In this paper, a microwave imaging approach based on artificial neural networks (ANNs) for neck tumor detection is presented. The aim of this technique is to retrieve the geometric and dielectric properties of the neck to identify the possible presence of tumors, starting from scattered electric field data. A fully-connected neural network is developed to test the feasibility of the proposed approach. Moreover, a numerical model including the main features of a cross section of the neck is specifically designed in order to create a suitable training dataset. Subsequently, for the optimization of the ANN architecture and performance evaluation, a numerical analysis is conducted. A set of simulated cases, based on realistic neck phantoms, is tested to evaluate the robustness of the network. Preliminary results show the possibility to identify and locate neck tumors.

An inverse scattering method working at microwave frequencies for cervical diagnostics is proposed in this work. The aim is the diagnosis of cervical myelopathy, which is a disease that affects the first part of the spinal cord (between the C3 and C7 vertebra). A preliminary feasibility analysis oriented toward the development of an imaging system is reported. The system prototype includes a set of antennas that illuminate the neck and retrieve samples of the scattered electric field. The related inverse scattering problem is solved by using a nonlinear Newton-type reconstruction procedure, which provides two-dimensional images of the dielectric parameters of a neck cross section. A simplified cylindrical phantom mimicking the human neck has been designed for assessing the feasibility of the envisioned microwave measurement system and processing technique. Numerical results are reported to evaluate the capabilities of the proposed approach. Moreover, initial experimental results have been obtained by using cylindrical containers and a 3D printed version of the developed neck phantom.

Magnetic biomaterials are multifunctional tools currently under investigation as theranostic platforms for biomedical applications. They can be implanted in bone tissue after bone cancer resection to perform local interstitial hyperthermia treatment. Given the requirements of high quality treatment, the hyperthermia therapy should be performed monitoring the system temperature, to avoid hot spots and control the treatment outcome. It is known that the magnetic properties of such implants vary with temperature. It is hypotesized that the treatment dynamic could be monitored using a microwave monitoring system. The variation of the electromagnetic properties of the biological tissues and the magnetic implant during the therapy would result in a different propagation of the microwave signal. This work investigates the feasibility of using microwaves to non-invasively monitor hyperthermia treatments with a simplified monodimensional propagation model. The forward problem is solved to identify the working frequencies, the matching medium properties and study several candidate materials. By using the numerical solutions from nonlinear and multiphysics simulations of the bone tumor hyperthermia treatment using magnetic scaffolds, the microwave signal propagation dynamic is studied. From our feasibility analysis, we found that it is possible to correlate the average tumor temperature with significant ( $\sim$ 20 dB) variations in the transmission coefficient during a typical interstitial hyperthermia session using magnetic scaffolds. Our work brings together, for the first time, the electromagnetic material properties, the physio-pathology and physics of the hyperthermia treatment and the microwave propagation problem, thus paving the route for the development of an innovative theranostic system.

In this letter, a microwave imaging strategy based on an artificial neural network (ANN) is applied, for the first time, to experimental data gathered from simplified neck phantoms. The ANN is used for solving the underlying inverse scattering problem, with the aim of retrieving the dielectric properties of the neck for monitoring and diagnostic purposes. The ANN is trained using simulated phantoms, to overcome the limited availability of experimental data. First, a simple configuration with a liquid-filled glass beaker is tested. Then, simplified 3-D-printed models of the human neck are considered. The preliminary findings indicate the possibility of training the network with numerical simulations and testing it against experimental measurements.

The nondestructive characterization of cylindrical objects is needed in many fields, such as medical diagnostics, tree trunk inspection, or concrete column testing. In this study, the radar equation of Lambot et al. is combined with cylindrical Green’s functions to fully model and invert ultra-wideband (UWB) ground-penetrating radar (GPR) data and retrieve the properties of cylindrical objects. Inversion is carried out using a lookup table (LUT) approach followed by local optimization to ensure retrieval of the global minimum of the objective function. Numerical experiments were conducted to analyze the capabilities of the developed inversion procedure to estimate the radius, permittivity, and conductivity of the cylinders. The full-wave model was validated in laboratory conditions on metallic and plastic pipes of different sizes. The adopted radar system consists of a lightweight vector network analyzer (VNA) connected to a single transmitting and receiving horn antenna. The numerical experiments highlighted the complexity of the inverse problem, mainly originating from the multiple propagation modes within cylindrical objects. The laboratory measurements demonstrated the accuracy of the forward modeling and reconstructions in far-field conditions.