Morphology based method for separating cells

A technology based on morphology and separation method, which is applied in the field of cell single cell image segmentation, can solve the problems of ineffective separation of adherent cells and affect the calculation of cell morphological parameters, etc., and achieve the effect of effective separation

Inactive Publication Date: 2010-04-07
ZHEJIANG UNIV OF TECH
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of the existing cell separation methods that cannot effectively separate the adhered cells and a

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
  • Morphology based method for separating cells
  • Morphology based method for separating cells
  • Morphology based method for separating cells

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0050] The present invention will be further described below in conjunction with the accompanying drawings.

[0051] refer to Figure 1 to Figure 11 , a cell separation method based on morphology, the cell separation method comprises the following steps:

[0052] 1), area mark:

[0053] For the binary image of the cell image segmentation result, the morphological markers are as follows:

[0054] e) Custom structural elements, including shape and size;

[0055] f) use the structural element to corrode the binary image to obtain the internal representative area;

[0056] g) Morphological finishing operation and filling method to eliminate small noise areas, and construct a new binary image containing internal representative areas;

[0057] h) Obtain the marker values ​​of each region with the watershed algorithm on the new binary map;

[0058] Obtain the mark value of each adhesion area through the above marks;

[0059] 2), extract single cells:

[0060] 2.1), the process...

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 provides a morphology based method for separating cells. The method comprises the following steps: 1) regions are marked, wherein a binary image of a cell image segmentation result is marked based on the morphology to obtain marked value of each adhering region; 2) a monomer cell is extracted, 2.1) a region is extracted; and 2.2) firstly, a marked graph existing adhering regions is found out, a round structure with the size of structure element of 1 is selected and expanded, and expansion is stopped when the boundary of the marked graph exceeds the boundary of an adhering graph, and the size of the marked graph is a whole of the monomer cell in adhering cells; and 3) a reconstructed new binary image set is traversed, attribution of each monomer is determined, and an image set is established according to an coordinate and area information. The method can effectively separate adhering cells, and prepares for accurate calculation on morphological parameters of the cells.

Description

technical field [0001] The present invention relates to a cell separation method, in particular to a method for segmenting a single cell according to a cell image. Background technique [0002] In the medical field, it is usually necessary to segment cells from cell images. Due to the inhomogeneity of gray levels of cell images and the overlapping of spatial positions, the segmentation results include overlapping images of many cells and some over-segmented regions in the nucleus. If the shape is directly calculated without processing, it will be a challenge to the partial attribution of over-segmentation and the accuracy of shape parameter calculation. [0003] The defects of traditional cell separation methods: 1. It cannot effectively separate adhered cells, and it is impossible to extract single cells from the adhered cells; 2. It affects the accuracy of cell morphological parameter calculation. SUMMARY OF THE INVENTION [0004] In order to overcome the shortcomings o...

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): G06T7/00
Inventor 陈胜勇陈敏姚春燕赵明珠柳刚锋
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap