Alzheimer's disease feature extraction method and system based on overall correlation coefficient
A technology of correlation coefficient and feature extraction, which is applied in the fields of biometric identification, instrumentation, recognition of medical/anatomical patterns, etc., can solve the research of feature extraction of Alzheimer's disease, application of genetic algorithm without overall correlation coefficient, unseen Problems such as the overall correlation coefficient and genetic algorithm can achieve the effect of improving the efficiency of feature extraction and improving the efficiency of feature optimization
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0095] Aiming at the current bottleneck problem of extracting key features for classification and recognition of Alzheimer's disease, mild cognitive impairment and normal health based on magnetic resonance imaging to effectively improve the classification effect but the optimization efficiency is not high, this implementation In this example, a genetic algorithm based on the overall correlation coefficient is proposed to optimize the feature extraction process, so as to find the key features that affect the conversion of different stages of Alzheimer's disease in a shorter time, so as to provide assistance for the research of computer-aided diagnosis of Alzheimer's disease .
[0096] Taking the Alzheimer's disease classifier as a Gaussian process classifier, the input is 100 MRI images, and the output is the key features reflecting the essence of Alzheimer's disease as an example, the specific implementation process of the genetic algorithm based on the overall correlation coef...
Embodiment 2
[0140] In order to illustrate the effect of the feature extraction method of the present invention, corresponding experiments are specially designed for verification in this embodiment. The experimental software of this experiment uses MATLAB2017a and FreeSurfer v5.3.0, and the experimental image is in the three-dimensional format.NII.
[0141] The specific implementation process of the experiment of this embodiment includes:
[0142] (1) Data acquisition
[0143] The data used in this embodiment comes from ADNI (Alzheimer's Disease Neuroimaging Initiative), a large public database of Alzheimer's disease in the United States. The selection criteria for the experimental data is to select data with a balanced ratio of male to female, and the TR / TE values of the imaging parameters must be the same. In this way, the interference of some unknown factors can be eliminated, and the inter-individual differences are small. Therefore, a 3.0T MR scanner was selected in this embodiment...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com