Blood vessel wall plaque recognition equipment, system and method and storage medium

A blood vessel wall and plaque technology, applied in the medical field, can solve problems such as low efficiency and inability to effectively guarantee the recognition accuracy, and achieve the effects of improving recognition efficiency, ensuring recognition accuracy, and preventing recurrence

Active Publication Date: 2019-04-05
SHENZHEN INST OF ADVANCED TECH
View PDF4 Cites 10 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 device, system, method and storage medium for identifying plaque on the blood vessel wall, aiming at solving the problems existing

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
  • Blood vessel wall plaque recognition equipment, system and method and storage medium
  • Blood vessel wall plaque recognition equipment, system and method and storage medium
  • Blood vessel wall plaque recognition equipment, system and method and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 It shows the blood vessel wall plaque recognition device provided by Embodiment 1 of the present invention, the device is mainly used for: using artificial intelligence (Artificial Intelligence, AI) technology to intelligently recognize plaque in the blood vessel wall MRI image, the device can It is a separate computer and chip, and it can also be physically integrated with other equipment, such as: integrated with MRI equipment, or it can be expressed as a cloud server. Vascular wall plaques can be roughly divided into stable plaques and unstable plaques. Unstable plaques are prone to detachment from the vessel wall and cause thrombus. Unstable plaques have fibrous caps, hemorrhage, calcification, lipid core, inflammation, etc. When using AI technology to identify vascular wall plaque, it can not only identify whether there is vascular wall plaque, but also identify the type of vascular wall plaque. For ease of description, only the parts related to the embod...

Embodiment 2

[0056] On the basis of Embodiment 1, this embodiment further provides the following content:

[0057] In this embodiment, when the processor 102 executes the computer program 103 stored in the memory 101, the specific implementation is as follows figure 2 Steps in the method shown:

[0058] In step S201, the above-mentioned MRI image is preprocessed to obtain an initial image. In this embodiment, preprocessing may involve cropping the image to reduce redundant calculations.

[0059] In step S202, the initial image is input to the deep learning neural network for plaque identification, and the identification result is obtained. In this embodiment, the architecture of the deep learning neural network can adopt R-CNN architecture, Fast R-CNN architecture, accelerated regional convolutional neural network (Faster R-CNN) architecture, SSD architecture, masked area convolutional neural network (Mask R-CNN) architecture, etc.

Embodiment 3

[0061] On the basis of Embodiment 2, this embodiment further provides the following content:

[0062] In this example, if image 3 As shown, the deep learning neural network specifically includes: a convolutional subnetwork 301 , a candidate frame subnetwork 302 and a fully connected subnetwork 303 . Wherein, each sub-network processing is roughly as follows, and each sub-network processing corresponds to the detailed flow of the above step S202:

[0063] The convolutional sub-network 301 can be executed as Figure 4 In step S401 shown, feature extraction processing is performed on the initial image to obtain a convolutional feature image. In this embodiment, the convolutional sub-network 301 may include multiple convolutional neural networks, and each convolutional neural network may use a residual convolutional neural network to alleviate problems such as gradient disappearance and gradient explosion, or a non-residual convolutional neural network may be used. Convolution...

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 is applicable to the technical field of medical treatment, and provides blood vessel wall plaque recognition equipment, system and method and a storage medium. The method comprises the following steps of identifying patches in the MRI image by using a deep learning method. adopting a deep learning method to identify the blood vessel wall plaque. manpower can be greatly reduced, the plaque identification accuracy is improved, the identification efficiency is improved, and the identification accuracy can be ensured. MRI is adopted to carry out comprehensive and accurate image assessment on ischemic stroke related vascular bed plaques, artificial intelligence is utilized to carry out rapid and accurate diagnosis, and the method has very important significance in screening cerebral stroke high-risk groups and exploring pathogenesis to prevent reoccurrence.

Description

technical field [0001] The invention belongs to the field of medical technology, and in particular relates to a blood vessel wall plaque identification device, system, method and storage medium. Background technique [0002] Magnetic resonance imaging (Magnetic Resonance Imaging, MRI) is currently the only non-invasive imaging method that can clearly display systemic atherosclerotic plaques. Vascular wall MRI can not only quantitatively analyze systemic vascular plaques such as intracranial arteries, carotid arteries, and aorta, but also accurately identify unstable features such as fibrous cap, hemorrhage, calcification, lipid core, and inflammation of vulnerable plaques. , is currently recognized as the best plaque imaging method. [0003] With the localization of MRI equipment and the popularization of social applications, as well as the unique advantages of MRI plaque imaging, the use of MRI for comprehensive plaque screening and stroke etiology exploration for stroke h...

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
IPC IPC(8): G06T7/00
CPCG06T7/0012G06T2207/30101G06T2207/20081G06T2207/20084G06T2207/10088
Inventor 郑海荣刘新胡战利张娜李思玥梁栋杨永峰
Owner SHENZHEN INST OF ADVANCED TECH
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