Embryo Automatic Recognition Method Based on Image Processing

An automatic recognition and image processing technology, applied in the field of embryo detection, can solve the problems of false circles and false ellipses in the recognition results, interference of embryo fragments in the petri dish aperture, and loss of blastomere edge details, etc., so as to improve objectivity and ensure comprehensive performance and high recognition accuracy

Active Publication Date: 2021-03-05
CHINA INNOVATION INSTR CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1. There is a problem of loss of details on the edge of the blastomere, which will cause some blastomeres to be unrecognized;
[0006] 2. The collected pictures have interference problems with the petri dish aperture and embryo fragments, resulting in pseudo circles and pseudo ellipses in the recognition results

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
  • Embryo Automatic Recognition Method Based on Image Processing
  • Embryo Automatic Recognition Method Based on Image Processing
  • Embryo Automatic Recognition Method Based on Image Processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 A schematic diagram of the structure of the image processing-based automatic embryo identification method in Example 1 of the present invention is given, as figure 1 As shown, the automatic embryo identification method based on image processing includes:

[0028] (A1) Edge detection based on EDContours algorithm: Using the EDContours algorithm, in different scale spaces, the original image is convolved with a Gaussian kernel, and the edge detection result is obtained by using the edge stacking operation of the EDPF algorithm. The number of operations is 15-30, preferably 21.

[0029] 2) Line segment drawing based on the EDCircles algorithm: Use the EDLines of the EDCircles algorithm to fit the edge segment as a line segment, and then use the Helmholtz principle to remove the pseudo-line segment to obtain a line segment diagram.

[0030] 3) Arc synthesis based on EDCircles algorithm: Combine the line segments that meet the conditions into arcs.

[0031] 4) Ci...

Embodiment 2

[0050] An application example of the automatic identification method based on embryo images according to Embodiment 1 of the present invention.

[0051] In this application example, as figure 2 As shown, the present invention is mainly applied to embryo images presented on the first day (D1), the second day (D2) and the third day (D3) of the embryonic development process.

[0052] The image processing-based automatic embryo identification method of the present embodiment includes the following steps:

[0053] (A1) Read embryo images and perform image preprocessing:

[0054] 1) Input an image I[x,y] to be processed, such as figure 1 As shown in (a), the initialized contour map ContourMap[x,y]=0, δ=1.0.

[0055] 2) Calculate the t value (scale parameter, representing the scale space level), t=δ×δ;

[0056] 3) Convolve the original image with the Gaussian kernel L(I[x,y],t):

[0057]

[0058] 4) Use the EDPF algorithm to perform edge detection on the convolution result, Ed...

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 present invention provides a method for automatic recognition of embryos based on image processing. The method for automatic recognition of embryos based on image processing includes the following steps: (A1) edge detection: preprocessing the image of the embryo to obtain the edge detection result of the image; (A2 ) line segment drawing: the edge end of described edge detection result is fitted as line segment, obtains line segment figure; (A3) arc is synthesized: the line segment in line segment figure is merged into arc; (A4) synthesis of circle and ellipse: described Fitting arcs to circles and ellipses (A5) Removal of pseudo circles and pseudo ellipses: removing pseudo circles and pseudo ellipses from circles and ellipses to obtain embryo recognition results. The invention has the advantages of fast detection, precise positioning, good objectivity of embryo selection and the like.

Description

technical field [0001] The present invention relates to embryo detection, in particular to an embryo automatic identification method based on image processing. Background technique [0002] The automatic analysis of human microscopic embryo images is an important technology in the field of assisted reproduction, including automatic segmentation of the zona pellucida, prokaryotic morphological analysis, fragmentation rate analysis, and automatic embryo identification. In the case of single embryo transfer, selecting high-quality embryos for transfer is the key to ensuring a successful pregnancy. At this stage, embryo quality assessment mainly relies on embryo experts to select high-quality embryos. The whole process is time-consuming and laborious, and the workload is huge. As one of the important means of embryo quality assessment, automatic embryo identification technology can effectively improve the work efficiency of embryo experts and increase the objectivity of embryo s...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T7/00G06T7/13
CPCG06T7/0012G06T7/13G06T2207/10056G06T2207/30044G06V20/695
Inventor 闻路红邹爽爽洪欢欢毕磊陈瑞强
Owner CHINA INNOVATION INSTR CO LTD
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