Artery and vein determination method and device, equipment and storage medium

A determination method, arteriovenous technology, applied in the field of image processing, can solve the problems of low accuracy, difficulty in obtaining pulmonary artery and pulmonary vein, poor operation efficiency, etc., and achieve accurate and complete separation effect

Active Publication Date: 2020-09-22
SHANGHAI UNITED IMAGING HEALTHCARE
View PDF10 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this solution is that the operation efficiency is poor, the classification accuracy of the deep learning network model is low, and the network prediction results are basically optimized by graph cuts, and it is difficult to obtain complete pulmonary arteries and pulmonary veins.

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
  • Artery and vein determination method and device, equipment and storage medium
  • Artery and vein determination method and device, equipment and storage medium
  • Artery and vein determination method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a flow chart of an arteriovenous determination method provided by Embodiment 1 of the present invention. This embodiment is applicable to situations where it is necessary to determine the arteriovenous vein of a target vessel in a medical image. This method can be performed by an arteriovenous determination device, which It can be realized by means of software and / or hardware, and the device can be configured in computer equipment. Such as figure 1 As shown, the method in this embodiment may specifically include:

[0031] S110. Acquire initial medical image data including target blood vessels.

[0032] Wherein, the target blood vessel can be a blood vessel at any position on the target object (the target object can be a human body or an animal, etc.), including arterial blood vessels and venous blood vessels. For example, the target blood vessel can be at least one of the pulmonary blood vessels, liver blood vessels, and spleen blood vessels. One, the ...

Embodiment 2

[0051] figure 2 It is a flowchart of an arteriovenous determination method provided in Embodiment 2 of the present invention. In this embodiment, on the basis of the above-mentioned embodiments, the neural network model based on the pre-trained trunk extraction can be selected to determine the arterial trunk information and venous trunk information in the initial medical image data, and further includes:

[0052] Performing three-dimensional resampling on the initial medical image data based on a second preset physical size corresponding to the second target voxel, to obtain second resampled medical image data having the second target voxel;

[0053] Inputting the second resampled medical image data into the pre-extraction neural network model to obtain an overview image of the target vessel;

[0054] Determining a target vessel region of interest of the target vessel based on the target vessel overview image;

[0055] According to the target blood vessel region of interest...

Embodiment 3

[0096] Figure 3a It is a flowchart of an arteriovenous determination method provided in Embodiment 3 of the present invention. This embodiment provides a preferred embodiment on the basis of the above-mentioned embodiments. In this preferred embodiment, the target blood vessel is a pulmonary blood vessel, such as Figure 3a As shown, the arteriovenous determination method may include the following steps:

[0097] Acquisition of three-dimensional data of the initial lung image;

[0098] Pulmonary artery and vein trunk segmentation: resampling the initial three-dimensional data of the lung image into the first resampled three-dimensional data of the lung image with a larger physical size, and then using the coarse segmentation neural network model (i.e. the pre-extraction neural network in the embodiment of the present invention) model) to segment the pulmonary vessels to obtain an overview image of the pulmonary vessels. Determine the largest connected region in the pulmona...

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 embodiment of the invention discloses an artery and vein determination method and device, equipment and a storage medium. The artery and vein determination method comprises the steps that initialmedical image data containing a target blood vessel is obtained; based on a pre-trained trunk extraction neural network model, artery trunk information and vein trunk information in the initial medical image data are determined, wherein the artery trunk and the vein trunk are the artery blood vessel and the vein blood vessel of a preset branch in the target blood vessel respectively; artery fine branch information and vein fine branch information in the initial medical image data are determined based on preset constraint conditions; and artery blood vessel information and vein blood vessel information of the target blood vessel are obtained according to the artery trunk information and the vein trunk information. According to the technical scheme of the embodiment of the invention, the artery blood vessel and the vein blood vessel can be quickly, accurately and completely separated.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a method, device, device, and storage medium for determining arteries and veins. Background technique [0002] Lung disease is a disease with a high incidence in my country, and the prevention and treatment of lung diseases depend on accurate diagnosis and quantitative analysis. The rapid development of medical imaging technology in recent years has made quantitative analysis of the lung possible, and computed tomography (CT) technology allows the delineation of lung anatomy, such as pulmonary vasculature and bronchi, at the submillimeter level with low radiation doses. Analysis of pulmonary vessels under high-resolution CT images is helpful for early detection of pulmonary nodules, pulmonary embolism, chronic obstructive pulmonary disease (COPD), chronic thromboembolic pulmonary hypertension (CTEPH) or pulmonary arterial / venous hypertension (P...

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): G06T7/00G06T7/11G06N3/08G06N3/04
CPCG06T7/0012G06T7/11G06N3/08G06T2207/10081G06T2207/10088G06T2207/20081G06T2207/20084G06T2207/30101G06N3/045G06T2207/20021G06V2201/03G06V10/82G06V10/25G06T7/70G06V10/764G06T2207/10072
Inventor 郭宇翔袁绍锋
Owner SHANGHAI UNITED IMAGING HEALTHCARE
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