Recent Advances in Secure and Energy-Efficient Secure MRI Image Transmission via IoT Devices and Hybrid Physics-Guided Neural Networks: A Systematic Review

Abstract

The rapid growth of Internet of Things (IoT) technologies in healthcare has significantly improved remote diagnosis, patient monitoring, and medical image transmission, particularly for Magnetic Resonance Imaging (MRI). However, secure and energy-efficient transmission of MRI images remains a major challenge due to the large size of imaging data, privacy concerns, and limited computational resources of IoT devices. This review examines recent advancements in secure MRI image transmission using hybrid approaches that integrate deep learning, physics-guided neural networks, and IoT communication frameworks. Recent studies highlight the use of encryption techniques such as chaotic maps, Arnold transforms, and generative adversarial networks combined with deep learning models to enhance data confidentiality, robustness, and transmission quality. Hybrid architectures integrating convolutional neural networks with encryption mechanisms enable secure MRI analysis without compromising diagnostic accuracy. Physics-Guided Neural Networks further improve MRI reconstruction by incorporating physical constraints into learning models, reducing data requirements and improving reconstruction quality in resource-constrained environments. Additionally, lightweight neural architectures, edge computing, and optimized communication protocols such as MQTT contribute to lower latency, reduced energy consumption, and improved scalability. These advancements demonstrate the growing potential of AI-driven IoT frameworks for secure, reliable, and efficient MRI image transmission in modern healthcare systems.