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

Alzheimer's disease classification method and system based on anatomical landmark and residual network

An Alzheimer's disease and classification method technology, applied in the field of Alzheimer's disease classification methods and systems, can solve the problems of not taking into account subtle changes, high time and cost, low classification accuracy, etc., to achieve auxiliary The effect of clinical diagnosis, reducing time cost, avoiding the risk of overfitting

Active Publication Date: 2020-07-10
SHANDONG NORMAL UNIV
View PDF11 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] However, the inventors have found that at least the following problems exist in the prior art: the methods based on regions of interest (ROIs) rely on the total changes of each brain area to Diagnosis without taking into account their subtle changes; voxel-based methods produce features with very high dimensionality, time-consuming classification and often challenged by overfitting; landmark-based depth The learning method conducts independent training for each landmark-based block. When the classification results of the blocks are quite different, the blocks with low classification accuracy will affect the final diagnosis result.

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
  • Alzheimer's disease classification method and system based on anatomical landmark and residual network
  • Alzheimer's disease classification method and system based on anatomical landmark and residual network
  • Alzheimer's disease classification method and system based on anatomical landmark and residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as figure 1 As shown, this embodiment provides a classification method for Alzheimer's disease based on anatomical landmarks and residual networks, including:

[0036] Step 1. After tissue segmentation and modulation of the training image set, the gray matter image is obtained;

[0037] Step 2. Perform a two-sample t-test on the voxels of the Alzheimer's disease image and the normal subject image in the training image set, and identify anatomical landmarks with a preset significance level threshold;

[0038] Step 3, extracting the gray matter feature block of the gray matter image centered on the obtained anatomical landmark;

[0039] Step 4. Connect the gray matter feature blocks, input the obtained synthetic blocks into the residual network model for feature extraction, use the features extracted by the residual network model as the input of the classifier, and test the Alzheimer's disease patients in the test image set Classified with normal subjects.

[0040...

Embodiment 2

[0065] This embodiment provides an Alzheimer's disease classification system based on anatomical landmarks and residual networks, including:

[0066] The preprocessing module is configured to obtain gray matter images after tissue segmentation modulation is performed on the training image set;

[0067] The anatomical landmark acquisition module is configured to compare the voxels of the Alzheimer's disease images in the training image set and the images of normal subjects to identify anatomical landmarks;

[0068] The gray matter feature extraction module is configured to extract the gray matter feature block of the gray matter image centered on the obtained anatomical landmark;

[0069] The training and classification module is configured to connect the gray matter feature blocks, input the obtained synthetic blocks to the residual network model for feature extraction, use the features extracted by the residual network model as the input of the classifier, and use the Al of t...

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 an Alzheimer's disease classification method and system based on an anatomical landmark and a residual network, and the method comprises the steps: carrying out the tissue segmentation modulation of a training image set, and obtaining a gray matter image; comparing voxels of the Alzheimer's disease image and the normal subject image in the training image set to identify ananatomical landmark; taking the obtained anatomical landmark as a center, and extracting grey matter blocks of the gray image; and connecting the grey matter blocks, inputting the obtained synthetic blocks into a residual error network model for feature extraction, taking features extracted by the residual error network model as input of a classifier, and classifying Alzheimer's disease patients and normal subjects in the test image set. The anatomical landmark is taken as the center, feature blocks of gray matters in three tissues of the brain are taken as the input of the residual network, the feature blocks are taken as the feature expression of each MR image, the residual network model is adopted to enhance the feature learning capability of the network, and the classification accuracyis enhanced.

Description

technical field [0001] The present disclosure relates to the technical fields of artificial intelligence and medical images, in particular to a method and system for classifying Alzheimer's disease based on anatomical landmarks and residual networks. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Magnetic resonance images (MRI) can clearly display the gray matter and white matter of the brain, and sensitively display changes in brain structure. There may be no obvious clinical symptoms in the early stage of the disease, but degenerative lesions must occur in some relevant brain regions. Therefore, MRI has now become an indispensable auxiliary system in the diagnosis of various neurological diseases. [0004] At present, the diagnosis of Alzheimer's disease (AD) based on MRI images is mainly divided into three types: [0005] (1) Metho...

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): G06T7/00G06T7/11G06K9/62
CPCG06T7/0012G06T7/11G06T2207/10088G06T2207/20081G06T2207/20084G06T2207/30016G06F18/2411
Inventor 乔建苹朱甜
Owner SHANDONG NORMAL 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