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

Processing method and system for reconstructing blood vessel three-dimensional model based on 2D-DSA images

A 2D-DSA and 3D model technology, applied in the field of reconstructing 3D models of blood vessels, can solve problems not involved in reconstructing 3D images

Pending Publication Date: 2020-10-23
复影(上海)医疗科技有限公司
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the technical solution disclosed in this patent document, an image processing technology is provided, but it does not involve how to reconstruct the content of a 3D image based on a 2D image

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
  • Processing method and system for reconstructing blood vessel three-dimensional model based on 2D-DSA images
  • Processing method and system for reconstructing blood vessel three-dimensional model based on 2D-DSA images
  • Processing method and system for reconstructing blood vessel three-dimensional model based on 2D-DSA images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] In order to verify the effectiveness of the scheme of the present invention, the present invention uses two data sets for experiments. The first data set is the self-constructed 2D DSA image of the present invention and the known intracranial blood vessel 3D model data set (2D DSA and 3D Model ofCarotid Artery Dataset), which includes 50 cases of patient's positive and lateral 2D DSA Image and its 3D vessel model reconstructed by 3D DSA. The second dataset is the 3D intracranial aneurysm dataset Intra (https: / / github.com / intra3d2019 / IntrA) proposed by Xi Yang et al. This dataset includes 103 3D models of blood vessels reconstructed from 2D MRA images.

[0054] Such as figure 1 As shown, the specific operation steps are as follows:

[0055] Step 1: Construct sparse blood vessel point clouds from 2D DSA images of 50 frontal and lateral angles.

[0056] In this step, the combination of multi-scale Gabor filter and Hessian matrix is ​​used to complete the segmentation of...

Embodiment 2

[0091] In this embodiment, a processing method for reconstructing a three-dimensional model of a blood vessel based on a 2D-DSA image is provided, which includes the following steps:

[0092] Step S1: Collect 2D-DSA images based on the two angles of the front view and the side view, and construct a sparse blood vessel point cloud based on the collected 2D-DSA images;

[0093] Step S2: Obtain point cloud slices and standard results based on the preprocessing of the constructed sparse blood vessel point cloud, and input the obtained point cloud slices, standard results, and known intracranial blood vessel datasets into the PU-GCN deep learning network as a training set. Perform training to obtain the trained PU-GCN deep learning network;

[0094] Step S3: Obtain the sparse point cloud to be reconstructed based on the 2D-DSA image to be reconstructed in step S1, input the sparse point cloud to be reconstructed into the trained PU-GCN deep learning network, and the trained PU-GCN ...

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 processing method for reconstructing a blood vessel three-dimensional model based on 2D-DSA images. The method comprises the following steps of: S1, collecting 2D-DSA imagesbased on a normal position angle and a side position angle, and constructing a sparse blood vessel point cloud based on the collected 2D-DSA images; S2, performing preprocessing based on the constructed sparse blood vessel point cloud so as to obtain a point cloud sheet and a standard result, taking the obtained point cloud sheet, the standard result and a known intracranial blood vessel data setas a training set, inputting the training set into a PU-GCN deep learning network for training, and obtaining a trained PU-GCN deep learning network; and S3, obtaining a to-be-reconstructed sparse point cloud of a to-be-reconstructed 2D-DSA image based on the step S1, inputting the to-be-reconstructed sparse point cloud into the trained PU-GCN deep learning network, outputting the to-be-reconstructed sparse point cloud to obtain a to-be-reconstructed dense point cloud, and obtaining a blood vessel three-dimensional model based on the to-be-reconstructed dense point cloud. In addition, the invention further discloses a processing system.

Description

technical field [0001] The present invention relates to a method and system for reconstructing a three-dimensional model of a blood vessel based on an anterior and lateral 2D DSA image, and in particular to a PU-GCN deep learning network for predicting dense point clouds from sparse point clouds. Background technique [0002] Cerebral aneurysm is a kind of occult lesion commonly seen in middle-aged and elderly people in which the lumen of cerebral arteries and vessels is enlarged and abnormal tumor tissue is formed. Preventing and diagnosing cerebral aneurysms as early as possible and accurately is an important task to protect people's health. Digital Subtraction Angiography (DSA) is the clinical standard inspection item for the diagnosis of cerebral aneurysm, and it is also the gold standard for the diagnosis of this lesion. However, conventional two-dimensional angiography (2D-DSA) has a limited display range, and it is difficult to clearly display the complex structure 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): G06T17/00G06T7/136G06T7/00G06T5/20G06K9/46
CPCG06T17/00G06T7/0012G06T5/20G06T7/136G06T2207/10028G06T2207/30101G06T2207/30016G06T2207/30096G06T2207/20081G06T2207/20084G06V10/44G06V10/513
Inventor 耿道颖于泽宽李美佳王俊杰刘杰李郁欣尹波张晓龙张军吴昊鲁刚狄若愚颜荣耀于媛媛费远宇
Owner 复影(上海)医疗科技有限公司
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