A novel algorithm for segmentation of leukocytes in peripheral blood

TL;DR

This paper introduces a fast, accurate segmentation algorithm for leukocytes in blood images, addressing challenges posed by variable conditions and outperforming existing fuzzy set-based methods.

Contribution

The paper proposes a novel segmentation algorithm combining color space analysis, fuzzy divergence minimization, and iterative repair for leukocyte detection.

Findings

Outperforms existing non-fuzzy segmentation methods

Interval-valued fuzzy sets yield slightly better results than other fuzzy sets

Effective in complex, variable blood sample conditions

Abstract

In the detection of anemia, leukemia and other blood diseases, the number and type of leukocytes are essential evaluation parameters. However, the conventional leukocyte counting method is not only quite time-consuming but also error-prone. Consequently, many automation methods are introduced for the diagnosis of medical images. It remains difficult to accurately extract related features and count the number of cells under the variable conditions such as background, staining method, staining degree, light conditions and so on. Therefore, in order to adapt to various complex situations, we consider RGB color space, HSI color space, and the linear combination of G, H and S components, and propose a fast and accurate algorithm for the segmentation of peripheral blood leukocytes in this paper. First, the nucleus of leukocyte was separated by using the stepwise averaging method. Then based on the interval-valued fuzzy sets, the cytoplasm of leukocyte was segmented by minimizing the fuzzy divergence. Next, post-processing was carried out by using the concave-convex iterative repair algorithm and the decision mechanism of candidate mask sets. Experimental results show that the proposed method outperforms the existing non-fuzzy sets methods. Among the methods based on fuzzy sets, the interval-valued fuzzy sets perform slightly better than interval-valued intuitionistic fuzzy sets and intuitionistic fuzzy sets.