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

Alzheimer's disease classification method based on depth forest

A classification method and forest technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of difficult MRI image features, low classification accuracy of Alzheimer's disease, etc., to achieve early diagnosis, good description of samples, The effect of improving the recognition rate

Inactive Publication Date: 2017-12-22
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a deep forest-based classification method for Alzheimer's disease, which solves the difficulty in extracting the features of MRI images of Alzheimer's disease by traditional machine learning algorithms, thereby enabling the classification of Alzheimer's disease Technical issues with low accuracy

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 based on depth forest
  • Alzheimer's disease classification method based on depth forest
  • Alzheimer's disease classification method based on depth forest

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0037] A deep forest-based Alzheimer's disease classification method, comprising the following steps:

[0038] Step 1: The MRI image for detecting Alzheimer's disease is used as the input of the multi-granularity scan, the output of the multi-granularity scan is connected to the cascade forest, and the cascade forest outputs a class vector of the MRI image to complete the deep forest model Constructed, the classification result of the MRI image includes Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal person (NC), and the class vector is the maximum probability value in the category of the MRI image.

[0039] Step 2: Preprocessing MRI images of several known categories, that is, performing AC-PC origin correction on the MRI images; segmenting each corrected MRI image to obtain MRI gray matter images; normalizing the MRI gray matter images to A unified MNI template, so that the size of each MRI gray matter image is unified; the standardized MRI gray matter i...

specific Embodiment 2

[0042] Step 1: The MRI image for detecting Alzheimer's disease is used as the input of the multi-granularity scan, the output of the multi-granularity scan is connected to the cascade forest, and the cascade forest outputs a class vector of the MRI image to complete the deep forest model Constructed, the category of the MRI image includes Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal person (HC), and the class vector is the maximum probability value in the category of the MRI image.

[0043] Step 2: Preprocessing MRI images of several known categories, that is, performing AC-PC origin correction on the MRI images; segmenting each corrected MRI image to obtain MRI gray matter images; normalizing the MRI gray matter images to A unified MNI template, so that the size of each MRI gray matter image is unified; the standardized MRI gray matter image is smoothed and down-sampled, and the processed image is sliced ​​to obtain a preprocessed MRI image, the MRI ima...

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 based on a depth forest, and belongs to the field of medical image classification and prediction. The method comprises the steps: taking an MRI image of the detection of the Alzheimer's disease as the input of the multi-granularity scanning, enabling the output of the multi-granularity scanning to be connected with a cascading forest, enabling the cascading forest to output one class vector of the MRI image, and completing the construction of a depth forest model; carrying out the preprocessing of a plurality of MRI images of known types; extending the depth forest model by one level, and carrying out the training and testing through the preprocessed MRI image: completing the training if a testing result is not improved remarkably, or else extending to the next level and continuing the training; inputting the preprocessed to-be-classified MRI image into the trained depth forest, and outputting and obtaining a classification result of the MRI image. The method greatly improves the recognition rate of the Alzheimer's disease.

Description

technical field [0001] The invention relates to the fields of medical image classification, pattern recognition and machine learning, in particular to a deep forest-based Alzheimer's disease classification method for classifying and judging Alzheimer's disease. Background technique [0002] Today, with the vigorous development of image processing technology, pattern recognition and machine learning theories and methods, medical image processing, as one of the fields most closely related to human life, has attracted more and more attention following in the footsteps of artificial intelligence. The classification of Alzheimer's disease is an important branch in the field of medical image classification. It is of great significance in the computer-aided diagnosis of Alzheimer's disease, especially in the early diagnosis of the disease and the timely control of the disease deterioration. [0003] MRI (Magnetic Resonance Imaging) images can provide a wealth of brain tissue morpho...

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): G06K9/62G06K9/66G06T7/00G06F19/00
CPCG06T7/0012G06T2207/10088G06T2207/20081G06V30/194G06F18/24
Inventor 程建朱晓雅张建张泽厚周娇
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com