Deep Learning and Optimization Approaches in IoT-Based Breast Cancer Detection with Bayesian Quantized Neural Networks Using Energy-Efficient WSN: A Review

Abstract

The integration of Internet of Things (IoT) technologies with deep learning has significantly enhanced the early detection and diagnosis of breast cancer. However, the deployment of intelligent diagnostic systems in IoT environments introduces challenges related to computational efficiency, energy consumption, and data security. This review paper explores recent advancements in deep learning and optimization approaches for IoT-based breast cancer detection, with a particular focus on Bayesian Quantized Neural Networks (BQNN) and energy-efficient Wireless Sensor Networks (WSNs). The study examines various deep learning architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based models used for medical image classification and tumour detection. Additionally, optimization techniques including feature selection, model pruning, quantization, and energy-aware routing are analysed for improving system performance in resource-constrained environments. Bayesian neural networks are highlighted for their ability to model uncertainty and improve diagnostic reliability, while quantization techniques reduce computational complexity and energy consumption. The role of WSNs in real-time data acquisition and transmission is also discussed, emphasizing the need for energy-efficient communication protocols. Comparative analysis reveals that hybrid approaches integrating deep learning, optimization algorithms, and IoT architectures provide a balanced solution for accuracy, efficiency, and scalability. The paper concludes by identifying key challenges and future research directions in developing robust, low-power, and intelligent healthcare systems.