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

Overlapped chromosome segmentation network based on multi-scale feature extraction

A chromosome and multi-scale technology, applied in biological neural network models, image analysis, image data processing, etc., can solve problems such as insufficient semantic features, difficulty in analyzing overlapping chromosome images, and different sizes, and achieve stable data generalization capabilities , Improve the overall segmentation effect, the effect of high-precision segmentation

Pending Publication Date: 2020-09-01
CHINA UNIV OF MINING & TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The size of the target area of ​​chromosome image segmentation is different, and the semantic features are not rich enough, which brings difficulties to the analysis of overlapping chromosome images

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
  • Overlapped chromosome segmentation network based on multi-scale feature extraction
  • Overlapped chromosome segmentation network based on multi-scale feature extraction
  • Overlapped chromosome segmentation network based on multi-scale feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Specific implementation plan

[0037] The following describes the present invention in further detail with reference to the drawings and specific embodiments:

[0038] Step 1. Perform data amplification on overlapping chromosome images;

[0039] 1a) Amplify the size of overlapping chromosome images to a size of 128×128;

[0040] 1b) Generate pixel-level category label images of corresponding sizes, such as Figure 5 Shown. Among them, (a) is the chromosome α with β Overlapping composite images, (b)-(e) are their corresponding category label images, and the light-colored areas in (b) and (c) correspond to chromosomes respectively α with β The non-overlapping area of, (d) corresponds to the overlapping area, (e) corresponds to the background area;

[0041] Step 2, build SSPM module, such as figure 2 Shown

[0042] 2a) Unify the step size of each pooling layer, all set to 2;

[0043] 2b) Considering that the size of the feature map at the bottom of the network is 4×4, the pooling s...

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 multi-scale U-shaped convolutional neural network MACS Net in order to solve the problems that target segmentation regions in overlapped chromosome images are different in size, not obvious in distinguishing and the like. Multi-layer cavity convolution and synchronous long pooling technology is introduced at the bottommost layer of UNet to realize detection of target segmentation regions of different sizes and extraction of features; convolution block connection is introduced between UNet codecs, so that semantic information difference is relieved. An intersection-to-parallel ratio (IoU) of chromosome overlapping regions is used as an evaluation index; the result shows that the segmentation IOU of the MACS Net at the chromosome overlapping part reaches 0.9860, which is improved by 2.78% compared with 0.99593 of UNet, and the MACS Net respectively shows more ideal noise robustness in the data set polluted by spiced salt, Gauss and Poisson noise.

Description

Technical field [0001] The invention belongs to the field of medical image segmentation, and particularly relates to a multi-scale feature extraction and image segmentation method, which can be used for segmentation of overlapping chromosomes in medical images and subsequent karyotype analysis. Background technique [0002] There are 23 pairs of chromosomes in human healthy cell nuclei, including 22 pairs of autosomes and 1 pair of sex chromosomes. As a carrier of genes, chromosomal abnormalities account for more than 50% of spontaneous abortions, stillbirths, and premature deaths, and are also important causes of many congenital diseases. The incidence of newborns is about 1%. Chromosomal abnormalities include quantitative variation and morphological structural aberrations, which can occur on each chromosome. Therefore, how to identify abnormalities in the number and morphological structure of chromosomes has become a key way to diagnose genetic diseases, especially early diagn...

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): G06T7/00G06T7/11G06N3/04G06N3/08
CPCG06T7/0012G06T7/11G06N3/08G06T2207/20084G06T2207/20081G06T2207/30024G06N3/045
Inventor 张林王广杰易先鹏李港深路霖朱静逸刘辉
Owner CHINA UNIV OF MINING & TECH
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