Microwave hyperthermia (MH) treatment for breast cancer is a research interest due to its capability to initiate cell necrosis in malignant tumor or to enhance the effect of other treatment modalities such as chemotherapy. The goal of MH treatment is to increase temperature of malignant tumor up to 45°C based on the treatment plan; however, microwave energy focusing is a challenging problem and may cause unwanted hotspots on healthy tissues. Therefore, there is a need to monitor the temperature to ensure that tumor and healthy tissues are at desired temperatures. In this paper, an iterative differential microwave imaging algorithm for temperature monitoring is presented. The algorithm is based on Born iterative method (BIM) and Tikhonov regularization. Feasibility of the algorithm is shown computationally using realistic digital breast phantoms via (i) TMz polarized 2-D scattered fields; and (ii) scattered fields calibrated from scattering parameters, which are obtained by a 3-D electromagnetic simulation program. An approach for selection of matching medium in hyperthermia monitoring applications is also presented. The reconstructions are performed with scattered field data collected at 11 discrete frequency points uniformly taken from the 0.5-1.5 GHz range. For a specific heating scenario, reconstruction error is lower than 0.3% with ±10% noise on reference dielectric property distribution and 35 dB signal to noise ratio (SNR). The results show that the proposed approach provides up to 3°C and 0.1°C resolution in temperature estimation with ±10\% noise on reference dielectric property distribution for 25 dB and 55 dB SNR values, respectively.

Microwave hyperthermia (MH) requires the effective calibration of the antenna excitations for selective focusing of the microwave energy to the target region with a nominal effect on the surrounding tissue. To this end, many different antenna calibration methods such as optimization techniques and lookup tables have been proposed in the literature. These optimization procedures, however, do not consider the whole nature of the electric field, which is a complex vector field, instead it is simplified to a real and scalar field component. Furthermore, most of the approaches in literature are system-specific, limiting the applicability of the proposed methods to specific configurations. In this paper, we propose an antenna excitation optimization scheme applicable to a variety of configurations and present the results of a Convolutional Neural Network (CNN) based approach for two different configurations. Data set for CNN training is collected by superposing the information obtained from individual antenna elements. The results of the CNN models outperform to look-up table results. The proposed approach is promising as the phase only optimization shows 27% and phase-power combined optimization shows 4% less hot spot-to-target energy ratio than look-up table results.

This study proposes a new method based on deep learning to determine whether the temperature values ​​are at an appropriate level during the use of microwave hyperthermia method in the treatment of breast cancer. To implement our method, we utilize the temperature dependent dielectric properties of biological tissues to generate the heating scenarios that simulates the thermal behavior of biological tissue during the breast cancer hyperthermia treatment. Using the temperature-dependent dielectric properties we designated corresponding temperature thresholds, next, we labeled the malignant tumor region and the healthy tissue region in accordance with the pre-determined thresholds. In addition, scattering problems are solved based on treatment (hot or heated) and pre-treatment (cool) scenarios. Using the difference between hot and cool states, we train, test, and validate the CNN. Our main purpose in the project is to determine whether the tissue is heated in the desired temperature region using only the single frequency differential scattered electric field data.

In the manuscript, we propose a new technique for determination of Debye parameters, representing the dielectric properties of materials, from the reflection coefficient response of open-ended coaxial probes. The method retrieves the Debye parameters using a deep learning model designed through utilization of numerically generated data. Unlike real data, using synthetically generated input and output data for training purposes provides representation of a wide variety of materials with rapid data generation. Furthermore, the proposed method provides design flexibility and can be applied to any desired probe with intended dimensions and material. Next, we experimentally verified the designed deep learning model using measured reflection coefficients when the probe was terminated with five different standard liquids, four mixtures,and a gel-like material.and compared the results with the literature. Obtained mean percent relative error was ranging from 1.21±0.06 to 10.89±0.08. Our work also presents a large-scale statistical verification of the proposed dielectric property retrieval technique.