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

Ultrasound diagnosis method of knee joint disorders based on deep learning multi-channel and image embedding method

A deep learning and ultrasound diagnosis technology, applied in medical images, medical automated diagnosis, informatics, etc., can solve the problems of staying in traditional algorithms, and achieve accurate ultrasound diagnosis, convenient life, simple and efficient methods of segmentation and classification and identification.

Active Publication Date: 2021-11-02
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the processing of knee ultrasound images still stays on the traditional algorithm. The deep learning algorithm, which is widely used in image processing in various fields, has not been effectively applied to ultrasound images, so its application and knee ultrasound Images are necessary and have important application context

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
  • Ultrasound diagnosis method of knee joint disorders based on deep learning multi-channel and image embedding method
  • Ultrasound diagnosis method of knee joint disorders based on deep learning multi-channel and image embedding method
  • Ultrasound diagnosis method of knee joint disorders based on deep learning multi-channel and image embedding method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] see Figure 1-Figure 10 , a method for ultrasonic diagnosis of knee joint disorders based on deep learning multi-channel and map embedding method provided in this embodiment, comprising the following steps:

[0025] (1) The Snakes algorithm is used to preprocess the image, and the background area similar to the target area is eliminated. The Snakes model algorithm needs to randomly or manually define a controllable and deformable initial contour curve, and the area inside the contour line is used as the segmentation area. Taking the contour line as the parameter curve, by defining and controlling the energy function of the parameter curve, taking its energy function as the objective function and minimizing it, the contour curve is deformed, and the closed curve with the minimum energy value after the final deformation is is the final stop profile. Using the Snakes model algorithm, the outermost contour curve is used as the initialization curve, with the goal of minimiz...

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 a method for ultrasonic diagnosis of knee joint disease based on deep learning multi-channel and image embedding method, which includes the following steps: using snake algorithm to preprocess the effusion area in the knee joint ultrasonic image, and then input it into the defined Semantic segmentation is realized in the network model of Resnet; On the basis of Resnet network structure, utilize the image embedding method of secondary training to train the knee joint ultrasound image in data set, finally utilize the experiment of segmentation network and classification network to verify; The present invention adopts The idea of ​​multi-channel superposition and image embedding method is used to segment and train the knee joint ultrasound images, and the disease category can be distinguished according to whether the effusion area is accompanied by synovial thickening in the ultrasound images of different knee joint diseases, avoiding the problem of knee joint ultrasound images. The judgment depends entirely on the doctor's naked eyes and personal judgment, eliminating the problems of subjectivity and human error. The entire segmentation and classification recognition method is simple and efficient, and the diagnosis is accurate.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to an ultrasonic diagnosis method for knee joint disorders based on deep learning multi-channel and image embedding method. Background technique [0002] The knee joint is the most complex joint in the human body, and people of all ages are susceptible to infection or injury. Common knee-related diseases include synovitis, synovial thickening, and cysts. Medical images are a common and important method for knee joint diagnosis at present. The liquid area of ​​the lesion appears as a darker black area in the image. Doctors use this area as the main basis for judgment. At the same time, the accuracy of the area demarcation also affects The doctor's correct diagnosis. At present, the diagnosis of common diseases of the knee completely depends on the doctor's naked eyes and personal judgment, which wastes a lot of manpower and material resources, and has certain subjectivity and...

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): G06T7/00G06T7/11G16H30/40G16H50/20
CPCG06T7/0012G06T2207/10132G06T2207/20081G06T2207/20084G06T2207/30008G06T7/11G16H30/40G16H50/20
Inventor 隆志力李祚华牛谨张小兵
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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