A Comprehensive Review of Energy Efficient Quantum Convolutional Neural Networks with Attention-Based Models for Quality Preservation in WSN assisted IoT Medical Image Diagnostics

Abstract

The rapid advancement of Wireless Sensor Networks (WSNs) and Internet of Things (IoT) technologies has transformed modern healthcare by enabling continuous acquisition, transmission, and intelligent analysis of medical data. In medical image diagnostics, these technologies support remote monitoring, early disease identification, and timely clinical decision-making. However, transmitting and processing high-dimensional medical images through resource-constrained WSN-assisted IoT environments introduces challenges related to energy consumption, bandwidth limitations, computational complexity, and image-quality preservation. Conventional Convolutional Neural Networks (CNNs) provide strong diagnostic performance but often demand substantial computational resources, limiting their suitability for energy-constrained healthcare devices. Quantum Convolutional Neural Networks (QCNNs) have consequently emerged as a promising computational paradigm for efficient medical image analysis. By exploiting quantum principles such as superposition and entanglement, QCNNs offer opportunities for efficient feature representation and reduced computational overhead. Integrating attention mechanisms can further strengthen diagnostic performance by emphasizing clinically significant image regions while suppressing irrelevant information. This review examines energy-efficient QCNNs integrated with attention-based models for quality-preserving medical image diagnostics in WSN-assisted IoT environments. It critically evaluates recent architectures, energy-efficiency strategies, diagnostic performance, and quality-preservation methods while identifying existing limitations and research gaps. The review further highlights future directions toward scalable, intelligent, and resource-efficient IoT healthcare diagnostic frameworks.