White cell segmentation method based on multi-feature nonlinear combination

Abstract

The invention discloses a white cell segmentation method based on multi-feature nonlinear combination. The method includes extracting the gray scale of white cells, color and texture gradient information of CIE Lab space and spectrum information of the white cells; combining in a nonlinear manner; processing the combined information in manners of orientated watershed transform and ultra metric boundary mapping OWT-UCM, and acquiring algorithm segmented results; performing corresponded parameter adjustment of the algorithm segmented results and expert segmented results; determining parameters until acquiring a predetermined segmentation result, and finally using the parameters for segmenting other white cells. The method has the advantages that the single feature noise influence is reduced, multiple pieces of feature information are combined in the nonlinear manner, the smaller training errors can be acquired as compared with that of the linear combination method, and the better segmentation result can be acquired; meanwhile, the combination information can be adjusted in an iterative manner, parameters of the network can be adjusted, a target can be closer gradually according to the predetermined result, and the target unavailability and inappropriate adjustment are avoided.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and relates to a white blood cell segmentation method based on multi-feature nonlinear combination. Background technique [0002] Leukocyte segmentation is a technique to separate the nucleus and cytoplasm of white blood cells from blood smears for subsequent feature extraction and identification of white blood cells. Because it is the basis for subsequent cell identification, at the same time, the complex characteristics of blood cells and the uncertainty of micrographs, and cells often overlap, cell staining is uneven, and the contrast between cell boundaries and background is not obvious, so cell segmentation is an image A big challenge to deal with. [0003] In recent years, the academic community has proposed a variety of segmentation schemes, which can be roughly divided into three categories: threshold-based, edge detection-based, and region-based segmentation methods. S...

AI Technical Summary

Problems solved by technology

[0005] In summary, the use of single feature segmentation for white blood cells has its limitations; due to the different goals of white blood cell segmentation and natural image segmentation, the method based on linear combination of multiple features cannot be effectively used for white blood cell segmentation

Images