Automatic counting method for complex overlapping erythrocytes based on seed prediction in microscopic imaging

Abstract

Blood cell counting is an important medical test to help medical staffs diagnose various symptoms and diseases. An automatic segmentation of complex overlapping erythrocytes based on seed prediction in microscopic imaging is proposed. The four main innovations of this research are as follows: (1) Regions of erythrocytes extracted rapidly and accurately based on the G component. (2) K-means algorithm is applied on edge detection of overlapping erythrocytes. (3) Traces of erythrocytes’ biconcave shape are utilized to predict erythrocyte’s position in overlapping clusters. (4) A new automatic counting method which aims at complex overlapping erythrocytes is presented. The experimental results show that the proposed method is efficient and accurate with very little running time. The average accuracy of the proposed method reaches 97.0%.