A Review of Modern Techniques for Skin Cancer Detection Using Imaging, Spectroscopy, and Machine Learning

Abstract

Skin cancer is one of the most prevalent forms of cancer, requiring early and accurate diagnosis to improve patient outcomes. This study presents a comprehensive review of non-invasive skin cancer detection techniques, including millimeter-wave imaging, microwave reflectometry, bio-impedance analysis, terahertz sensing, and machine learning-based image analysis. These approaches exploit variations in dielectric, structural, and biochemical properties between normal and malignant tissues. The integration of advanced sensing technologies with intelligent classification methods significantly enhances diagnostic accuracy and reliability. However, challenges such as limited penetration depth, data variability, and lack of multimodal integration persist. The study highlights current advancements, identifies key research gaps, and emphasizes the need for hybrid, cost-effective, and real-time diagnostic systems for improved clinical applicability.