Missing multi-modal representation learning algorithm for Alzheimer's disease diagnosis

An Alzheimer's disease and learning algorithm technology, applied in the field of missing multimodal representation learning algorithms, can solve problems such as missing multimodal data, and achieve the effect of good diagnosis accuracy and good development prospects.

Pending Publication Date: 2020-11-17
TIANJIN POLYTECHNIC UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, we often face the situation of missing multimodal data (that is, not all modal data are complete). Most of the multimodal learning algorithms are not able to effectively deal with missing multimodal data

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
  • Missing multi-modal representation learning algorithm for Alzheimer's disease diagnosis
  • Missing multi-modal representation learning algorithm for Alzheimer's disease diagnosis
  • Missing multi-modal representation learning algorithm for Alzheimer's disease diagnosis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described in detail below in combination with specific embodiments. figure 1 A flow chart of the missing multimodal representation learning algorithm for Alzheimer's disease diagnosis of the present invention is given. Such as figure 1 As shown, the missing multimodal representation learning algorithm for Alzheimer's disease diagnosis of the present invention includes:

[0022] 1. Obtain the original data of MRI and PET-CT of Alzheimer's disease;

[0023] 2. Obtain the feature vector of each sample through data preprocessing;

[0024] 3. Use the autoencoder network to learn the potential representation of the complete MRI modality, while constraining the correlation between samples through graph regularization;

[0025] 5. Map the eigenvectors to the kernel space, fill in the missing information through kernel techniques, and constrain the correlation between the two modes through the Hilbert-Schmidt Independence Index (HSIC);

...

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 provides a missing multi-modal representation learning algorithm for Alzheimer's disease diagnosis. The invention provides a brand-new missing multi-modal data completion model. The missing multi-modal representation learning algorithm for Alzheimer's disease diagnosis comprises the following steps: firstly, mapping original complete modal data to a hidden space by using an automaticencoder network; then supplementing a kernel matrix of an incomplete view in the kernel space by utilizing potential representation learned from the complete mode, meanwhile, constraining the correlation between samples and between modes through graph regularization and an HSIC algorithm, and finally mapping the kernel matrix into a feature matrix through correlation analysis of a kernel method to complete a subsequent diagnosis task. The Alzheimer's disease can be rapidly and accurately diagnosed under the condition that certain modal data are lost, and the algorithm has good performance andobvious advantages, can be applied to scenes such as assisting in diagnosis of doctors and community screening, and has a good development prospect along with development of a population aging process.

Description

technical field [0001] The invention relates to a missing multimodal representation learning algorithm for the diagnosis of Alzheimer's disease, and belongs to the fields of machine learning and medical image analysis. Background technique [0002] Alzheimer's disease (AD) and its early stages are an irreversible neurodegenerative disease that has a serious impact on people's health worldwide. Alzheimer's disease is usually difficult to cure, However, early comprehensive treatment can alleviate the condition and delay the development, so early diagnosis and treatment are of great significance to improve the quality of life of patients. [0003] Computer-aided diagnosis of Alzheimer's disease through machine learning can improve diagnostic efficiency, and a large number of studies have shown that computer-aided diagnosis methods combined with multimodal data can further improve diagnostic accuracy. However, in practical applications, we often face the situation of missing mu...

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): A61B5/00
CPCA61B5/4088A61B5/7267
Inventor 刘彦北樊连玺王忠强肖志涛耿磊张芳吴骏王雯
Owner TIANJIN POLYTECHNIC 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