РАЗРАБОТКА МОДЕЛИ АВТОМАТИЧЕСКОГО ОПРЕДЕЛЕНИЯ ГРАНИЦ ПАТОЛОГИИ ПРИ ОНКОЛОГИЧЕСКОЙ ДИАГНОСТИКЕ ЛЕГКИХ

Resultado de la investigación: Articlerevisión exhaustiva

Resumen

The paper deals with the problem of determining the boundaries of pulmonary pathologies in the diagnosis of lung cancer. Pulmonary pathologies are one of the most widespread diseases in the history of mankind, leading to high mortality rates worldwide. This is due to the presence of complexities that provoke errors in the diagnosis of pathology, and as a result, errors in the treatment stage. Such factors include: complex structure of pulmonary pathologies, absence of correct information about the borders of pathology in the process of their visualization (separately from other organs), shortcomings of existing algorithms of determining the borders, connected with modern means of forming, processing and analysis of images. The aim of this work was to create a method allowing to automatically set more precise limits of pulmonary pathologies and to minimize the errors that occur during semi-automatic segmentation based on algorithms of lung image processing and analysis. In order to achieve this goal, the following steps were taken - a literary and analytical review was carried out and a package of structural and mathematical models was developed. The results of this study can be used in cancer diagnosis of the lungs, for automatic determination of the boundaries of the pathology to enhance their diagnostic value.
Título traducido de la contribuciónDEVELOPMENT OF MODEL FOR AUTOMATIC DETERMINATION OF THE PATHOLOGY BOUNDARIES IN LUNG CANCER DIAGNOSTICS
Idioma originalRussian
Páginas (desde-hasta)84-89
Número de páginas6
PublicaciónНаука и бизнес: пути развития
N.º5 (107)
EstadoPublished - 2020

GRNTI

  • 76.29.00

Level of Research Output

  • VAK List

Huella

Profundice en los temas de investigación de 'РАЗРАБОТКА МОДЕЛИ АВТОМАТИЧЕСКОГО ОПРЕДЕЛЕНИЯ ГРАНИЦ ПАТОЛОГИИ ПРИ ОНКОЛОГИЧЕСКОЙ ДИАГНОСТИКЕ ЛЕГКИХ'. En conjunto forman una huella única.

Citar esto