Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Occluded embryo pronucleus and cleavage ball detection method based on attention mechanism

A technology of blastomeres and attention, which is applied in computer components, image data processing, image enhancement, etc., and can solve problems such as false detection and missed detection

Active Publication Date: 2020-10-23
四川通信科研规划设计有限责任公司 +2
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve (1) the problem of false detection caused by impurities such as pronucleus or blastomere and similar air bubbles in the embryo body or culture medium; The problem of missing detection due to mutual occlusion,

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
  • Occluded embryo pronucleus and cleavage ball detection method based on attention mechanism
  • Occluded embryo pronucleus and cleavage ball detection method based on attention mechanism
  • Occluded embryo pronucleus and cleavage ball detection method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The invention provides a method for detecting embryonic pronuclei and blastomeres based on an attention mechanism, comprising the following steps:

[0068] Step S1: preprocessing the embryo image, and segmenting the embryo body from the image;

[0069] The specific steps of embryo body segmentation are as follows:

[0070] S1: Annotate the image, use the image annotation software labelme to segment the embryo from the background, the software automatically generates a JSON format file, and then convert the JSON file into a PNG format label image.

[0071] The effect diagram of the image annotation process is as follows figure 1 As shown, from top to bottom are the original embryo image, the image with annotations, and the label image (the background is black, and the label is the central circular part):

[0072] S2: Build a network model. The segmentation network based on network symmetry and residual structure contains two basic units (identity_block and conv_block)....

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 the technical field of information, provides an occluded embryo pronucleus and cleavage ball detection method based on an attention mechanism and aims to solve the problem ofmissing detection caused by mutual occlusion between an embryo pronucleus or a cleavage ball. According to the main technical schemes, the method involves a main body segmentation network used for cutting an embryo main body part from an original image, a CNN feature extraction layer combining a residual structure, a RPN network for preliminarily generating and correcting target candidate boxes, acoordinate refinement unit for refining the coordinates of the target candidate boxes predicted by the RPN network, an improved Soft-NMS algorithm for screening out redundant target candidate boxes,a shielding score network used for enhancing the characteristics of a core channel and the characteristic expressions of a target occluded part, a classification network for identifying the specific categories of targets in a fine candidate box, and a number prediction network for identifying the number of the targets.

Description

technical field [0001] The invention relates to the field of automatic detection of embryonic pronuclei and cleavage stages, in particular to an attention mechanism-based detection method for blocking embryonic pronuclei and blastomeres. [0002] technical background [0003] With the rapid development of modern medical level and the continuous deepening of the research on the mechanism of embryo development, in vitro fertilization-embryo transfer technology is becoming more and more mature, and at the same time, the demand for embryo transfer is also greatly increasing. In order to improve the utilization rate of embryos and provide more and higher opportunities for infertility patients, the detection of pronuclei is extremely important. The pronuclear and cleavage stages basically determine whether an embryo can be used for transfer. Doctors need to take the embryos out of the culture environment for observation every day and record the observation results. On average, hun...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/62G06N3/04G06T5/00G06T7/00
CPCG06T7/0012G06T2207/30044G06V20/695G06V10/25G06N3/045G06F18/214G06T5/94
Inventor 蒲逊杨波汪燕邓唐樊伟牛新征肖凌云梅克进叶志佳
Owner 四川通信科研规划设计有限责任公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com