Classification of Cell-types in Myocardial Tissue by Quantification of Physiological Characteristics

8 pages•Published: January 24, 2024

Abstract

Heart disease is the second leading cause of death in Japan, contributing to 15% of all fatalities. Consequently, there exists a pressing need to unveil the pathogenesis of this disease and develop innovative treatment methods. Traditional analysis methods, however, require a significant amount of man-hours and execution time, while being limited in the amount of information they can obtain due to their reliance on two- dimensional images. In this study, we propose a classification method for three- dimensional quantitative analysis of myocardial tissue that considers the cell-specific features existing in the tissue. Using the proposed method, we extracted the nuclei, cells, and vascular endothelial cell membrane regions, and derived two quantitative indices: coverage and filling rate. The experimental results showed that the coverage rate, which quantifies the features of the nucleus of vascular endothelial cells covered by the vascular endothelial cell membrane, is effective in identifying vascular endothelial cells. In addition, the filling rate, which quantifies the characteristic of cardiomyocytes having a small percentage of nuclei in the total cell volume, has been shown to be effective in the identification of cardiomyocytes.

Keyphrases: Cell-types classification, Heart Disease, medical image processing

In: Krishna Kambhampaty, Gongzhu Hu and Indranil Roy (editors). Proceedings of 36th International Conference on Computer Applications in Industry and Engineering, vol 97, pages 1--8

Links:	https://easychair.org/publications/paper/2GDZ
	https://doi.org/10.29007/c6jx