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

Carotid artery vulnerability grading method and system based on multi-modal radiomics

A radiomics and grading method technology, applied in the field of medical image recognition, can solve problems such as easy omission of hypoechoic plaques, poor ability to identify plaque components, and large influence of subjective judgments by testers

Pending Publication Date: 2022-05-31
SHANDONG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Two-dimensional ultrasound has been affirmed in clinical application, but it has certain limitations: ①The subjective judgment of the tester is greatly affected, and the results vary greatly among different operators; ②The ability to identify the components in the plaque is poor, and the ultrasound resolution It is not enough to accurately identify lipid-rich plaque IPH and new blood vessels in the plaque; ③ It is difficult to detect blood vessels above the bifurcation of the carotid artery, and the position is deep in obese people or those with poor lumen transmission plus multiple The existence of this kind of artifact makes it easy to miss some hypoechoic plaques by two-dimensional ultrasound, and hyperechoic calcified plaques can interfere with sound waves and affect image quality; Spatial location and configuration are difficult to clearly display on a map, so its role in identifying vulnerable plaques is limited
However, because MRI is expensive, inconvenient to operate, and has a certain degree of radiation, it also has certain limitations.

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
  • Carotid artery vulnerability grading method and system based on multi-modal radiomics
  • Carotid artery vulnerability grading method and system based on multi-modal radiomics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] like figure 1 As shown, this embodiment provides a carotid artery vulnerability grading method based on multimodal radiomics. In this embodiment, the method is applied to the server as an example. It can be understood that this method can also be applied to The terminal can also be applied to include the terminal, the server and the system, and is realized through the interaction between the terminal and the server. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud service, cloud database, cloud computing, cloud function, cloud storage, network server, cloud communication, intermediate Cloud servers for basic cloud computing services such as software services, domain name services, security services CDN, and big data and artificial intelligence platforms. The terminal may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, e...

Embodiment approach

[0051] As one or more implementations, the feature fusion refers to first connecting two feature layers and then training a weight network through a downsampling layer and a softmax layer according to the guidance of a common label to obtain a new weight feature layer.

[0052] As one or more embodiments, the NMR attention classification network is to learn the weight value according to the label guidance after parallel connection of the high-level features extracted from the MRI image and the fused features, and then train to obtain an output result.

[0053] As one or more embodiments, the ultrasonic image attention classification network is to learn the weight value according to the label guidance after parallel connection of the high-level features extracted from the ultrasonic image and the fused features, and then train to obtain an output result.

[0054] As one or more implementations, the result output module 4 outputs the grading results of ultrasound images and MRI i...

Embodiment 2

[0056] This embodiment provides a carotid artery vulnerability grading system based on multimodal radiomics.

[0057] A multimodal radiomics-based carotid arterial vulnerability grading system including:

[0058] a data acquisition module configured to: acquire at least one of a carotid artery ultrasound image and a nuclear magnetic resonance image;

[0059] an output module, configured to: obtain a carotid artery plaque vulnerability grade by adopting a carotid artery plaque grading model based on at least one of the carotid artery ultrasound image and the nuclear magnetic resonance image;

[0060] A model building module configured as: the carotid artery plaque grading model includes: a multi-scale feature fusion network and an attention classification network; wherein the multi-scale feature fusion network is used for carotid artery ultrasound image samples based on carotid artery ultrasound image samples and carotid artery MRI image samples, fuse the extracted carotid art...

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 belongs to the field of medical image recognition, and provides a carotid artery vulnerability grading method and system based on multi-modal imaging omics. The method comprises the following steps: acquiring at least one of a carotid artery ultrasound image and a nuclear magnetic resonance image; based on at least one of the carotid artery ultrasound image and the nuclear magnetic resonance image, adopting a carotid artery plaque grading model to obtain a vulnerability grade of the carotid artery plaque; the carotid plaque grading model comprises a multi-scale feature fusion network and an attention classification network; wherein the multi-scale feature fusion network is used for fusing extracted carotid ultrasound image sample features and carotid nuclear magnetic resonance image sample features based on carotid ultrasound image samples and carotid nuclear magnetic resonance image samples to obtain fusion features; the attention classification network is used for obtaining the vulnerability level of the carotid plaque based on the fusion features and the carotid ultrasound image sample features / carotid nuclear magnetic resonance image sample features.

Description

technical field [0001] The invention belongs to the field of medical image recognition, and in particular relates to a carotid artery vulnerability grading method and system based on multimodal imaging omics. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The appearance of carotid plaque is a common pathological phenomenon in the process of carotid atherosclerosis and is closely related to the occurrence of ischemic cerebrovascular disease. Autopsy studies have confirmed that, on the basis of carotid atherosclerosis, the sudden and unpredictable damage of vulnerable plaques, platelet activation, and thrombosis are important pathogenic mechanisms of ischemic cerebrovascular disease. Carotid color Doppler ultrasound is a routine examination method for carotid plaque, which can measure the thickness and length of the plaque, and make a prel...

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): G06T7/00G06V10/764G06V10/80G06V10/82G06K9/62G06N3/04
CPCG06T7/0012G06T2207/10088G06T2207/10132G06T2207/30101G06N3/045G06F18/241G06F18/253
Inventor 刘治曹艳坤米加
Owner SHANDONG UNIV
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