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

Segmentation method of aortic valve ultrasound image sequence based on gcv model based on inter-frame shape constraints

A technology for aortic valve and ultrasound images, applied in the field of medical ultrasound image segmentation, can solve problems such as incomplete segmentation and severe overflow of aortic valve ultrasound images

Active Publication Date: 2016-08-17
HEBEI UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for segmenting aortic valve ultrasonic image sequences based on inter-frame shape constraints of the GCV model to solve the incompleteness and seriousness of the aortic valve ultrasonic image segmentation for ultrasonic long-axis images in the prior art. overflow problem

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
  • Segmentation method of aortic valve ultrasound image sequence based on gcv model based on inter-frame shape constraints
  • Segmentation method of aortic valve ultrasound image sequence based on gcv model based on inter-frame shape constraints
  • Segmentation method of aortic valve ultrasound image sequence based on gcv model based on inter-frame shape constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with the accompanying drawings and a specific example.

[0036] This example is in Dual-Core CPU E5800@3.20GHz, graphics card is NVIDIA GeForceGT430NVIDIA GeForce GT430, memory is 2.00GB, operating system is Window XP, and the whole segmentation method is written in C++ and Matlab language.

[0037] The procedure of this method is as follows figure 1 The steps shown are performed:

[0038] (1) Acquire a set of continuous ultrasound image sequences of the aortic valve, and extract the fan-shaped area of ​​each frame, such as figure 2 (a), the threshold of the non-sector area is 255; then Wiener filtering is performed on the image acquired in each frame, and the filtered result is as follows figure 2 (b).

[0039] After the Wiener filtering process, the speckle noise in the ultrasound image can be removed, and the edge information can be well preserved.

[0040] (2) Build the GCV model:

[0041]...

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 method for segmenting aortic valve ultrasonic image sequence based on a GCV model constrained by inter-frame shape, which comprises the following steps: acquiring a group of ultrasonic images and performing Wiener filtering; calculating the gradient vector flow field of each image frame by frame and Add it to the CV model as an energy constraint to obtain the GCV model; by defining the initial constraint shape, add it as an energy constraint item to the GCV model, and then minimize the energy functional to obtain the segmentation result of the first frame image; for the adjacent The aortic valve segmentation result of the previous frame image is filtered by the rolling ball method, and the obtained result is added to the GCV model as an energy constraint item, and the segmentation result of the current frame is calculated. The present invention operates on short-axis images of echocardiography, which not only greatly reduces the workload of doctors, but also solves the problem of serious overflow in the segmentation of aortic valve ultrasound images in the prior art. It is very close, and can divide the aortic valve simply and efficiently.

Description

technical field [0001] The invention relates to a medical ultrasonic image segmentation method, in particular to a method for segmenting an aortic valve ultrasonic image sequence based on a GCV model constrained by inter-frame shapes. Background technique [0002] In my country, aortic valve disease is the most common, complex and dangerous cardiovascular disease, which seriously endangers human health. The aortic valve is located at the junction of the end of the left ventricular outflow tract and the aorta. It acts like a "one-way valve" to prevent blood backflow and ensure the normal and good pumping function of the heart. Due to the safe, non-invasive, simple, cheap, and repeatable characteristics of B-ultrasound, echocardiography has been widely used in clinical diagnosis to observe the shape and position of the aortic valve. The accurate segmentation of the aortic valve in the ultrasound image can not only assist doctors in clinical diagnosis, but also the basis of im...

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 Patents(China)
IPC IPC(8): G06T7/00G06T5/00A61B8/00
Inventor 顾力栩董斌郭怡婷王兵
Owner HEBEI UNIVERSITY
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