The methods of processing biomedical images, namely thermal images, are investigated. Algorithms for calculating the temperature and area of the zone of interest in the manual mode operator-computer, as well as in the automatic mode, are specified. Methods of thermal image processing are presented, namely recursive generalized contour preparation and preparation based on histograms of connections. An experimental study of these methods was performed, as well as a comparison of thermal image segmentation methods in manual segmentation modes, using contour preparation-based segmentation, multilevel segmentation based on recursive generalized contour preparation, and automatic segmentation based on connectivity histograms.

No abstract

The purpose of this study is to develop a fuzzy expert system based on the analysis of biomedical images for the diagnosis of oncological diseases using breast cancer as an example. The main directions of application of mathematical methods in medical diagnosis are analyzed, their drawbacks are evaluated, and principles of diagnosis, based on fuzzy logic, are formulated. Mathematical models and algorithms are developed, formalizing the process of diagnostic decision-making based on fuzzy logic with quantitative and qualitative parameters of the patient's condition; mathematical models of membership functions are developed, formalizing the representation of quantitative and qualitative parameters of the patient's condition in the form of fuzzy sets, used in models and algorithms for diagnosing and determining the diagnosis in the case of breast cancer.

This paper is devoted to topical issues - the development of methods for analyzing texture images of breast cancer. The main problem that is resolved in the article is that the requirements for the results of pre-processing are increasing. As a result of the task, images of magnetic resonance imaging of the breast are considered for image processing using texture image analysis methods. The main goal of the research is the development and implementation of algorithms that allow detecting and isolating a tumor in the breast in women in an image. To solve the problem, textural features, clustering, orthogonal transformations are used. The methods of analysis of texture images of breast cancer, carried out in the article, namely: Hadamard transform, oblique transform, discrete cosine transform, Daubechies transform, Legendre transform, the results of their software implementation on the example of biomedical images of oncological pathologies on the example of breast cancer, it is shown that The most informative for image segmentation is the method based on the Hadamard transform and the method based on the Haar transform. The article presents recommendations for using the results in practice, namely, it is shown that clinically important indicators that make a significant contribution to assessing the degree of pathology and the likelihood of developing diseases, there are other information parameters: diameter, curvature, etc. Therefore, increased requirements for the reliability, accuracy, speed of processing biomedical images.

The article analyzes the growing incidence of breast cancer, which has become particularly clear in the last two decades, requires special involvement of all specialists and researchers in this area. Identification of patients with hereditary forms of breast cancer allows to form strategies for early diagnosis, prevention and treatment. As a result of the analysis, the multiple regression equation was obtained.The statistical significance of the equation was verified using the coefficient of determination and Fisher's test. Prompt diagnosis should be combined with effective cancer treatment, which in many cases requires specialized cancer care at some level. Thanks to the creation of centralized services in oncology facilities or hospitals, which use as a model everything related to breast cancer, the treatment of breast cancer can be optimized while improving the treatment of other cancers.