Deep learning-based CBCT image cross-modal prediction CTA image stroke risk screening method and system

A deep learning and CT image technology, applied in the field of medical image processing, can solve problems such as irritation, leakage of intravenous contrast agent, skin damage, etc., to avoid repeated CT examinations and reduce radiation exposure dose.

Pending Publication Date: 2020-12-18
复影(上海)医疗科技有限公司
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, administration of contrast media requires the insertion of a needle
This causes additional discomfort and has been associated with complications, including inadvertent needle punctures in arteries, and leakage of IV contrast material leading to irritation and even damage to the skin
In addition, contrast agents are nephrotoxic, with acute kidney injury (contrast-induced nephropathy) occurring in up to 12% of patients after use

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
  • Deep learning-based CBCT image cross-modal prediction CTA image stroke risk screening method and system
  • Deep learning-based CBCT image cross-modal prediction CTA image stroke risk screening method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0048] Such as figure 1 According to the stroke risk screening method for cross-modal prediction of CTA images based on deep learning CBCT images provided by the present invention, comprising the following steps:

[0049] Step 1: Build a cyclic adversarial generative network model;

[0050] Such as figure 2 As shown, it is a schematic structural diagram of the cyclic adversarial generation network model in the present invention, the cyclic adversarial generation network model includes: encoder, generator and discriminator, encoder, generator and discriminator mainly include: three-dimensional convolutional layer, ReLU layer (corrected linear unit layer), pooling layer, Batch Normalization layer (batch normalization layer) and Full Connect layer (full connection layer), the optimal step size of the convolutional layer: 3*3*3, the pooling layer uses Max pooling.

[0051] Step 101: use an encoder to encode high-order features;

[0052] The encoder is based on convolutional n...

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 provides a deep learning-based CBCT image cross-modal prediction CTA image stroke risk screening method and system. The method comprises the steps of 1, constructing a cyclic adversarialresistance generation network model; 2, training a cyclic adversarial resistance generation network model through the CBCT images and the contrast image data corresponding to the CBCT images; 3, inputting a test image into the trained cyclic antagonism generation network model to generate an angiography CT image; and 4, predicting the stroke risk according to the form, the carotid artery stenosisdegree and the curvature of the carotid artery in the angiography CT image. According to the method, based on the deep learning model, the non-enhanced CBCT image is converted into the enhanced CT angiography image, carotid artery blood vessel segmentation and extraction are carried out, the carotid artery stenosis degree and curvature are quantitatively calculated, then the stroke risk is predicted, and a convenient, economical and efficient new way is provided for clinically obtaining the CTA image and diagnosing.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to a stroke risk screening method and system for cross-modal prediction of CTA images based on deep learning CBCT images. Background technique [0002] Stroke is the most common cerebrovascular disease and one of the leading causes of death and long-term disability worldwide. Ischemic stroke is the most common type of stroke, accounting for 75-85% of all stroke cases, due to obstruction and narrowing of the internal carotid artery leading to impaired blood supply to the brain, which can lead to tissue hypoxia (hypoperfusion) and tissue death within hours . Stroke has become the number one cause of death in my country and the leading cause of disability among Chinese adults. Stroke has the characteristics of high morbidity, high mortality and high disability rate. Since no effective treatment has been available, prevention is currently considered the best m...

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): G06N3/04G06N3/08G06T5/00G06T7/00
CPCG06N3/084G06T7/0012G06T5/009G06T2207/30101G06T2207/10081G06N3/045
Inventor 耿道颖于泽宽陈泓亦张军尹波李郁欣吴昊曹鑫张海燕胡斌潘嘉炜鲍奕仿周书怡陆怡平耿辰夏威杨丽琴
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 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