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

Stroke disability prediction method and system based on magnetic resonance imaging

A magnetic resonance and imaging technology, which is applied in the directions of using nuclear magnetic resonance imaging system for measurement, magnetic resonance measurement, neural learning methods, etc., can solve problems such as the inability to assess the degree of disability of patients, the inability of doctors to carry out treatment, and incontinence, so as to avoid The effect of subsequent disability

Active Publication Date: 2020-05-12
BEIJING ANDE YIZHI TECH CO LTD
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its evaluation results are divided into seven levels, which are 0: no symptoms at all; 1: despite symptoms, no obvious disability is seen, and can complete all usual duties and activities; 2: mild disability; cannot complete all previously able activities. 3: Moderately disabled; needs some assistance, but walks without assistance; 4: Severely disabled; unable to walk without assistance and unable to take care of own physical needs; 5: Severely disabled; bedridden, incontinent, requiring constant care and attention; 6: Death
[0006] The current stroke disability prediction method mainly uses the NIHSS or mRS scales to observe the current actual tasks or states of stroke patients, so as to evaluate the disability status, and cannot evaluate the future time points of patients. level of disability, doctors are unable to provide follow-up treatment

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
  • Stroke disability prediction method and system based on magnetic resonance imaging
  • Stroke disability prediction method and system based on magnetic resonance imaging
  • Stroke disability prediction method and system based on magnetic resonance imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] figure 1 It is a flowchart of a stroke disability prediction method based on magnetic resonance images in Embodiment 1 of the present invention.

[0055] see figure 1 , the method for predicting stroke disability based on magnetic resonance images in this embodiment includes:

[0056] Step S1: Obtain a test set of magnetic resonance images; the test set of magnetic resonance images is the magnetic resonance images of stroke patients to be tested.

[0057] Step S2: Input the magnetic resonance image test set into the trained brain age prediction model to obtain the brain age prediction value of the stroke patient to be tested.

[0058] The trained brain age prediction model is obtained by training an age-based convolutional neural network model with the baseline diffusion weighted magnetic resonance images of healthy elderly people as input and the real age of healthy elderly people as output. The age-based convolutional neural network model is constructed based on a ...

Embodiment 2

[0077] The stroke disability prediction method based on magnetic resonance images in this embodiment, based on the magnetic resonance images collected at the time of admission and the results of longitudinal follow-up evaluation, establishes a high-dimensional model of the relationship between image features and the future disability of patients through deep learning methods, so as to achieve Only through imaging at the admission stage, it can predict the disability of patients at future time points (such as three months, six months or one year later).

[0078] Artificial intelligence methods can use brain structural magnetic resonance images to establish a prediction model of brain aging, so as to predict the age of the elderly. The age predicted by the model is called "brain age". Brain age can indicate the current stage of brain aging and even predict future risk of related diseases. The prediction model established by the image data of the healthy elderly actually describe...

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 stroke disability prediction method and system based on magnetic resonance imaging. The method comprises the following steps: acquiring a magnetic resonance imaging testing set; inputting the magnetic resonance imaging set into a trained brain age prediction model so as to obtain a brain age prediction value of a stroke patient to be tested; confirming a brain age difference of the stroke patient to be tested according to the brain age prediction value of the stroke patient to be tested and a corresponding real brain age value of the stroke patient to be tested; and inputting the magnetic resonance imaging set and the brain age difference of the stroke patient to be tested into a trained disability prediction model, so as to obtain a disability degree of the stroke patient to be tested. By adopting the method and system, future disability situations of stroke patients can be predicted.

Description

technical field [0001] The present invention relates to the technical field of stroke disability prediction, in particular to a stroke disability prediction method and system based on magnetic resonance images. Background technique [0002] Cerebral stroke, also known as stroke and cerebrovascular accident (cerebral vascular accident, CVA), is an acute cerebrovascular disease. Stroke is the leading cause of death and disability among adults in my country, and it has the characteristics of high incidence, high disability, high mortality and high recurrence rate. At present, the treatment methods for stroke are limited, and the curative effect is not ideal. Prevention is the best treatment at this stage. For doctors, it is necessary to effectively evaluate which patients will be more affected by the disease at a future time point and have a high degree of disability, so as to take corresponding measures in subsequent treatment. [0003] Currently, the most widely used evalua...

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): A61B5/055G01R33/48G01R33/54G06N3/04G06N3/08
CPCA61B5/055G01R33/4806G01R33/54G06N3/04G06N3/08
Inventor 刘涛刘子阳程健徐红
Owner BEIJING ANDE YIZHI TECH CO LTD
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