Unlock instant, AI-driven research and patent intelligence for your innovation.

Leukocyte segmentation method based on visual attention mechanism and model fitting

A visual attention mechanism and model fitting technology, applied in the field of white blood cell segmentation, can solve the problems of low segmentation accuracy, accurate removal of cumbersome white blood cells, etc., and achieve the effect of reducing human error

Pending Publication Date: 2021-08-27
FUZHOU UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a leukocyte segmentation method based on visual attention mechanism and model fitting in view of the existing technical deficiencies. As well as the low accuracy of leukocyte segmentation and the separation of cohesive leukocytes in the prior art, the accuracy of blood leukocyte segmentation has been improved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Leukocyte segmentation method based on visual attention mechanism and model fitting
  • Leukocyte segmentation method based on visual attention mechanism and model fitting
  • Leukocyte segmentation method based on visual attention mechanism and model fitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0041] A kind of white blood cell segmentation method based on visual attention mechanism and model fitting of the present invention comprises the following steps:

[0042] S1. Cell nucleus segmentation based on color space volume;

[0043] S2. Background removal and cytoplasmic segmentation based on boundary prior knowledge;

[0044] S3. Separation of adherent leukocytes based on breakpoint detection and model fitting.

[0045] The following is the specific implementation process of the present invention.

[0046] The present invention studies a white blood cell segmentation algorithm based on visual attention mechanism and model fitting. Firstly, a color space volume based on visual attention mechanism is proposed to highlight the nucleus regions, and then an adaptive thresholding method is used to segment the nuclei. Then, the algo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a leukocyte segmentation method based on a visual attention mechanism and model fitting. According to the method, firstly, a color space volume based on a visual attention mechanism is provided to highlight a cell nucleus region, and then the cell nucleus is segmented by using an adaptive threshold method. And then, a method based on boundary priori knowledge is provided, a background region is removed, the obtained central region is taken as an initial white blood cell region, a white blood cell contour is further obtained through edge detection, and a cell nucleus is subtracted from the obtained white blood cell contour to obtain a cytoplasm segmentation result. Finally, a method based on a model fitting strategy is provided to solve the problem of leukocyte adhesion, leukocytes (including cell nucleuses and cytoplasm) are effectively segmented from a peripheral blood smear image, the leukocytes obtained through segmentation are counted and classified, and the influence of personal errors is effectively reduced.

Description

technical field [0001] The invention relates to a white blood cell segmentation method based on visual attention mechanism and model fitting. Background technique [0002] White blood cells are the most important immune cells in the human body and are very important for maintaining the immune function of the human body. White blood cells include five types of cells, neutrophils, eosinophils, basophils, lymphocytes, and monocytes. The total number of white blood cells in human peripheral blood, the proportion and shape of various types of white blood cells are important indicators for the diagnosis of leukemia and other human blood diseases. Differential white blood cell count is an important part of hospital blood routine examination, that is, to calculate the total number of peripheral blood white blood cells and the percentage of various types of white blood cells. This count can be used to diagnose blood diseases such as leukemia, infectious diseases, inflammation, and ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/11G06T7/13G06T7/194G06T7/62G06T7/90
CPCG06T7/11G06T7/13G06T7/62G06T7/90G06T7/194G06T2207/10056G06T2207/30004G06T2207/30242
Inventor 童同郑浩男周小根李静邓扬霖黄毓秀
Owner FUZHOU UNIV