Application of digital processing methods for automated cardiac segmentation from computed tomography data

Computed tomography is now widely used in cardiac surgery as a method of non-destructive study of internal structure of objects, including specific tasks, such as mathematical modeling of physiological processes, surgical interventions in augmented reality, 3D printing, and radiomics. One of the key steps in creating a 3D model from computed tomography data is segmentation – the process of selecting objects in the image. Currently, there are several approaches to automating the segmentation process, including image processing methods, texture analysis and machine learning algorithms (in particular, clustering). Image processing methods are the simplest of the presented approaches and are found in various applications for segmentation of tomographic data. This paper reviews the advantages and disadvantages of various image processing methods (threshold, region growing, contour detection, and morphological watersheds) as tools for automated cardiac segmentation from computed tomography data. It was revealed that computed tomography images have characteristic features affecting the segmentation process (presence of noise, partial volume effect, etc.). The choice of the segmentation method is based on the brightness characteristics of the area of interest and also requires knowledge of the subject area, so it should be performed by a specialist with competence in anatomy and digital image processing. As independent methods of automated segmentation, the listed methods are applicable only in relatively simple cases (selection of homogeneous or high-contrast areas), otherwise, a combination of these methods, the use of machine learning algorithms or manual correction of the results is required.