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

Method for extracting image features based on multi-film CT image and 3DCNN network

A CT image and network extraction technology, applied in the field of image processing, can solve the problems of poor determination of judgment standards and high error rate, and achieve the effect of improving the accuracy of analysis

Inactive Publication Date: 2021-09-28
武汉幻视智能科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Based on the 2DCNN method, a single CT image is judged, and then the results of multiple CT images are logically judged. This kind of judgment method has a high error rate because the judgment standard is not easy to determine.

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
  • Method for extracting image features based on multi-film CT image and 3DCNN network
  • Method for extracting image features based on multi-film CT image and 3DCNN network
  • Method for extracting image features based on multi-film CT image and 3DCNN network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0035] Pathological CT images include images of various organs of the human body or animal body. In this application, lung CT images are used for illustration, and the processing of other CT images is deduced by analogy, and will not be described in detail.

[0036] A method of extracting image features based on a multi-membrane CT image and a 3DCNN network of the present application, such as figure 1 As shown, it includes image preprocessing, image segmentation, building multi-modal images, generating 3D images, using 3DCNN network to output classification features, and training based on multiple sets of classification features to obtain a classification network.

[0037] Preprocessing is to perform various morphological transformations on CT images, using at least one of the following methods: Gaussian blurring, binarization, erosion and dilation, and contour finding , seed filling, clearing border, labelling, filling holes, etc.

[0038] Filter out unqualified images in pa...

specific Embodiment 2

[0064] An embodiment of the present invention provides a terminal device for extracting image features based on a multi-membrane CT image and a 3DCNN network. The terminal device in this embodiment includes: a processor, a memory, and a device that is stored in the memory and can be used in the processor. A computer program running on the computer, such as a 3DCNN running program, and the processor implements the method in Embodiment 1 when executing the computer program.

[0065] Alternatively, when the processor executes the computer program, it realizes the functions of each module / unit in the above-mentioned device embodiments, for example, a feature calculation module and a discrimination module.

[0066] Exemplarily, the computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program ...

specific Embodiment 3

[0074] The integrated module / unit of the image feature extraction terminal equipment based on multi-membrane CT images and 3DCNN network can be stored in a computer-readable in the storage medium. Based on this understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps in the above-mentioned various method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk,...

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 extracting image features based on a multi-film CT image and a 3DCNN network, and the method comprises the steps: carrying out the preprocessing of a pathological CT image, obtaining an original image, carrying out the morphological transformation of the original image, extracting a pathological first appearance image, filtering the original image through the pathological first appearance image, obtaining a qualified image, carrying out the image segmentation of the qualified image, extracting a second pathology profile image, performing mask operation on the original image by using the second pathology profile image to obtain a local pathology image, inputting the original image, the second pathology profile image and the local pathology image as three-channel input images into the 3DCNN network, and extracting pathology image features. According to the method, the pathological region is segmented from the CT image, multiple modes are formed by the original image, the pathological region profile image and the pathological region image, multiple groups of 3D images are generated, comprehensive analysis is carried out, and the judgment accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for extracting image features based on multi-membrane CT images and a 3DCNN network. Background technique [0002] At present, CT scanning is a common detection method for pathological detection. The number of CT images is relatively large. The analysis based on CT images mainly relies on the naked eye observation and analysis of doctors. In this case, the judgment results of different doctors will be different. , and each doctor has to observe a large number of CT images during analysis, which consumes manpower and time. [0003] There are also many image processing and analysis methods, including image preprocessing, image recognition, etc. There are also many methods of image preprocessing and image recognition. The method based on deep learning is the mainstream method, which extracts image features for analysis, so as to realize image analysis. analysis pr...

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): G06T7/00G06T7/12G06T17/00G06K9/62
CPCG06T7/0012G06T7/12G06T17/00G06T2207/10081G06T2207/30004G06F18/214
Inventor 谭卫军
Owner 武汉幻视智能科技有限公司
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