding and Noise Crypt, to secure medical images in a web-based application implemented using Streamlit and FastAPI. The hybrid 2DNA-NoiseCrypt method uses DNA-inspired encoding and chaotic encryption to enhance security without degrading the image structure. The application allows users to work with medical image encryption and analyze security metrics such as Peak Signal-to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Mean Squared Error (MSE), Entropy, and Unified Averaged Changed Intensity (UACI). Experimental results show that the combined 2DNA-NoiseCrypt method outperforms isolated methods by providing higher entropy and encryption. Compared to 2DNA encoding and Noise Crypt, the hybrid method provides greater security while ensuring image quality, thus offering a high suitability for medical image protection.