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

Blood vessel calcification false alarm detection method based on brightness analysis

A technology of brightness analysis and vascular calcification, applied in the field of medical image processing, can solve problems such as calcification false positives, and achieve the effect of avoiding false positives

Active Publication Date: 2019-06-07
数坤(北京)网络科技股份有限公司
View PDF21 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] For the existing calcification detection algorithm, due to the presence of contrast agents or other reasons, many calcification false positives are generated

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
  • Blood vessel calcification false alarm detection method based on brightness analysis
  • Blood vessel calcification false alarm detection method based on brightness analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] reference figure 1 As shown, the present invention discloses a method for detecting false positives of vascular calcification based on brightness analysis, including the following steps:

[0027] S1. Use a calcification detection algorithm to obtain a calcification candidate area for the blood vessel image. The calcification detection algorithm can use conventional fixed threshold, dynamic threshold, contrast or extreme value algorithms, which are not specifically limited in the present invention.

[0028] S2. Perform morphological analysis on the calcification candidate area to detect whether there is a large area of ​​calcification filling the blood vessel and whether there is a small area calcification that occurs at the bifurcation of the blood vessel;

[0029] S3. Adjust the detection threshold of large area calcification based on the brightness analysis for the condition of large area calcification filling blood vessels, and use the large area calcification detection th...

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 blood vessel calcification false alarm detection method based on brightness analysis. The method comprises the following steps: obtaining a calcification candidate area by utilizing a calcification detection algorithm aiming at a blood vessel image; performing morphological analysis on the calcification candidate area, and detecting whether a large-area calcification fills blood vessels or not and whether a small-area calcification occurs at a blood vessel bifurcation or not; for the condition that the large-area calcification fills blood vessels, adjusting a large-area calcification detection threshold value based on brightness analysis, and judging whether the calcification is true or not by using the large-area calcification detection threshold value; and for the condition that the small-area calcification occurs at the blood vessel bifurcation, judging whether the calcification is true or not by raising the detection threshold value of the small-area calcification. The method firstly performs morphological analysis on the calcification candidate area to find out the candidate area where false alarm condition easily occurs, then, adjusts the detection threshold value based on brightness analysis, and discriminates and eliminates false calcification so as to effectively avoid the occurrence of false alarm condition.

Description

Technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for detecting false positives of vascular calcification based on brightness analysis. Background technique [0002] Automated coronary medical image detection has important clinical value and practical significance for doctors. It can feed back intuitive detection results for doctors, which can be used as a reference for doctors to diagnose disease and free doctors from the tedious work of interpreting medical images. This reduces the doctor’s diagnosis time, improves diagnosis efficiency, and alleviates the current difficulties in seeking medical attention. Calcification area recognition is an important part of automated coronary medical image detection. Calcification is usually manifested in medical images in that its brightness value is higher than that of surrounding blood vessels. According to this, most of the existing algorithms set a Fixed threshold ...

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): A61B5/02G06T7/90
Inventor 肖月庭阳光郑超
Owner 数坤(北京)网络科技股份有限公司
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