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

Auxiliary diagnosis system and method for Parkinson's disease based on multimodal transcranial ultrasonography

A technology for auxiliary diagnosis and Parkinson's disease, applied in ultrasound/sound wave/infrasonic wave diagnosis, sound wave diagnosis, infrasonic wave diagnosis, etc., can solve problems such as difficult diagnosis

Active Publication Date: 2018-10-19
SHANGHAI UNIV
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the diagnosis of Parkinson's disease is still mainly based on its clinical core symptoms. However, these core symptoms are not all of Parkinson's disease, and it is difficult to diagnose only based on medical history and clinical manifestations. Therefore, it is especially necessary to develop a method for early diagnosis of Parkinson's disease.

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
  • Auxiliary diagnosis system and method for Parkinson's disease based on multimodal transcranial ultrasonography
  • Auxiliary diagnosis system and method for Parkinson's disease based on multimodal transcranial ultrasonography
  • Auxiliary diagnosis system and method for Parkinson's disease based on multimodal transcranial ultrasonography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] see figure 1 , the present invention is an auxiliary diagnosis system and method for Parkinson's disease based on multimodal transcranial ultrasound, including an input module (1), a feature extraction module (2), a feature selection module (3) and a diagnosis module (4), It is characterized in that: the input module (1) is connected to the diagnosis module (4) after performing feature extraction module (2) and feature selection module (3); the input module (1) reads in ultrasonic images and ultrasonic color Doppler Le image, the feature extraction module (2) extracts the image features of the substantia nigra region of the ultrasound image, and obtains the arterial blood flow spectrum curve in the Doppler image by segmentation; the feature selection module (3) selects the features of the ultrasound module; the diagnosis module (4) Multimodal features are classified by multimodal learning algorithm, and auxiliary diagnosis results are obtained, which can be used as an a...

Embodiment 2

[0026] see figure 1 with figure 2 , the present invention is an auxiliary diagnosis system and method for Parkinson's disease based on multimodal transcranial ultrasound, which is operated by using the above system, and is characterized in that:

[0027] (1). Two modality data of transcranial ultrasound image and ultrasound color Doppler image are read in;

[0028] (2). Extract the midbrain target area in the transcranial ultrasound image, and extract various features of the corresponding texture, geometry and statistical features;

[0029] (3). Intercept the middle artery blood flow spectrum in the ultrasound color Doppler image, segment the background and foreground, obtain the blood flow spectrum data, and calculate various related parameters;

[0030] (4). Calculate the significant difference of the target area features, and select the features with significant differences;

[0031] (5). The multimodal learning method is used to learn the data of the two modalities, an...

Embodiment 3

[0033] The present embodiment is basically the same as the second embodiment, and the special features are as follows: in the step (2) of the second embodiment, when processing the data of the ultrasonic image, a variety of features are extracted through various methods; the embodiment In the second step (3), the adaptive threshold separation algorithm is used to separate the foreground and background of the blood flow spectrum, and then the edge detection method is used to extract the foreground contour, and the MeanShift method is used to smooth the foreground contour curve to obtain the required blood flow spectrum. flow signal curve data, and finally calculate various parameters related to the curve; in the step (4) of the second embodiment, the feature selection step can extract effective features through different feature selection methods; the steps of the second embodiment ( In 5), the multimodal learning method is used to learn the fusion features of the two modalities...

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 auxiliary diagnosis system and method for a Parkinson's disease based on multimodal transcranial ultrasonography. The system comprises an input module, a feature extractionmodule, a feature selection module and a diagnosis module. The input module passes through the feature extraction module and the feature selection module and then is connected with the diagnosis module; the input module reads an ultrasound image and an ultrasound colorful Doppler image, the feature extraction module extracts image features of a substantia nigra area of the ultrasound image, and division is conducted to obtain an arterial blood flow frequency spectrum curve in the Doppler image; the feature selection module selects features of the ultrasound module; the diagnosis module classifies multimodal features through a multimodal learning algorithm to obtain an auxiliary diagnosis result as an auxiliary reference for doctors to carry out diagnosis.

Description

technical field [0001] The invention relates to the application field of computer analysis technology based on medical images, in particular to a multimodal transcranial ultrasound-based auxiliary diagnosis system and method for Parkinson's disease. Background technique [0002] Parkinson's disease (Paekinson's disease, PD), also known as Parkinson's paralysis, is a common neurodegenerative disease in middle-aged and elderly people. Clinically, the main manifestations are bradykinesia, rigidity, resting tremor, and asymmetrical movement symptoms of postural balance disorder. At present, the diagnosis of Parkinson's disease is still mainly based on its clinical core symptoms. However, these core symptoms are not unique to Parkinson's disease, and it is difficult to make a diagnosis based on medical history and clinical manifestations alone. Therefore, it is especially necessary to develop a method for early diagnosis of Parkinson's disease. [0003] As a non-invasive techniq...

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): A61B8/00A61B8/08
CPCA61B8/0808A61B8/0891A61B8/4411A61B8/488A61B8/5223A61B8/5246
Inventor 施俊郑晓
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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