Medical Microwave Imaging Using Physics-Guided Deep Learning Part 2: The Inverse Solver

Deep learning has the potential to address the bottleneck of conventional medical microwave tomography, which is ill-posed and has a high computation cost. However, current physics-guided deep learning methods may fail to capture the imaged object's salient regions, resulting in misdiagnosis. A deep neural network inspired by the distorted Born iterative method (DBIM) is proposed to address this challenge. This method, which avoids using Green's function, provides a theoretical explanation of why current deep learning methods guided by iterative physics algorithms fail in detecting abnormal tissues, making them unsuitable for real-life clinical applications. The proposed method consists of two main components: a set of forward neural network solvers and a series of inverse neural network blocks for updating the dielectric contrast of the imaging domain. The training of the network, designed to emulate the DBIM framework, is regularized by a hybrid loss function composed of two supervised and one self-supervised function. Each iteration in DBIM is performed using a neural network block with parameters different from those of other blocks, forming a sequential iterative approach. By calculating the perturbations in the electrical properties' profiles at each iteration, the proposed network can accurately reconstruct abnormal tissues associated with signals masked by those from healthy tissues. Assessments of the proposed method using the relative error, structure similarity index measure, Dice similarity coefficient, and Hausdorff distance show significant enhancements (19%, 18%, 40%, and 72%, respectively) compared to two recent deep learning-based microwave medical imaging algorithms.