Severity Based Light-Weight Encryption Model for Secure Medical Information System

As the amount of medical images transmitted over networks and kept on online servers continues to rise, the need to protect those images digitally is becoming increasingly important. However, due to the massive amounts of multimedia and medical pictures being exchanged, low computational complexity techniques have been developed. Most commonly used algorithms offer very little security and require a great deal of communication, all of which add to the high processing costs associated with using them. First, a deep learning classifier is used to classify records according to the degree of concealment they require. Medical images that aren’t needed can be saved by using this method, which cuts down on security costs. Encryption is one of the most effective methods for protecting medical images after this step. Confusion and dispersion are two fundamental encryption processes. A new encryption algorithm for very sensitive data is developed in this study. Picture splitting with image blocks is now developed by using Zigzag patterns, rotation of the image blocks, and random permutation for scrambling the blocks. After that, this research suggests a Region of Interest (ROI) technique based on selective picture encryption. For the first step, we use an active contour picture segmentation to separate the ROI from the Region of Background (ROB). Permutation and diffusion are then carried out using a Hilbert curve and a Skew Tent map. Once all of the blocks have been encrypted, they are combined to create encrypted images. The investigational analysis is carried out to test the competence of the projected ideal with existing techniques.