Federated convolutional model with cyber blockchain in medical image encryption using Multiple Rossler lightweight Logistic sine mapping

Abstract

Doctors' ability to diagnose and treat patients will be facilitated by the Internet of Medical Things (IoMT), which can connect a variety of medical imaging devices to medical data network. A number of encryption techniques have been suggested and created in an effort to enhance medical picture encryption. This study suggests a unique method for classifying and encrypting medical images using machine learning and a blockchain IoT paradigm. Here, the input medical image has been learned with Federated convolutional adversarial learning (FCAL) and a blockchain model. This image has been encrypted utilising Multiple Rossler lightweight Logistic sine mapping (MRLLSM).For diverse medical imaging datasets, experimental analysis is done in terms of accuracy, precision, data security rate, and encryption time. A high level of security may be attained using the suggested technique while still performing well in terms of efficiency, according to extensive experimental findings and security analysis.