Method and apparatus for extracting trachea from chest CT images
A CT image and trachea technology, which is applied in the field of extracting trachea from chest CT images, can solve the problems of slow running time, failure to use trachea shape and size information, and easy leakage of lung parenchyma in segmentation results, so as to achieve the effect of avoiding leakage and robust extraction
Active Publication Date: 2017-10-03
SHANGHAI UNITED IMAGING HEALTHCARE
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] At present, many methods for automatic extraction of trachea are based on region growth. This type of method does not use the shape and size information of the trachea, and its disadvantage is that the segmentation results are easily leaked to the lung parenchyma.
The morphology-based method uses a series of filters to process the image to select the region that may belong to the trachea, and finally obtains the segmentation result through the reconstruction method. The segmentation effect of this method is better than that of the region growth method, but the cost is the running time. Slower and less effective at extracting the distal trachea
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] In order to make the above objects, features and advantages of the present invention more comprehensible, specific implementations of the present invention will be described in detail below in conjunction with the accompanying drawings.
[0031] In the following description, many specific details are set forth in order to fully understand the present invention, but the present invention can also be implemented in other ways than those described here, so the present invention is not limited by the specific embodiments disclosed below.
[0032] The repeated branches of the bronchi in the lungs form a dendritic structure, so it is called the bronchial tree (Bronchail Tree). The bronchial tree can include levels 1-13 according to its branching level. The main goal of lung trachea extraction is to reconstruct the pulmonary peripheral bronchial tree as accurately and as comprehensively as possible. Leakage is one of the major challenges in bronchial tree reconstruction today...
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
Login to View More Abstract
The present invention provides a method and device for extracting the trachea from chest CT images. The method includes the following steps: extracting a low-level trachea from the chest CT image; based on the low-level trachea, extracting a terminal trachea using a three-dimensional reconstruction method based on an energy function; and fusing the low-level trachea and the terminal trachea to obtain a tracheal extraction result. Compared with the existing technology, the method and device for extracting trachea from chest CT images of the present invention fully consider the differences in structure and grayscale characteristics of low-level trachea and terminal trachea, and use two different strategies to extract different levels of trachea. trachea.
Description
technical field [0001] The present invention mainly relates to processing of computerized tomography (Computerized Tomography, CT) images, in particular to a method and device for extracting trachea from chest CT images. Background technique [0002] Computerized Tomography (abbreviated as CT) is a radiological diagnostic technique based on the fact that different substances have different attenuation properties for rays. CT irradiates the measured object with radiation from various directions, measures the intensity of the radiation passing through the object, and calculates the linear attenuation coefficient of each point inside the object for the radiation through a certain reconstruction algorithm, so as to obtain the radiological diagnosis of the tomographic image of the measured object technology. The tomographic image reconstructed by CT has the advantages of no image overlap, high density and high spatial resolution, so it has attracted much attention as a medical n...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/11
CPCG06T7/0012G06T2207/30101G06T2200/04G06T2207/10072G06T2207/20156G06T2207/20161G06T2207/30061G06T7/143G06T7/155G06T7/187G06T7/136G06T7/11
Inventor 王立龙
Owner SHANGHAI UNITED IMAGING HEALTHCARE