A Perceptual Encryption-Based Image Communication System for Deep Learning-Based Tuberculosis Diagnosis Using Healthcare Cloud Services

Block-based perceptual encryption (PE) algorithms are becoming popular for multimedia data protection because of their low computational demands and format-compliancy with the JPEG standard. In conventional methods, a colored image as an input is prerequisite to enable smaller block size better security. However, in domains such medical processing, unavailability color images makes PE methods inadequate secure transmission storage. Therefore, this study proposes method that applicable both grayscale images. proposed method, efficiency achieved by considering steps have negligible effect on compressibility image. The analyses shown system offers security only 12% more bitrate requirement opposed 113% methods. As application we considered smart hospital avails healthcare cloud services outsource deep learning (DL) computations storage needs. EfficientNetV2-based model implemented automatic tuberculosis (TB) diagnosis chest X-ray addition, noise-based augmentation address deficiency analysis. result, accuracy was improved 10%.