CT image target lung segment identification method based on pulmonary artery tree grading

A CT image and recognition method technology, applied in the field of image recognition, can solve problems such as insufficient bronchial segmentation, difficult division of bronchi into sub-pulmonary segments, and insufficient integration

Pending Publication Date: 2022-04-12
FUZHOU UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current methods still have the following limitations: (1) they are easily affected by the CT imaging quality and the patient's disease, resulting in insufficient bronchial segmentation and poor lung segment segmentation; (2) at the same time, it is difficult to extract the bronchi to the subsegment level Carry out sub-segment division; (3) The anatomical structure of the lung is complex and changeable, often considering the local anatomical features, ignoring the overall structure of the lung, and not fully combining the corresponding relationship with other anatomical structures

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
  • CT image target lung segment identification method based on pulmonary artery tree grading
  • CT image target lung segment identification method based on pulmonary artery tree grading
  • CT image target lung segment identification method based on pulmonary artery tree grading

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0035] Please refer to figure 1 , the present invention provides a CT image target lung segment recognition method based on pulmonary artery tree classification, comprising the following steps:

[0036] Step S1: obtain CT image data, and reconstruct lung structures, including pulmonary nodules, bronchi, pulmonary artery tree and lung lobes;

[0037] Step S2: extract initial centerline to pulmonary artery tree, and construct complete and continuous topological tree by endpoint detector and trajectory extractor;

[0038] In this embodiment, step S2 is specifically as follows:

[0039] Step S21: The distance map is obtained by performing distance transformation on the three-dimensional artery tree, and iteratively traces from the potential end point to the root node through the fast step method to obtain branch trajectories. That is, to obtain the initi...

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 CT image target lung segment identification method based on pulmonary artery tree grading, and the method comprises the following steps: S1, obtaining CT image data, and reconstructing lung structures, including pulmonary nodules, bronchus, pulmonary artery trees and lung lobes; s2, extracting an initial center line from the pulmonary artery tree, and constructing a complete and continuous topological tree through an endpoint detector and a trajectory extractor; s3, according to the topological tree, combining lung lobe and bronchus prior knowledge for constraint, and determining 18 artery segment subtrees; s4, determining a targeted artery branch; s5, calculating the nearest arterial segment subtree for each voxel point on the lung lobe, and attributing the nearest arterial segment subtree to the corresponding lung segment; similarly, according to the distance relationship, calculating the dominated area of the target artery branch in the associated lung segment, and determining the target lung segment. According to the method, the relevance between the lung anatomical structures is fully considered, grading labeling of arteries is achieved, targeted artery branches are accurately determined, and then the lung segment is divided and the target lung segment is determined.

Description

technical field [0001] The invention relates to the field of image recognition, and relates to a method for recognizing a target lung segment of a CT image based on pulmonary artery tree classification. Background technique [0002] The confirmation of the target lung segment is based on extracting the lung parenchyma, dividing the corresponding lung segment according to the classification of the pulmonary bronchi, and then determining the minimum resection range according to the resection margin of the lesion. The target lung segment is not only a single lung segment, but also the combined lung segment, combined sub-segment, and combined lung segment and sub-segment. However, due to the partial volume effect of CT imaging, bronchial resolution is limited, and it is difficult to obtain complete subsegmental bronchi. Given that subsegmental bronchi are accompanied by pulmonary arteries at corresponding levels, and arteries have better visibility and characteristics on CT ima...

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): G06T7/00G06T7/11
Inventor 潘林郑耀湧黄立勤郑绍华傅荣达张桢沈志强
Owner FUZHOU 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