Recent Advances in IoT-Based Breast Cancer Detection with Bayesian Quantized Neural Networks Using Energy-Efficient WSN: A Systematic Review

Abstract

Breast cancer remains one of the most widespread and life-threatening diseases, making early and accurate detection essential for improving survival rates. The integration of Internet of Things (IoT) technologies in healthcare has enabled real-time monitoring, efficient data collection, and remote diagnosis. Wireless Sensor Networks (WSNs) support this ecosystem by continuously capturing and transmitting medical data while maintaining energy efficiency. Despite these advancements, challenges such as high computational demands, limited battery life, data security concerns, and diagnostic uncertainty continue to hinder system performance. Deep learning techniques, particularly convolutional neural networks (CNNs), have achieved high accuracy in breast cancer detection using imaging modalities like mammography and MRI, often exceeding 90%. However, conventional models lack the ability to quantify uncertainty, which is critical for clinical decision-making. Bayesian neural networks (BNNs) address this limitation by providing probabilistic predictions and confidence measures, improving diagnostic reliability. Furthermore, quantized neural networks reduce computational complexity and energy consumption, making them suitable for resource-constrained IoT and WSN environments. This review examines recent developments in IoT-based breast cancer detection, emphasizing Bayesian quantized models and energy-efficient WSN architectures, while outlining key challenges and future research directions for building scalable, reliable, and intelligent healthcare systems.