Methods and systems for extracting blood vessel

1. A method for extracting a blood vessel implemented on at least one machine each of which has at least one processor and storage, the method comprising:

acquiring an image relating to a blood vessel, the image including multiple slices;

determining a region of interest in the image;

determining a centerline of the blood vessel;

establishing a blood vessel model; and

extracting the blood vessel from the region of interest based on the blood vessel model and the centerline of the blood vessel,

wherein the centerline of the blood vessel is determined according to one or more operations including:

retrieving training samples;

performing a classifier training based on the training samples to determine weak classifiers;

combining the weak classifiers to determine a strong classifier;

determining an enhanced image based on the strong classifier; and

determining the centerline of the blood vessel in the enhanced image based on a fast marching algorithm.

2. The method of claim 1 , wherein the determining a region of interest in the image comprises:

identifying slice information relating to the multiple slices of the image;

determining a slice range of the multiple slices corresponding to a sub-image based on the slice information;

determining the sub-image in the slice range;

acquiring a template based on the sub-image;

registering the sub-image based on the template to determine a registered result; and

identifying the region of interest based on the registered result.

3. The method of claim 1 , wherein the determining a region of interest in the image comprises performing machine learning.

4. The method of claim 1 , further comprising determining a seed point of the blood vessel including:

performing an enhancement operation on the image to obtain a second enhanced image;

determining gradients of grey values relating to the image to obtain a gradient image;

constructing a feature function of the blood vessel based on the second enhanced image and the gradient image; and

determining the seed point of the blood vessel based on the feature function of the blood vessel.

5. The method of claim 1 , wherein the training samples include a positive training sample and a negative training sample.

6. The method of claim 1 , the extracting the blood vessel based on the blood vessel model and the centerline of the blood vessel including:

determining a first segmentation result based on the centerline of the blood vessel;

determining a second segmentation result based on the first segmentation result;

assessing the second segmentation result based on a global condition to determine a third segmentation result;

determining a boundary condition relating to the blood vessel model;

assessing the third segmentation result based on the boundary condition to determine a fourth segmentation result; and

extracting the blood vessel based on the fourth segmentation result.

7. The method of claim 1 , wherein the blood vessel is extracted by a segmentation technique relating to an aneurysmal blood vessel, a segmentation technique relating to a blood vessel with a low dose contrast agent, or a segmentation technique relating to a calcific malformation blood vessel.

8. The method of claim 1 , wherein the extracting the blood vessel comprises:

performing a statistical analysis on gray values within the region of interest;

determining a growing parameter based on the statistical analysis;

determining a trunk of the blood vessel based on a fast marching algorithm; and

tracking a branch of the blood vessel by adjusting the growing parameter.

9. The method of claim 1 , further comprising extracting a specific portion of the blood vessel including:

determining a region including the specific portion of the blood vessel;

determining a first connected component in the region;

extracting a feature of the first connected component;

determining a connected component of the specific portion based on the feature of the first connected component; and

determining the specific portion of the blood vessel based on the connected component of the specific portion.

10. The method of claim 9 , wherein the feature of the first connected component includes a position, a size, or a shape of the first connected component.

11. The method of claim 9 , wherein the determining the specific portion of the blood vessel comprises performing a dilation operation or a region growing operation on the determined connected component of the specific portion.

12. A system for extracting a blood vessel, the system comprising:

at least one processor; and

executable instructions, the executable instructions being executed by the at least one processor, causing the at least one processor to implement a method, comprising:

acquiring an image relating to a blood vessel, the image including multiple slices;

determining a region of interest in the image;

determining a centerline of the blood vessel;

establishing a blood vessel model; and

extracting the blood vessel from the region of interest based on the blood vessel model and the centerline of the blood vessel,

wherein the centerline of the blood vessel is determined according to one or more operations including:

retrieving training samples;

performing a classifier training based on the training samples to determine weak classifiers;

combining the weak classifiers to determine a strong classifier;

determining an enhanced image based on the strong classifier; and

determining the centerline of the blood vessel in the enhanced image based on a fast marching algorithm.

13. The system of claim 12 , wherein the determining a region of interest in the image comprises:

identifying slice information relating to the slices of the image;

determining a slice range of the multiple slices corresponding to a sub-image based on the slice information;

determining the sub-image in the slice range;

acquiring a template based on the sub-image;

registering the sub-image based on the template to determine a registered result; and

identifying the region of interest based on the registered result.

14. The system of claim 12 , further comprising determining a seed point of the blood vessel including:

performing an enhancement operation on the image to obtain a second enhanced image;

determining gradients of grey values relating to the image to obtain a gradient image;

constructing a feature function of the blood vessel based on the second enhanced image and the gradient image; and

determining the seed point of the blood vessel based on the feature function of the blood vessel.

15. A non-transitory computer readable medium, comprising:

instructions being executed by at least one processor, causing the at least one processor to implement a method, comprising:

acquiring an image relating to a blood vessel, the image including multiple slices;

determining a region of interest in the image;

determining a centerline of the blood vessel;

establishing a blood vessel model; and

extracting the blood vessel from the region of interest based on the blood vessel model and the centerline of the blood vessel,

wherein the centerline of the blood vessel is determined according to one or more operations including:

retrieving training samples;

performing a classifier training based on the training samples to determine weak classifiers;

combining the weak classifiers to determine a strong classifier;

determining an enhanced image based on the strong classifier; and

determining the centerline of the blood vessel in the enhanced image based on a fast marching algorithm.