Pulmonary nodule detection method for multi-scale enhancement filter and 3D features

A detection method and multi-scale technology, applied in image enhancement, instrument, character and pattern recognition, etc., can solve the problem of high false positives, affecting the accuracy of lung nodule detection, and achieve the effect of reducing false positives

Active Publication Date: 2017-11-24
TAIYUAN UNIV OF TECH
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the computer CAD system of pulmonary nodules, because the density and CT value of blood vessels in CT images are similar to those of nodules, there are often high false positives, which affect the detection accuracy of pulmonary nodules.

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
  • Pulmonary nodule detection method for multi-scale enhancement filter and 3D features
  • Pulmonary nodule detection method for multi-scale enhancement filter and 3D features
  • Pulmonary nodule detection method for multi-scale enhancement filter and 3D features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] The present invention will be described in detail below in conjunction with specific embodiments.

[0074] refer to figure 1 , the implementation process of the inventive method is as follows:

[0075] (1) Nodule and blood vessel model

[0076] Since nodules and blood vessels exhibit spherical and tubular characteristics in shape, they can be approximated as a sphere and a cylinder, respectively, in a 3D image. To this end, first construct three ideal models, which respectively represent points (spheres), lines (columns), and surfaces in three-dimensional space. The expressions are as follows, and the schematic diagrams of the ideal spherical model and cylindrical model are shown figure 2 shown.

[0077]

[0078] The Hessian matrix is ​​a square matrix composed of the second-order partial derivatives of a multivariate function, which describes the local curvature of the function. In the ideal sphere model, the expression of the Hessian matrix H corresponding to ...

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 present invention discloses a pulmonary nodule detection method for a multi-scale enhancement filter and 3D features. The method comprises: constructing a tubercle and blood vessel ideal model, and constructing an enhancement filter to perform enhancement of tubercle images and blood vessel images in a lung 3D image; extracting a suspected lung tubercle image, and extracting the SNOAH features thereof; and finally, employing the SVM classifiers with different kernel functions to perform classification of features. An experiment result shows that a pulmonary nodule feature descriptor-surface normal direction angle histogram is effective so as to distinguish other images such as tubercle images and blood vessel and effectively reduce the fake positive of a detection result.

Description

technical field [0001] The invention relates to the detection of pulmonary nodule images, in particular to a method for realizing pulmonary nodule detection by using a multi-scale enhancement filter and a histogram of surface normal direction angles. Background technique [0002] In the computer CAD system of pulmonary nodules, because the density of blood vessels and CT values ​​in CT images are similar to those of nodules, there are often high false positives, which affects the detection accuracy of pulmonary nodules. In the present invention, an automatic lung nodule detection method based on multi-scale enhancement filters and 3D shape features is proposed. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a lung nodule detection method using multi-scale enhancement filters and 3D features in view of the deficiencies in the prior art. [0004] Technical scheme of the present invention is as follows: [0005] ...

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): G06T7/00G06T5/00G06K9/62G06K9/46
CPCG06T5/002G06T7/0012G06T2207/30064G06T2207/10081G06V10/44G06F18/2411G06F18/214
Inventor 赵涓涓廖晓磊强彦强薇
Owner TAIYUAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap