Integrating microwave reflectometry and deep learning imaging for in-vivo skin cancer diagnostics

Abstract

Skin cancer is a major global health concern, with rising incidence rates. However, current diagnostic methods often lack objectivity, speed, and non-invasiveness. To overcome this limitation, this work proposes a novel approach combining microwave reflectometry (MR) with artificial intelligence (AI) techniques for the diagnosis of in-vivo skin cancer. In particular, MR exploits the dielectric properties of biological tissues, revealing chemical-physical differences in normal skin and benign/malignant lesions. To better improve the diagnostic performance, MR analysis is integrated with AI algorithms, particularly those based on deep learning (DL) and convolutional neural networks (CNNs), which analyze dermoscopic skin images and identify asymmetry, irregular borders, abnormal colorations, and other skin cancer indicators. Combining MR with AI image analysis provides a comprehensive diagnostic approach, as MR informs on tissue dielectric composition, while AI analyzes lesion-specific details, offering more accurate and timely assessments. This combined approach promises early skin cancer detection and could significantly impact clinical practice.