In this article we investigate the efficiency of deep learning algorithms in solving the task of detecting anatomical reference points on radiological images of the head in lateral projection using a fully convolutional neural network and a fully convolutional neural network with an extended architecture for biomedical image segmentation -U-Net. A comparison is made for the results of detection anatomical reference points for each of the selected neural network architectures and their comparison with the results obtained when orthodontists detected anatomical reference points. Based on the obtained results, it was concluded that a U-Net neural network allows performing the detection of anatomical reference points more accurately than a fully convolutional neural network. The results of the detection of anatomical reference points by the U-Net neural network are closer to the average results of the detection of reference points by a group of orthodontists.

This article demonstrates the possibility of creating memory devices based on polycrystalline mayenite. In the course of the study, structural characterization (XRD, TEM) of ceramic samples of mayenite was carried out, as well as a study of the spectral (THz range) and electrophysical characteristics. Materials obtained by calcination at high (1360–1450 °C) temperatures in an inert argon atmosphere differ in the degree of substitution of oxygen anions О2− for electrons, as indicated by the data on the unit cell parameters and dielectric constant coefficients in the range of 0.2–1.3 THz, as well as differences in the conducting properties of the samples under study by more than five orders of magnitude, from the state of the dielectric for C12A7:O2− to the conducting (metal-like) material in the state of the C12A7:e− electride. Measurements of the current–voltage characteristics of ceramic C12A7:e− showed the presence of memristive states previously detected by other authors only in the case of single crystals. The study of the stability of switching between states in terms of resistance showed that the values of currents for states with high and low resistance remain constant up to 180 switching cycles, which is two times higher than the known literature data on the stability of similar prototypes of devices. It is shown that such samples can operate in a switch mode with nonlinear resistance in the range of applied voltages from –1.3 to +1.3 V.

The possibility of application of different textural features for the lung disease automatic diagnosis on the basis of the 2D digital computed tomography (CT) images was studied. Histogram features, covariance features, Haralick’s features and run length features were used. A procedure based on the discriminant analysis criterion was used for the selection of the best features group. We experimentally showed that the approach offered is convenient to use for solving the problem of automatic diagnosis on a 160-image set received during examination of patients with a chronic obstructive pulmonary disease. The resulting group of effective features includes two Haralick’s features and three run length features, providing the error rate of 0.11, which is better than similar results obtained without a feature selection procedure.

We studied the formation process of a mayenite structure from hydroxide precursors in different gas media. According to X-ray diffraction data, this method allows a well-crystallized mayenite (Ca12Al14O33 or C12A7) phase to be obtained at low (500–900 °C) temperatures with an insignificant impurity of CaO. It was shown that the lattice parameters for C12A7 obtained in an inert atmosphere (Ar) were lower when compared with similar samples in the air. These results can be explained by the different levels of oxygen nonstoichiometry in the resulting phase. We noted that sintering and crystallization of mayenite proceeds at lower temperatures in Ar than in the air medium. We found the presence of donor and acceptor active sites on the surface of mayenite, which was detected by the spin probe method. The specific (per unit surface) concentration of such sites (2.5 × 1016 m−2 and 1.5 × 1015 m−2 for donor and acceptor sites, respectively) is comparable to that of γ-Al2O3, which is traditionally used as catalyst support. This allows it to be used in adsorption and catalytic technologies, taking into account its high specific surface area (~30–50 m2/g at a low synthesis temperature).

We proposed a method of automated scintigram image processing enabling an objective evaluation of the renal parenchyma condition to be made based on scintigram brightness and geometric characteristics with threshold processing. We studied the method using a set of real radionuclide images of a renal transplant. The results of clinical studies confirm the effectiveness of the developed method. We obtained objective numerical values associated with thresholding the image from 40% to 80%, based on which one can form an independent assessment of the presence or absence of focal lesions in the renal parenchyma.

We compare approaches for the automatic detection of pathological changes in brain MRI images that are visible to the naked eye. We analyse multi-stage approaches based on deep learning and threshold processing. A convolutional neural network was formed, a classifier was built based on the use of an ensemble of decision trees, and an algorithm was created for multi-stage image processing. Because of experimental studies, it was found that the most effective method for recognizing images of magnetic resonance imaging is an approach based on an ensemble of decision trees. With its help, 95 % of the images from the test sample were classified correctly. At the same time, using the convolutional neural network, it was possible to classify correctly all images containing the area of pathological changes. The data obtained can be used in practice for the diagnosis of brain diseases, for automating the processing of a large number of studies of magnetic resonance imaging.

This article discusses an idea of a joint analysis of medical images and texts aimed at improving the quality of automated diagnosis of emphysema. We compare the quality of image classification with and without taking into account the localization of the pathology mentioned in radiological reports. The study was carried out on sets of real images of computed tomography of the lungs obtained in clinical studies at Samara State Medical University. It was established that the use of information on the localization of pathology contained in radiological reports leads to an increase in the F-score for the detection from 0.55 to 0.73.

The article presents the results of evaluation of vitamin D3, osteoprotegerin, carbohydrate and fat metabolic parameters in women with type 2 diabetes and obesity. The study subjects showed an increase of osteoprotegerin, decrease of vitamin D3, insulin resistance and compensatory hyperinsulinemia.