Bioinformatics-Inspired Medical Image Protection Through DNA Mapping and Chaotic Diffusion

Abstract

The increasing use of digital healthcare systems has led to a significant rise in the transmission and storage of medical images, creating a critical need for secure image protection mechanisms. Traditional encryption techniques often face limitations in preserving privacy while handling large volumes of medical image data efficiently. This work presents a secure medical image encryption framework based on content-aware DNA computing and chaotic random sequence generation. The proposed system transforms image pixels into DNA-encoded sequences using biologically inspired encoding rules and further applies permutation and XOR-based encryption operations to enhance security. A Piecewise Linear Chaotic Map (PWLCM) is utilized to generate random values that increase encryption complexity and resistance against unauthorized access. The framework consists of image acquisition, DNA encoding, permutation and encryption, correlation analysis, and decryption modules. Experimental results demonstrate that the encrypted images exhibit very low correlation with the original images, indicating strong resistance to statistical and differential attacks. Histogram analysis further confirms the randomness and security of the encrypted output. The successful reconstruction of the original image during decryption validates the reliability of the proposed approach. The obtained results show that the framework provides an effective and robust solution for securing sensitive medical images in healthcare environments while maintaining data confidentiality and integrity.