Lung airway tree segmentation method for tracheal wall notch plugging under sphere-like area constraint

A region-constrained, sphere-like technology, applied in the field of medical image processing, can solve problems such as extraction and leakage of small airways, and achieve the effect of reducing difficulty and good segmentation of the environment

Active Publication Date: 2019-09-06
SHANDONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the unique leakage problem and small airway extraction problem in the field of pulmonary airway tree segmentation, the main reason for the difficulty of pulmonary airway tree segmentation is considered that the gap in the low-brightness tracheal wall is considered

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 airway tree segmentation method for tracheal wall notch plugging under sphere-like area constraint
  • Lung airway tree segmentation method for tracheal wall notch plugging under sphere-like area constraint
  • Lung airway tree segmentation method for tracheal wall notch plugging under sphere-like area constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. The present invention realizes a lung airway tree segmentation method for blocking the gap in the trachea wall under the constraint of a spheroidal region, which mainly includes the following steps:

[0018] Step 1: Read in the chest CT image and set the initial seed point in the main trachea;

[0019] Step 2: Detect and mark the connected domain, and push the single-connected seed point set in the seed point retention matrix into the stack in turn. The stack is used to clarify the order of independent segmentation of various sub-point sets, expressed as:

[0020] P Label (P)=[P area (k),k],k=1,2,3,...,n.

[0021] Among them, P is the seed point retention matrix, k is the sorting value and tag value in the stack, n is the maximum value of k in the stack, P area (k) is a set of singly connected seed points labeled k, satisfying the f...

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 lung airway tree segmentation method for tracheal wall notch plugging under sphere-like area constraint, and belongs to the field of image processing. In order to solve the problem of leakage caused by a low-brightness trachea wall notch in lung airway tree segmentation, the invention provides the lung airway tree segmentation method for plugging the trachea wall notch under sphere-like area constraint. The method comprises the following steps: (1) establishing a sphere-like area constraint model; (2) carrying out intra-area segmentation and parameter self-adaptive adjustment; and (3) plugging a trachea wall notch. The difficulty of leakage detection is reduced due to the constraint of the sphere-like area on segmentation, all parameters can be adjusted easily ina self-adaptive mode in the constraint area, and conditions are created for trachea wall notch plugging through the spheroid area constraint; tracheal wall notch plugging can effectively position andplug a tiny low-brightness tracheal wall notch, and a good segmentation environment is created for extraction of the three-dimensional structure of the pulmonary airway tree.

Description

technical field [0001] The invention belongs to the field of medical image processing, in particular to lung airway tree segmentation based on chest CT images. Background technique [0002] An accurate three-dimensional pulmonary airway tree model constructed based on chest 3D-CT image data is of great significance for the auxiliary diagnosis of lung diseases. In addition to the common problems in medical image segmentation, the research on lung airway tree segmentation algorithm also needs to face two unique problems, namely, the leakage problem and the small airway extraction problem. The root of the two problems is that under the influence of partial volume effect and noise, there are low-brightness tracheal wall gaps on the high-brightness tracheal wall in CT images, such as figure 1 As shown, it is difficult for the tracheal wall to perfectly isolate the airway and lung parenchyma, resulting in the segmentation process being mistakenly extended from the airway to the l...

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): G06T7/11G06T7/187G06T7/136
CPCG06T7/11G06T7/187G06T7/136G06T2207/10081G06T2207/30061
Inventor 崔文韬韩贺薛鹏纪慧中熊文硕董恩清张德敬孙祺高翔常树旺
Owner SHANDONG UNIV
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