A method to distinguish leukocytes from marrow cell images based on fuzzy clustering

Abstract

A fuzzy clustering recognition method is proposed to identify cells from sliced marrow cell image. In our image processing, leukocytes can be distinguished against other cells like red cell, megakaryocyte, and cytoplasm. The leukocytes can be further distinguished into promyelocyte, myelocyte or metamyelocyte. Probably the ratio of the counts of these three kinds of leukocytes can be used as the indication of leukemia relapse. Previous work on this project involves the recognition using pixel distribution and probability lays the background of data processing and preprocessing. Constraints based on size, pixel distribution, and grayscale pattern are used for the successful counting and positioning of individual cells. This shape, pattern and color based method can reach satisfied counting and we hope it can be used to get the relative positions for the research of pro-ALIP structure.