Abstract:

Biomedical images are used for diagnosis and treatment of malignant neoplasms. Images of normal and pathological cells and tissues are derived using light microscopes. These images are the objects of study in histology and cytology. One of the most important stages in the automation of measuring optical and geometrical parameters of images is the segmentation of micro objects. Analysis of biomedical images is complicated due to the highly variable parameters and weak contrast in most micro objects. The use of point connections for segmenting the images has several advantages: processing images of any type, splitting micro objects that are in contact, insensitivity to noise. A method of image segmentation based on preliminary markup implies splitting a color image into homogeneous regions, calculating the coefficient of relation between adjacent points, and merging points into homogeneous regions. The algorithm allows for the automated segmentation. A texture segmentation method involves computing values of spatial moments for each point of the image. A feature space, obtained in this way, is segmented by the algorithm. The algorithm calculates thresholds based on mathematical expectation. This makes it possible to identify such complex micro objects as the layers of cells, cross-sections of blood vessels and ducts.The quality of segmentation was estimated using a metric approach. The developed segmentation algorithms made it possible to improve quality of the biomedical image segmentation by 18−21 % on average Author Biographies Yuriy Batko, Ternopil National Economic University Lvivska str., 11, Ternopil, Ukraine, 46020 PhD, Senior Lecturer Department of Computer Engineering

Keywords: