Three-dimensional image segmentation method based on random walk and level set
A three-dimensional image and random walk technology, applied in the field of image processing, can solve the problems of low segmentation efficiency and large amount of calculation, and achieve the effect of improving accuracy, efficiency, segmentation speed and accuracy
Active Publication Date: 2019-09-20
南京景三医疗科技有限公司
View PDF8 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and provides a three-dimensional image segmentation method based on random walk and level set, which solves the problems in the prior art. The 3D segmentation method has a large amount of calculation and the technical problems of low segmentation efficiency
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
[0081] Attached below figure 1 To illustrate the specific process of the present invention:
[0082] Step 1, acquiring carotid MRI image sequences.
[0083] The image sequence can be bright blood sequence such as 2D TOF (time of flight), 3D TOF, or black blood sequence such as T1, T2, T1+ and PD. In the present invention, a T1+ sequence is taken as an example to illustrate the specific process of the three-dimensional segmentation of the lumen.
[0084] Step 2, manually specify a rectangular region of interest (ROI) within the slice
[0085] Browse through the 3D carotid artery image sequence, and select a slice with the best blood vessel quality. The selection criteria are generally healthy blood vessels with less artifacts and no plaque or relatively few plaques. A slice with the best blood vessel quality is as follows: figure 1 a) as shown.
[0086] Then, a rectangular region of interest (ROI) is selected in the slice through manual interaction. The rectangular region m...
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 invention discloses a three-dimensional image segmentation method based on random walk and a level set. The method comprises the following steps: obtaining a three-dimensional image sequence; selecting a two-dimensional slice from the three-dimensional image sequence, and defining a region of interest on the two-dimensional slice; carrying out super-pixel processing on the region of interest to obtain a plurality of super-pixel segmentation regions, and taking a pixel mean value in each super-pixel segmentation region as a pixel value of the super-pixel region to obtain a corresponding super-pixel uniform filling region; according to the superpixel uniform filling region, segmenting the region of interest by using a random walk algorithm to obtain a two-dimensional segmentation result in the slice; and transmitting the obtained two-dimensional segmentation result to other slices based on a level set method to obtain a segmentation result of the three-dimensional image. According to the method, two-dimensional slice segmentation is carried out by utilizing random walk based on superpixels, and then a segmented result is transmitted to other slices by utilizing a local binary fitting level set method, so that three-dimensional segmentation is accurately and quickly completed.
Description
technical field [0001] The invention belongs to the technical field of image processing, and relates to a carotid lumen image segmentation method, in particular to a three-dimensional image segmentation method based on superpixel random walk and local binary fitting level set. Background technique [0002] Image segmentation technology is an important research topic in the field of image processing, such as the segmentation of carotid artery image lumen applied in the medical field. This segmentation is an important step in the diagnosis of atherosclerotic plaque. An important basis for block segmentation and mechanical simulation analysis. [0003] It is very difficult to achieve fully automatic and accurate segmentation of the lumen, especially for carotid artery images of black blood techniques such as T1 images, T2 images, and proton density (PD) images. At present, some semi-automatic segmentation methods are mainly used in clinical and academic research. Semi-automat...
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 IPC IPC(8): G06T7/11G06T3/40
CPCG06T7/11G06T3/4053G06T2207/10012
Inventor 刘泽安滕忠照
Owner 南京景三医疗科技有限公司