A Comprehensive Review of Secure and Energy-Efficient MRI Image Transmission via IoT Devices and Hybrid Physics-Guided Neural Networks

Abstract

The rapid growth of Internet of Things technologies in healthcare has significantly improved medical imaging systems, particularly for the transmission and analysis of Magnetic Resonance Imaging data. However, integrating IoT devices into healthcare environments introduces major challenges related to data security, privacy protection, computational efficiency, and energy consumption. MRI images contain highly sensitive patient information and therefore require secure transmission frameworks capable of preventing unauthorized access, cyberattacks, and data leakage. At the same time, IoT devices often operate under limited computational power, storage, and battery capacity, making energy-efficient processing and communication essential for reliable healthcare services. Traditional machine learning and deep learning approaches have achieved strong performance in medical image analysis but often struggle with interpretability, robustness, and efficiency in real-world IoT systems. Hybrid physics-guided neural networks address these limitations by combining domain-specific MRI knowledge with data-driven learning, improving diagnostic accuracy while reducing computational complexity. Recent studies emphasize the integration of encryption methods, edge computing, cloud-based architectures, and hybrid deep learning models to ensure secure and efficient MRI image transmission. Emerging technologies such as federated learning and distributed cloud-edge systems further improve privacy preservation, scalability, and energy efficiency. Overall, secure and energy-efficient IoT-enabled MRI transmission systems represent a promising direction for future intelligent healthcare applications.