Blockchain enabled secure image transmission and diagnosis scheme in medical cyber-physical systems

Medical cyber-physical systems (MCPSs) are life critical, context aware, networked systems of medical devices that are increasingly used in hospitals to achieve seamless high-quality healthcare. The design of the MCPS for the healthcare sector necessitates significant attention to achieving security. As the medical images need to be communicated regularly for timely and accurate diagnosis, medical images need to be secured by encryption and blockchain technologies. In this aspect, we present a blockchain enabled secure image transmission and diagnosis (BESITD) for the MCPS environment. The BESITD technique encompasses an image acquisition process that enables the wearable devices to capture the medical images. Then, the presented model executes an intrusion detection system using recurrent neural network to determine the presence of intruders in the MCPS. In addition, the block-wise encryption process takes place in which the medical image is partitioned into n blocks, each of which is individually encrypted using the signcryption technique. Moreover, a consortium blockchain technology is used to store the encrypted image along with the hash value of the original medical image to accomplish integrity and traceability. At the cloud server side, the disease diagnosis process takes place in different stages, namely, multilevel thresholding-based segmentation, MobileNet-based feature extraction, and optimal kernel extreme learning machine (OKELM)-based classification. Furthermore, a multiobjective political optimizer is designed for effective selection of threshold values and KELM parameters. A wide range of simulations was performed on two benchmark medical image datasets, and the experimentation results highlighted the promising performance of the BESITD technique over the recent techniques with the maximum accuracy of 0.9816. (c) 2022 SPIE and IS&T