A denoising method for a chromosome G banding mid-term gray level image

A gray-scale image and chromosome technology, applied in the field of image processing, can solve the problems affecting the adaptive threshold and the unevenness of the image background

Inactive Publication Date: 2018-11-20
湖南省自兴人工智能研究院 +1
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the experiment, it was found that part of the chromosome image after filming was unevenly illuminated, which made the image background light and dark, which would inevitably affect the calculation of the adaptive threshold

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 denoising method for a chromosome G banding mid-term gray level image
  • A denoising method for a chromosome G banding mid-term gray level image
  • A denoising method for a chromosome G banding mid-term gray level image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0130] Example 1: A mid-stage grayscale image of chromosome G banding with a relatively uniform background

[0131] (1) Read in a pair of original chromosome G-banded mid-phase grayscale image m_imgSrc, as attached figure 1 ;

[0132] (2) Perform 3×3 median filtering on m_imgSrc to obtain m_imgGray, as attached figure 2 ;

[0133] (3) Extract the background mask area of ​​m_imgGray, as attached image 3 , the white area marks the background;

[0134] (4) Calculate the grayscale distribution standard deviation std_bk=3.477 of the background mask area of ​​m_imgGray, and set the threshold T2=10. Since std_bk

[0135] (5) Carry out the Otsu method binarization segmentation on the grayscale image m_imgGray to obtain m_imgBW, the result is as attached Figure 4 ;

[0136] (6) Carry out expansion operation on step (5) m_imgBW to obtain m_imgFore of chromosome foreground area, as attached Figure 5 , and its cor...

Embodiment 2

[0142] Example 2: Aiming at the mid-phase grayscale image of chromosome G banding with uneven background

[0143] (1) Read in a pair of original chromosome G-banded mid-phase grayscale image m_imgSrc, as attached Figure 13 ;

[0144] (2) Perform 3×3 median filtering on m_imgSrc to get m_imgGray, as attached Figure 14 ;

[0145] (3) Extract the m_imgGray background mask area and calculate its gray distribution standard deviation std_bk=30.96, set the threshold T2=10, since std_bk>T2, m_imgGray needs to be corrected;

[0146] (4) Extract the background image m_imgBKgray of m_imgGray as attached Figure 15 ;

[0147] (5) Perform background correction on m_imgGray, as attached Figure 16 ;

[0148] (6) Use the Otsu method to segment and expand the foreground area of ​​m_imgGray, as attached Figure 17 , and do gamma correction as attached Figure 18 ;

[0149] (7) For attached Figure 18 The foreground area is segmented by the Otsu method, and part of the grain noise is ...

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 denoising method for a chromosome G banding mid-term gray level image. The method provides a local threshold segmentation scheme, ingenious integration and optimization can beperformed on a classic image processing algorithm, and a method which has adaptability and can automatically process a chromosome image can be formed. For a data set with 5000 chromosome G banding mid-term gray level images, mutual comparison is performed on a processing result of the method and a manual processing result of a medical worker and the automatic processing accuracy of the method canreach 86.38%. Image reading pressure of the medical personnel can be greatly reduced, and the chromosome karyotyping work efficiency is reduced.

Description

Technical field: [0001] The invention relates to a method for removing grayscale image noise in the mid-stage of chromosome G banding, belonging to the field of image processing. Background technique: [0002] When performing karyotype analysis on the gray-scale image of chromosome G banding in the middle stage, a clean image with clear banding is helpful for medical staff to carry out diagnostic analysis. However, in the actual situation, due to the production process in the metaphase of the cell, the chromosome image will inevitably be mixed with noise. Observation of a large number of chromosome images found that the chromosome images are often accompanied by clump noise, cell debris noise, irregular flocculent or granular noise formed by tissue fluid, and even chromosomes from different cells splashed into each other's chromosome clusters. At present, in relevant reproductive and genetic specialized hospitals, the noise removal of chromosome images still relies on docto...

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): G06T5/00G06K9/62
CPCG06T5/002G06F18/23
Inventor 丰生日蔡自兴卢光琇蔡昱峰林戈穆阳谭跃球李仪
Owner 湖南省自兴人工智能研究院
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