Implementation of Secure Lossless Compression of Medical Images Based on Multi- Model Frame Work

Abstract

The integration of the Internet of Medical Things (IoMT) into healthcare systems has transformed patient care by enabling continuous monitoring, remote diagnostics, and intelligent treatment delivery. However, this rapid expansion of interconnected medical devices has also introduced critical cybersecurity concerns, including unauthorized access, data breaches, and system-level disruptions that compromise patient safety and privacy. This survey conducts a structured review and classification of existing hybrid security architectures specifically those that combine conventional rule-based mechanisms with intelligent approaches such as machine learning (ML) and deep learning (DL) to address these growing security challenges in IoMT environments. Through critical analysis of peer-reviewed literature, the study categorizes security threats across IoMT architectural layers and evaluates state-of-the-art hybrid Intrusion Detection and Prevention Systems (IDPS) based on key performance indicators, including detection accuracy, false positive rates, and response times. While the study does not explore implementation trends, it provides forward-looking recommendations such as the adoption of federated learning, lightweight edge-based models, and privacy-preserving techniques to improve resilience and scalability. Ultimately, this review offers a foundational resource for researchers and practitioners working toward robust and adaptive security solutions in IoMT-enabled healthcare ecosystems