Modular feature selection method for brain disease classification

A feature selection method and disease classification technology, applied in the field of modular feature selection, can solve problems such as ignoring topology and disaster of dimensionality

Pending Publication Date: 2021-10-19
LIAOCHENG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the design of edge-based features is simple, due to the small number of subjects, such high-dimensional features will lead to the problem of the curse of dimensionality.
And this operation of splicing adjacency matrices into vectors ignores the topology of brain maps such as modularity

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
  • Modular feature selection method for brain disease classification
  • Modular feature selection method for brain disease classification
  • Modular feature selection method for brain disease classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to deepen the understanding of the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments, which are only used to explain the present invention and do not limit the protection scope of the present invention.

[0034] Such as figure 2 and image 3 As shown, a modular feature selection method for brain disease classification, the steps are as follows:

[0035] 1. Data acquisition and data preprocessing: In the example, using a data set from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, a total of 174 subjects (48 normal controls (NCs), 95 MCI and 31 AD) conducted 563 scans. It is worth noting that the subjects in this study were scanned once or more times with an interval of at least half a year. Therefore, the 563 scans can be divided into 154 cases of NC, 310 cases of MCI (eMCI 165 cases, lMCI 145 cases) and AD 99 cases, then, the rs-fMRI scans of all...

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 modular feature selection method (MLFS for short) for brain disease classification, and the method comprises the following steps: carrying out the preprocessing of a functional magnetic resonance image, and dividing a brain into a pre-designated brain region; extracting an average time sequence corresponding to all brain regions and constructing a functional brain map; searching modular structure information by using a signed spectral clustering algorithm; and selecting a discriminative feature through a group LASSO method based on modularization, wherein a support vector machine (SVM) is used for classification. According to the embodiment of the invention, the discriminative features in the brain map can be clearly identified by using modular information, and the method is used for brain disease classification, and has a certain reference value for studying cognitive impairment of the brain.

Description

technical field [0001] The invention relates to a modular feature selection method for brain disease classification, specifically a method for selecting features using modular information as network prior knowledge, and belongs to the technical field of biomedical information processing. Background technique [0002] Resting-state functional magnetic resonance imaging (rs-fMRI) provides a non-invasive method for exploring human brain function and has received widespread attention as an important tool for understanding brain functional organization. Based on this advanced technology, functional brain map analysis, as a new research hotspot in the field of medical images, has been shown in the identification and classification of brain diseases such as Alzheimer's disease (AD) and its early stage, mild cognitive impairment (MCI). great potential. [0003] In the research of brain map analysis, it is a question of great research significance to select which features to classif...

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): G06K9/62G06K9/46G06T5/00
CPCG06T5/002G06T2207/10088G06T2207/30016G06F18/241
Inventor 张丽梅乔立山张阳阳
Owner LIAOCHENG UNIV
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