Neural fingerprint extraction and classification method and system

A classification method and neural technology, applied in the medical field, can solve the problems of lack of quantifiable standards, lack of quantitative standards and speech system, standardization of electronic medical records and bottlenecks of big data mining, etc.

Active Publication Date: 2018-07-17
迈格生命科技(深圳)有限公司
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The interpretation and classification of existing magnetic resonance brain images are completely dependent on the doctor's visual observation and subjective judgment based on experience. The discovery of lesions is overly dependent on experience and lacks

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
  • Neural fingerprint extraction and classification method and system
  • Neural fingerprint extraction and classification method and system
  • Neural fingerprint extraction and classification method and system

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0037] Taking Alzheimer's disease as an example, the specific steps of the method of the present invention are as follows:

[0038] ① Image acquisition. Select a number of healthy people and Alzheimer's disease patients with different classifications and stages as the initial subjects, collect T1, T2, DTI, ASL, MRS and other multi-modal magnetic resonance images of each subject, and obtain each subject's Clinical data such as age, gender, and scale scores.

[0039] ② Image preprocessing. First, the whole brain automatic segmentation algorithm based on brain atlas is used to process the 3D magnetic resonance data, and the results of whole brain labeling and positioning are obtained, and then the registration algorithm is used to integrate other modal brain images (T2, DTI, ASL, MRS, etc.) The annotated structural image (T1) is registered to map the segmentation results to the MRI images of different modalities.

[0040] ③ Extract neural fingerprints. For MRI data of differe...

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 neural fingerprint extraction and classification method. The method comprises an image acquisition step, a brain structure annotation step and a neural fingerprint extractionstep in sequence. The method has the advantages that information mining is performed on magnetic resonance images in different sequences, a unified fingerprint extraction and establishment method forall brain areas is formed through unified structure annotation establishment and positioning, a comprehensive neural fingerprint system is constructed, neural fingerprint standard libraries for different sexes and different ages are established, and therefore brain health assessment, disease classification and parting and disease prediction can be performed on a to-be-tested target; through the establishment of the neural fingerprint standard libraries, quantitative assessment and classification can be performed on brain development, brain senescence, neural diseases and mental diseases of a to-be-tested object, and talent assessment, advantage assessment, senescence assessment, rehabilitation assessment, assistant diagnosis, disease prediction and other technologies can be formed; and a standard technical foundation is laid for advantage cultivation, brain healthcare and diagnosis and prevention of brain diseases of human talents.

Description

technical field [0001] The invention relates to image processing technology and artificial intelligence recognition technology in the medical field, in particular to a neural fingerprint extraction and classification method and system. Background technique [0002] Magnetic resonance imaging is a commonly used medical tomographic imaging method, which uses magnetic resonance phenomena to obtain electromagnetic signals from the human body and reconstruct human body information. This technology uses the principle of nuclear magnetic resonance, according to the different attenuation of the released energy in different structural environments inside the material, and through the detection of the emitted electromagnetic waves by an external gradient magnetic field, the position and type of the atomic nucleus that constitutes the object can be known. This can be mapped into an image of the structure inside the object. Two-thirds of the weight of the human body is water, and the w...

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): G06K9/62G06T7/12G06T7/38
CPCG06T7/12G06T7/38G06T2207/10088G06V10/751G06F18/253G06F18/259
Inventor 马婷
Owner 迈格生命科技(深圳)有限公司
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