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

Lung CT image classification method based on feature migration

A CT image and classification method technology, applied in the field of machine learning, can solve the problems of low model classification accuracy and efficiency, achieve the effects of improving classification accuracy and classification efficiency, reducing hyperparameter adjustments, and enriching image information

Pending Publication Date: 2020-09-25
ZHANG ZHOU HALTH VOCATIONAL COLLEGE
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to aim at the technical defects of the prior art, and provide a lung CT image classification method based on feature migration, so as to solve the technical problem of low accuracy and efficiency of model classification by conventional methods in the prior art

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
  • Lung CT image classification method based on feature migration
  • Lung CT image classification method based on feature migration
  • Lung CT image classification method based on feature migration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] The data set publicly available on the https: / / github.com / UCSD-AI4H / COVID-CT website is used for verification. The dataset is a collection of 760 articles about COVID-19 from medRxiv1 and bioRxiv2, and was released from January 19th to March 25th. Many of these articles report cases of COVID-19, and some also show CT scans in the reports, as well as descriptions of associated clinical presentations. Use PyMuPDF3 to extract the underlying structure information of PDF files in articles and locate any embedded graphics. The quality of the image (including resolution, size, etc.) is well preserved. In the end, 275 CT scans were obtained labeled as positive for COVID-19. image 3 Some examples of COVID-19 CT scans are shown.

[0063] Image filtering and contrast stretching results Figure 4 As shown, the left side is the original CT image, the middle is the image after adaptive noise filtering, and the right side is the image after contrast stretching:

[0064] Network ba...

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 lung CT image classification method based on feature migration. According to the technical scheme, the depth and the number of freezing layers of the pre-trained GoogLeNet network are determined through preprocessing, data enhancement and feature visualization of the CT image data, intrinsic information of the image is effectively extracted, and the classification accuracyand the classification efficiency of the model are improved. According to the invention, an adaptive CT image filtering algorithm is adopted to filter images acquired by different devices; contrast stretching is carried out on the CT image, image information is enriched, and image features are better extracted; a selection is provided for network depth determination of the model by using a feature map visualization technology, and hyper-parameter adjustment is reduced. By applying the method, the feature extraction problem of the label-free image can be solved, the problem of dimensionality disasters faced by high-dimensional image data classification is relieved, and the accuracy of image classification is remarkably improved.

Description

technical field [0001] The invention relates to the field of machine learning, in particular to a method for classifying lung CT images based on feature migration. Background technique [0002] Coronaviruses are a large class of viruses that exist widely in nature, and many strains of them are infectious to vertebrates including humans. Early detection, early diagnosis, and early isolation are important methods to control the spread of such diseases. Due to the insufficient speed of nucleic acid detection and the sensitivity of nucleic acid detection, false negatives may occur. Therefore, using computer vision to assist diagnosis of possible new coronary pneumonia screening CT images can effectively reduce the missed or misdiagnosed rate of new coronary pneumonia and alleviate the shortage of medical resources. [0003] At present, the new crown pneumonia detection method based on the deep learning framework and the new crown pneumonia detection method based on the transfer...

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): G06K9/42G06K9/46G06K9/62G06T7/00
CPCG06T7/0012G06T2207/10081G06V10/32G06V10/443G06F18/241
Inventor 杨东海陈小娟
Owner ZHANG ZHOU HALTH VOCATIONAL COLLEGE
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