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

Brain image classification method and device, electronic equipment and storage medium

A classification method and brain technology, applied in the field of image processing, can solve the problems of small sample size, large heterogeneity, low signal-to-noise ratio, etc., and achieve the effects of assisting diagnosis and improving prediction accuracy

Pending Publication Date: 2022-03-25
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the image information of brain regions has the characteristics of relatively small sample size, high dimensionality, large heterogeneity, and is easily interfered by

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
  • Brain image classification method and device, electronic equipment and storage medium
  • Brain image classification method and device, electronic equipment and storage medium
  • Brain image classification method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] figure 1 It is a schematic flowchart of a brain image classification method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of classifying brain images at multiple time points. Classification device, which can be implemented by software and / or hardware, and can be configured in a terminal and / or server to implement the brain image classification method in the embodiment of the present invention.

[0030] Such as figure 1 As shown, the method in this embodiment may specifically include:

[0031] S110. Acquire target resting-state functional image information of the brain region of the target subject.

[0032] Wherein, the resting state functional image information of the target is obtained based on resting state functional magnetic resonance imaging technology.

[0033] In the embodiment of the present invention, the target resting state functional image information can be understood as the image information obtained a...

Embodiment 2

[0062] figure 2 It is a schematic flow chart of a brain image classification method provided in Embodiment 2 of the present invention. On the basis of the above technical solution, this embodiment further refines the technical solution. In this embodiment, on the basis of any optional technical solution in the embodiments of the present invention, optionally, the processing of the target resting-state functional image information is performed to obtain the target brain network map of the target object, including : according to the target resting state functional image information, determine the data acquisition time series of each brain region of the target object; calculate the Pearson correlation coefficient of the data acquisition time series of every two brain regions respectively, and compare the Pearson The correlation coefficient is subjected to Fisher Z transformation, and the target brain functional connection image is determined according to the transformed Pearson ...

Embodiment 3

[0078] image 3 It is a schematic diagram of the network training process of a brain image classification method provided by Embodiment 3 of the present invention, Figure 4 It is a schematic diagram of the construction process of the target brain functional connection image in a brain image classification method provided by Embodiment 3 of the present invention; the embodiment of the present invention is a preferred embodiment of the above-mentioned invention embodiments, as image 3 As shown, the network training process in the embodiment of the present invention may include a data processing process, a network training process, and a network testing process.

[0079] First, the original Resting-State Functional Magnetic Resonance Imaging (RS-FMRI) information from different data sources is obtained, where different data sources can be represented by source 1, source 2, ..., source N, etc.; then, Enter the data processing process, perform preprocessing operations such as sk...

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 embodiment of the invention discloses a brain image classification method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining target resting state function image information of a brain region of a target object, and enabling the target resting state function image information to be obtained based on a resting state function magnetic resonance imaging technology; the target resting state function image information is processed, a target brain network map of the target object is obtained, and the target brain network map comprises target brain function connection images of the target object at at least two preset time points; inputting each target brain function connection image corresponding to the target brain network atlas into a pre-trained brain atlas classification model to obtain a prediction probability that the target object belongs to each preset category, the brain atlas classification model is obtained based on training of the sample brain network atlas and classification labels corresponding to the sample target brain network atlas. According to the technical scheme of the embodiment of the invention, the classification of the brain image can be accurately predicted.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a method, device, electronic device, and storage medium for classifying brain images. Background technique [0002] With the increasing pace of life in contemporary society, the incidence of various brain diseases is increasing year by year. Among them, Alzheimer's disease (AD) is the most common, progressive and irreversible senile neurological disease. diseases, and their influence on the current society is also increasing day by day. Mild cognitive impairment (MCI) is a state of cognitive impairment between normal aging and mild AD, belonging to a transitional stage, characterized by memory impairment or accompanied by other cognitive impairments, However, their social functions have not been affected, and the ability of daily life is not affected. Therefore, early identification of MCI patients is of great significance for improving the qu...

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): G06V10/764G06V10/82A61B5/055A61B5/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08A61B5/055A61B5/0033A61B5/0042A61B5/4088G06N3/045G06F18/2415
Inventor 徐锦萍胡庆茂
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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