A mouse embryo organ recognition and scoring method and system

A technology of mouse embryos and organs, applied in the field of artificial intelligence-assisted basic medical research, can solve the problems of high cost and low consistency of scoring, achieve the effect of reducing workload and improving scientific research efficiency

Active Publication Date: 2022-05-10
TAIYUAN UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are many problems in the manual identification and judgment itself: 1. The actual operator needs to have a considerable medical basis to make a judgment on the scoring of embryonic development, and in the current situation of insufficient basic medical personnel, the cost of artificially implementing this work is too high
2. Manual judgment itself has a strong subjectivity. In actual work, there are often situations where the scoring consistency between different researchers is not high
3. The time cost of manual identification is also a current problem, and new methods need to be considered to improve efficiency

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
  • A mouse embryo organ recognition and scoring method and system
  • A mouse embryo organ recognition and scoring method and system
  • A mouse embryo organ recognition and scoring method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Such as figure 2 As shown, Embodiment 1 of the present invention provides a mouse embryo organ recognition and scoring method, comprising the following steps:

[0044] S1. Collect the original images of mouse embryos at different stages, and manually label the organs in the images with names and development scores. Set each organ label box and organ name on the image when labeling.

[0045] Specifically, for the images of mouse embryos at different stages captured by a stereo microscope, professional basic medical researchers annotate the organ location and developmental score of each embryo image, and the annotated files are saved locally on the computer.

[0046] First, professional basic medical researchers cultivate mice by themselves. After the mice are conceived, the embryos are removed according to the number of days of development, and the in vitro embryos at different stages are photographed using a stereo microscope. The captured images are saved to the loc...

Embodiment 2

[0073] Such as figure 2As shown, Embodiment 2 of the present invention provides a mouse embryo organ recognition and scoring system, including:

[0074] Image collection module: used to collect embryo images;

[0075] Organ recognition module: used to train the Mask-RCNN network through the marked embryo image to obtain an organ recognition model; the organ recognition model is used to recognize the embryo image to be recognized to obtain each organ or tissue in the embryo image , and intercept it from the image and save it by category;

[0076] Image classification module: including a plurality of convolutional neural network models, which are used to train the convolutional neural network models separately through different embryonic organ images to obtain image scoring models for each organ, and the image scoring models are used to classify different embryonic organ images respectively. The organs are classified and identified, and their scoring results are obtained;

...

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 belongs to the field of artificial intelligence, and specifically relates to a mouse embryo organ recognition and scoring method and system. The method includes the following steps: collecting original images of mouse embryos in different periods and manually labeling them; Input the Mask-RCNN network for training to obtain the organ recognition model; intercept the organs in the marked image from the original image, and use it and the corresponding score as the training set data, and train different convolutional neural networks respectively. Obtain an image scoring model that can score the development of each organ separately; input the original image of the mouse embryo to be recognized into the organ recognition model, and output all organs in the image; intercept all organs from the original image, and input them into the image scoring model Model, get the development score of each organ; get the total score. The invention can quickly and accurately identify the organs in the mouse embryo, and judge the current development stage of each organ.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence-assisted basic medical research, and in particular relates to a mouse embryo organ recognition and scoring method and system. Background technique [0002] Embryo toxicity (Embryo toxicity) mainly refers to the damage caused by various chemical substances to the occurrence and development of embryos, resulting in embryonic developmental disorders, resulting in birth defects, and even clinical outcomes such as miscarriage. The rapid development of chemical and industrial production has brought great progress to human society, but it has caused damage and pollution to the natural environment, and the chemical process is accompanied by the production of many new substances, but it also makes many previously unknown Toxic substances produce toxicity, and at the same time, by-products and wastes generated in chemical production activities are discharged into the environment, making the ...

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): G06V10/25G06V10/44G06V10/774G06K9/62G06N3/04G06T7/00G06T7/11
CPCG06T7/11G06T7/0012G06N3/045G06F18/214
Inventor 李明马雪涛奥瑞芳郝芳李心宇欧阳佳子
Owner TAIYUAN 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