Chromosome division phase image quality evaluation method based on deep learning

A technology of image quality evaluation and deep learning, which is applied in neural learning methods, image enhancement, image analysis, etc., can solve the problems affecting the accuracy of chromosomal division phase image evaluation, being easily affected by the external environment, and long time periods, etc. Screening time, improving evaluation and selection efficiency, and improving efficiency

Pending Publication Date: 2020-06-23
HANGZHOU DIAGENS BIOTECH CO LTD
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing conventional practice is to give all 200 pictures to medical workers, observe the mitosis images one by one with the naked eye, and roughly evaluate a mitosis image by identifying some basic characteristics of chromosomes, such as length, variance, and dispersion Quality, but this method has a large error and

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
  • Chromosome division phase image quality evaluation method based on deep learning
  • Chromosome division phase image quality evaluation method based on deep learning
  • Chromosome division phase image quality evaluation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0088] The second step specifically includes the following steps:

[0089] a) Enlarge / shrink the chromosome image along the longest axis to bs pixels; scale up the other axis proportionally;

[0090] b) For the axis of the enlarged image less than bs pixels, fill with white pixels until the axis length is bs;

[0091] Before training the deep learning neural network, the image is rotated and flipped for data enhancement operations;

[0092] Realize the standardized processing of the input image, and then the subsequent network training is easier to converge.

[0093] Since the quality of the chromosome image is related to the dyeing quality of the sample and is seriously affected by the light, there are many impurities in the image, the contrast is poor, and the light and dark stripes in the chromosome make the gray level distribution inside the target uneven. Therefore, the chromosome image must be preprocessed to prepare for the later analysis and processing.

[0094] The...

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 discloses a chromosome division phase image quality evaluation method based on deep learning, and belongs to the technical field of chromosome image processing. Through the deep learningmodel, the quality of the chromosome split-phase images can be scored, the image quality of the chromosome images can be accurately evaluated, the robustness for evaluating different types of chromosome split-phase images is high, and the operation efficiency of doctors is improved. According to the invention, the chromosome division phase image quality can be evaluated accurately and efficiently; the method can effectively improve the evaluation and selection efficiency of the chromosome division phase images, shortens the screening time of the chromosome division phase images, can effectively reduce the workload of doctors, is not interfered by the outside, is simple and reasonable in process, can be popularized and applied to the outside in a large scale, and is simple in deployment.

Description

technical field [0001] The invention relates to a method for evaluating the image quality of chromosome division phases based on deep learning, and belongs to the technical field of chromosome image processing. Background technique [0002] The first step in chromosome analysis and diagnosis is to select 30 of the best bands from about 200 images of chromosome division phases. It is generally believed that the longer the bands, the better, the clearer the better, and the more discrete the better. Phase to carry out the next counting analysis and other operations. [0003] The existing conventional practice is to give all 200 pictures to medical workers, observe the mitosis images one by one with the naked eye, and roughly evaluate a mitosis image by identifying some basic characteristics of chromosomes, such as length, variance, and dispersion Quality, but this method has a large error and a high probability of misjudgment. At the same time, the entire evaluation process t...

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): G06T7/00G06K9/62G06N3/04G06N3/08
CPCG06T7/0002G06N3/08G06T2207/10056G06T2207/20081G06T2207/20084G06T2207/30168G06N3/045G06F18/2415
Inventor 宋宁马伟旗韩云鹏陈罗克晏青沈晓明吴朝玉
Owner HANGZHOU DIAGENS BIOTECH 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