Automatic neutrophil nucleus lobe counting based on graph representation of region skeleton

Abstract

Abnormal neutrophil nucleus lobation (like left shift and right shift) helps to diagnose for some clinical conditions. Currently, quantification of it depends on the manual microscopic inspection of blood smears by clinicians. The quality of the manual inspection is extremely limited by the efficiency of clinicians and their medical background. This article proposed an automatic lobe counting method based on the graph representation of the nucleus region skeletons. Skeletons of the segmented nucleus regions are computed by augmented Fast Marching Method and transformed into plane graphs. Then the nucleus lobes are split based on the extracted graph properties including width distribution along the skeleton and graph structure decomposition. Experiments show that the proposed method could efficiently approaches the real lobe numbers in blood smears and reliably distinguish the stabs from the segmented neutrophils, thus it should be helpful in automatic neutrophil lobe number quantification and abnormal lobation diagnosis.