AN ITERATIVE BASED NOVEL MULTI-NUCLEUS DETECTION SCHEME FOR PROTOZOAN PARASITE MICROSCOPIC IMAGES

Abstract

Protozoan parasites cause many diseases, such as malaria, EHEC infection, shigellosis, amoebiasis, etc. Different kinds and growing stages of protozoan parasites would lead to different treatments. The most significant characteristic of different growing stages is the number of nuclei. But some nuclei in a cell could be unclear causing the missing in nucleus detection. Common and traditional segmentation methods can not be used to obtain satisfied results directly. This paper presents a novel multi-nucleus detection scheme which is composed from adaptive protozoan parasite boundary erasure, iterative gamma equalization, two-means clustering algorithm, modified connected component detection method, and circle mask scoring method. Except the two-means clustering algorithm, all other parts are modified methods or new methods designed for nucleus extraction, Experiments show that the proposed scheme can detect the nuclei with indistinct boundaries effectively and can obtain better results than other commonly used image segmentation methods.