Deep learning enhanced medical microwave Imaging

This chapter is devoted to the thriving field of deep learning enhanced medical microwave imaging. Microwave imaging is a technology with applications in different fields involving the inspection of hidden or nested targets. Thanks to its non-ionizing nature and low-cost, it represents an emerging modality for non invasive medical diagnostics, with potential to compensate the limitations of well-established medical imaging modalities. However, microwave imaging faces several challenges that are slowing down its adoption. In particular, the underlying problem at the core of microwave imaging is a non-linear and ill-posed inverse scattering problem. Recently, employing deep learning techniques to address the difficulties in solving inverse scattering problems has received a significant attention. In this regard, this chapter reviews the main aspects concerned with the adoption of deep learning to enhance microwave imaging and then provides two examples to outline its potential in medical imaging applications. The first application is concerned with monitoring of thermal treatments (hyperthermia) whereas the second is dedicated to imaging the brain.