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

Double centromere distorted chromosome analysis and prediction method based on multi-scale fusion method

A multi-scale fusion and prediction method technology, applied in image analysis, neural learning methods, image enhancement, etc., can solve problems such as poor robustness and poor detection accuracy, achieve fast analysis speed, small error, and improve analysis efficiency.

Pending Publication Date: 2021-02-19
SHANGHAI BEION MEDICAL TECH CO LTD
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the shortcomings of poor detection accuracy and poor robustness of the detection method in the prior art, the present invention provides a method for analyzing and predicting dicentric aberration chromosomes based on a multi-scale fusion method, which can accurately and quickly analyze the input chromosome image to be analyzed Carry out automatic analysis and prediction, mark the dicentric aberration chromosomes in the chromosome image to be analyzed, and count the number of dicentric aberration chromosomes in the chromosome image to be analyzed, and assist doctors to complete biological dose estimation

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
  • Double centromere distorted chromosome analysis and prediction method based on multi-scale fusion method
  • Double centromere distorted chromosome analysis and prediction method based on multi-scale fusion method
  • Double centromere distorted chromosome analysis and prediction method based on multi-scale fusion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] like Figure 1-2 As shown, the network structure of the designed neural network model is mainly composed of three parts: the backbone neural network CSPN, the FPN+PAN feature fusion network and the output prediction end. The backbone neural network CSPN is mainly composed of several CSPs, and the specific backbone neural network CSPN is composed of five cross-stage partial neural network modules (Cross Stage Partial, CSP). CSP module structure such as image 3 As shown, the CSP module is composed of several CBM modules and n-cycle residual units. The CBM module mainly performs convolution operations on the input feature map and then uses the Mish activation function to process the features.

[0045] The invention provides a method for analyzing and predicting dicentric aberration chromosomes based on a multi-scale fusion method. Before performing regression prediction on the dicentric aberration chromosomes, a neural network model is trained. The training steps are as ...

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 a chromosome analysis technology, and discloses a double centromere distorted chromosome analysis and prediction method based on a multi-scale fusion method, and the method comprises the steps: enabling a trained neural network model to extract the deep features of an inputted to-be-analyzed chromosome image through CSPN; carrying out Drop Block operation and spatial pyramid pooling operation to extract key features; respectively outputting three feature tensors on three scales by adopting a feature fusion strategy combining a feature pyramid network and a path aggregation network; after Drop Block operation is carried out, outputting three prediction tensors; adopting a DIOU NMS algorithm to screen the predicted bounding box; and analyzing the double centromere distorted chromosome. The trained neural network model can quickly mark the distorted chromosomes on the distorted chromosome image and count the number of the distorted chromosomes, the detection accuracy is higher, the robustness is higher, and a doctor is assisted in completing biological dose estimation.

Description

technical field [0001] The invention relates to biological dose estimation, in particular to a method for analyzing and predicting dicentric aberration chromosomes based on a multi-scale fusion method. Background technique [0002] Chromosomal aberration analysis has been used for biological dose estimation for more than 50 years, its reliability has been confirmed by a large number of data, and it is considered as one of the most reliable radiation biometric methods in accident dose estimation. [0003] At present, the occupational health examination of radiation workers mainly analyzes and counts dicentric chromosomes (dicentricchromosome), centromeric rings and acentric chromosomes. In the estimation of biological dose of radiation accident, only dicentric chromosomes or dicentric chromosomes plus the number of centromeric rings are counted, and acentric chromosomes are used as auxiliary indicators. Estimation is important. [0004] The traditional aberrant chromosome a...

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): G06T7/00G06T7/10G06T7/62G06T7/73G06K9/62G06N3/04G06N3/08
CPCG06T7/0012G06T7/10G06T7/62G06T7/73G06N3/084G06T2207/30004G06T2207/20016G06N3/045G06F18/23
Inventor 崔玉峰
Owner SHANGHAI BEION MEDICAL TECH CO LTD
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