Search

Background and Objective: Medical microwave radiometry (MWR) is used to capture the thermal properties of internal tissues and has usages in breast cancer detection. Our goal in this paper is to improve classification performance and investigate automated neural architecture search methods. Methods: We investigated extending the weight agnostic neural network by optimizing the weights using the bi-population covariance matrix adaptation evolution strategy (BIPOP-CMA-ES) once the topology was found. We evaluated and compared the model based on the F1 score, accuracy, precision, recall, and the number of connections. Results: The experiments were conducted on a dataset of 4912 patients, classified as low or high risk for breast cancer. The weight agnostic BIPOP-CMA-ES model achieved the best average performance. It obtained an F1-score of 0.933, accuracy of 0.932, precision of 0.929, recall of 0.942, and 163 connections. Conclusions: The results of the model are an indication of the promising potential of MWR utilizing a neural network-based diagnostic tool for cancer detection. By separating the tasks of topology search and weight training, we can improve the overall performance.

Evaluation of the effectiveness of treatment of nonspecific lower back pain (LBP) is currently largely based on the patient’s subjective feelings. The purpose of this study was to use passive microwave radiometry (MWR) as a tool for assessing the effectiveness of various treatment methods in patients with acute and subacute nonspecific LBP. Patients with a pain assessment on a visual analogue scale (VAS) of 6 to 10 points were divided into two groups: Group I included patients with pharmacological, syndrome-oriented treatment (n = 30, age 54.9 ± 2.3 years); Group II included a combination of pharmacotherapy with self-controlled energy-neuroadaptive regulation (SCENAR) (n = 25, age 52.8 ± 2.5 years). The analysis showed that the addition of SCENAR therapy (Group II) significantly potentiated the analgesic effect at the stages of treatment, and after 3 weeks, this had increased by more than two times, by 1.3 points on the VAS. There was also a significant decrease in the maximum internal temperature and normalization of the gradient of internal and skin temperatures, and a decrease in thermo-asymmetry, as assessed by temperature fields. Thermal asymmetry visualization allows the identification of the area of pathological muscle spasm and/or inflammation in the projection of the vertebral-motor segment for the possible targeted use of treatment methods such as percutaneous electro neurostimulation, massage, manual therapy, diagnostic and treatment blocks, etc. The MWR method also avoids unnecessary radiation exposure.