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

Automatic Recognition Method of Medical Ultrasound Images Based on Redundant Feature Reduction

An ultrasound image and automatic identification technology, applied in the field of automatic identification of medical ultrasound images, can solve the problems of not comprehensively and objectively reflecting image characteristics, low classification correct identification rate, and few extracted features, etc., and achieves good application effect and clinical application. Practicality, excellent classification effect

Active Publication Date: 2016-02-24
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The existing image classification methods are limited in use, only for a certain specific image; the extracted features are few, which cannot comprehensively and objectively reflect the characteristics of the image; at the same time, the correct recognition rate of classification is low, the classification effect is poor, and it lacks practicability

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
  • Automatic Recognition Method of Medical Ultrasound Images Based on Redundant Feature Reduction
  • Automatic Recognition Method of Medical Ultrasound Images Based on Redundant Feature Reduction
  • Automatic Recognition Method of Medical Ultrasound Images Based on Redundant Feature Reduction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical idea of ​​the present invention is: select a region of interest (ROI) according to the characteristics of the medical ultrasound image to be processed, extract image feature information and perform de-redundancy processing, and use SVM to classify the features of the region of interest. See the specific process figure 1 , including the following 5 steps:

[0048] Step 1. Select the medical ultrasound image to be processed, and obtain the region of interest ROI as the recognition region;

[0049] Step 2. Preprocessing the ROI, such as denoising, enhancing, etc.;

[0050] Step 3, performing feature extraction on the selected ROI;

[0051] The image features that can be extracted by the present invention include three types, namely texture features, morphological features and elastic features. In the present invention, the more complete the extracted features are, the better it can reflect the essential characteristics of the image.

[0052]Among them, th...

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 automatic medical ultrasonic image recognition method based on redundant characteristic reduction. The method comprises the following steps of: extracting regions of interest from a medical ultrasonic image to be processed, and extracting characteristics from the regions of interest; analyzing principal components of the extracted characteristics, removing redundancy and irrelevant characteristic components, and determining independent and effect characteristics; and finally classifying the regions of interest by a classifier according to the independent and effect characteristics. The medical ultrasonic image is analyzed through a computer, the space and frequency domains are covered by the extracted image characteristics, the essential characteristics of the image are more comprehensively reflected, and the accurate classification is promoted, so that the method has high clinical practicality.

Description

technical field [0001] The present invention relates to the field of computerized medical image analysis, in particular to a method for automatic recognition of medical ultrasound images based on redundant feature reduction, through feature extraction and de-redundancy of pre-analyzed medical ultrasound image regions of interest (ROI), using a classifier Its features are classified after training and learning, which provides an important reference for clinical application. Background technique [0002] In the past 20 years, medical imaging technology has achieved rapid development. Ultrasound imaging, as an important branch, has been widely used in clinical diagnosis due to its advantages of low cost, real-time, non-invasive, non-ray radiation, high repeatability and sensitivity. , and become an important tool. Ultrasound imaging holds great promise for quantitative analysis, real-time diagnosis, and surgical planning. However, image defects such as speckle noise and artif...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/46
Inventor 丁明跃杨鑫王瑞尉迟明张旭明侯文广王龙会
Owner HUAZHONG UNIV OF SCI & TECH
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