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

YOLO convolutional neural network-based cholelithiasis CT medical image data enhancement method

A convolutional neural network and medical image technology, applied in the field of rapid recognition of cholelithiasis CT medical images, can solve problems such as efficiency issues, and achieve the effect of improving the accuracy rate and rapid diagnosis process

Pending Publication Date: 2019-05-28
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although network performance has been improved, but with it comes the problem of efficiency

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
  • YOLO convolutional neural network-based cholelithiasis CT medical image data enhancement method
  • YOLO convolutional neural network-based cholelithiasis CT medical image data enhancement method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The technical solutions of the present invention will be further described below in conjunction with specific embodiments.

[0034] The theme scheme of this system mainly embodies the basic idea of ​​intelligent diagnosis, fast and high accuracy. like figure 1 As shown, the fast recognition method of cholelithiasis CT medical images based on YOLO convolutional neural network includes the following modules:

[0035] 1) input component, for inputting cholelithiasis CT medical image dataset;

[0036] 2) analysis component, for processing described cholelithiasis CT medical image, generates a plurality of training samples;

[0037] 3) The training component uses the training samples to perform deep learning-based cholelithiasis CT medical image recognition training to generate a cholelithiasis CT medical image rapid recognition model;

[0038] 4) The detection component uses the newly constructed CT medical image verification set of gallstone disease to verify the traine...

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 relates to a YOLO convolutional neural network-based cholelithiasis CT medical image data enhancement method. The method belongs to the technical field of image processing, medical big data and deep learning. The method comprises the steps of 1) collecting medical images and constructing a training set; 2) processing the image in the training set to generate a required training sample; 3) performing deep learning-based medical image recognition training by using the training sample, and generating a trained medical image rapid recognition model; 4) collecting a new medical image,and constructing a verification set; 5) verifying the model by utilizing images in the verification set. According to the method, the problem of redundancy of a medical image data set in current deeplearning is avoided. The rapid identification of medical images is realized, and the identification speed is high.

Description

technical field [0001] The invention relates to a method for fast recognition of cholelithiasis CT medical images based on YOLO convolutional neural network, which belongs to the field of artificial intelligence Background technique [0002] Since the concept of convolution was proposed in 2012, convolutional neural network (referred to as CNN) has been widely used in image classification, image segmentation, target detection and other fields. [11] , especially with the rise and development of the smart medical field, the types of diagnosed diseases have increased, and the complexity of pathological relationships between diseases has increased, and the application requirements for convolutional neural networks have become more and more stringent. So big cows from all walks of life have proposed CNN networks with better performance, such as VGG, GoogLeNet, ResNet, DenseNet [12-15] Wait. Due to the nature of the neural network, in order to obtain better performance, the numb...

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): G16H30/20G16H50/70
Inventor 庞善臣王硕于世行谢鹏飞
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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