Image segmentation apparatus, medical image device and image segmentation method

1. An image segmentation apparatus for segmenting an object having a tree-shaped tubular structure from a volume image consisting of a series of images photographed on the basis of slices, comprising:

processing circuitry configured to

perform region growing on the basis of the volume image, based on a seed point and a preset threshold, to obtain at least one part of the tree-shaped tubular structure;

determine whether or not the at least one part of the obtained tree-shaped tubular structure is correct;

change, when determining that the at least one part of the tree-shaped tubular structure is incorrect and a given condition is not met, the preset threshold to re-perform the region growing until the given condition is met; and

perform, when determining that the at least one part of the tree-shaped tubular structure is correct and the given condition is met, centricity-limited region growing on the basis of the volume image, based on the seed point and the preset threshold, to obtain at least one part of the tree-shaped tubular structure.

2. The image segmentation apparatus according to claim 1 , wherein the given condition is that the number of times of performing the region growing reaches a given number, or the preset threshold exceeds a preset range.

3. The image segmentation apparatus according to claim 1 , wherein the processing circuitry is further configured to determine whether or not the given condition is met according to a pixel percentage of the at least one part of the tree-shaped tubular structure grown by the processing circuitry.

4. The image segmentation apparatus according to claim 1 , wherein the processing circuitry is further configured to:

perform morphological reconstruction based on local extrema for each one of the series of images, to obtain candidate data capable of constructing a second part of the tree-shaped tubular structure; and

fuse the at least one part of the obtained tree-shaped tubular structure with the second part of the tree-shaped tubular structure constructed by at least one part of the obtained candidate data to obtain the tree-shaped tubular structure of the object.

5. The image segmentation apparatus according to claim 4 , wherein the processing circuitry is further configured to perform simple growing of the at least one part of the tree-shaped tubular structure based on the candidate data, the simple growing comprising growing the part of the candidate data spatially connected with each branch of the at least one part of the tree-shaped tubular structure into the second part of the tree-shaped tubular structure.

6. The image segmentation apparatus according to claim 4 , wherein the processing circuitry is further configured to:

perform grayscale morphological reconstruction for each one of the series of images, to obtain a marked image with the local extrema in the original image identifiable;

compare the marked image with a second preset threshold and reserve merely a part of the marked image with a value higher than the second preset threshold; and

extract spatial coordinates of the part and the corresponding pixel values in the original image as the candidate data.

7. The image segmentation apparatus according to claim 6 , wherein the processing circuitry is further configured to change the second preset threshold so that a ratio of a characteristic factor of the obtained tree-shaped tubular structure to a characteristic factor of the at least part of the obtained tree-shaped tubular structure becomes a given ratio.

8. The image segmentation apparatus according to claim 7 , wherein the processing circuitry is further configured to compare the pixel values corresponding to the at least one part of the tree-shaped tubular structure and the second part of the tree-shaped tubular structure with a preset range of pixel value of the object, to remove the part of the tree-shaped tubular structure the pixel values of which are beyond the preset range of pixel value.

9. The image segmentation apparatus according to claim 8 , wherein the processing circuitry is further configured to change the preset range and the second preset threshold, so that the ratio of the characteristic factors becomes the given ratio.

10. The image segmentation apparatus according to claim 7 , wherein the characteristic factor is at least one of a pixel number, a volume, a shape, and a size of the tree-shaped tubular structure.

11. The image segmentation apparatus according to claim 7 , wherein the object is an airway tree, the characteristic factor is a pixel number of the airway tree, and the given ratio is in the range of 1.1 to 1.25.

12. The image segmentation apparatus according to claim 1 , wherein the image is a medical image formed by data obtained by a medical diagnostic apparatus.

13. The image segmentation apparatus according to claim 1 , wherein the object is an airway tree, a blood vessel or a skeleton.

14. A medical image device, comprising an image segmentation apparatus for segmenting an object having a tree-shaped tubular structure from a volume image consisting of a series of images photographed on the basis of slices, wherein the image segmentation apparatus includes:

processing circuitry configured to

perform region growing on the basis of the volume image, based on a seed point and a preset threshold, to obtain at least one part of the tree-shaped tubular structure;

determine whether or not the at least one part of the obtained tree-shaped tubular structure is correct; and

change, when determining that the at least one part of the tree-shaped tubular structure is incorrect, the preset threshold to re-perform the region growing until a given condition is met.

15. The medical image device according to claim 14 , wherein the medical image device is a computer tomography device or a magnetic resonance imaging device.

16. The medical device of claim 14 , wherein the processing circuitry is further configured to

change, when determining that the at least one part of the tree-shaped tubular structure is incorrect and the given condition is not met, the preset threshold to re-perform the region growing until the given condition is met; and

perform, when determining that the at least one part of the tree-shaped tubular structure is correct and the given condition is met, centricity-limited region growing on the basis of the volume image, based on the seed point and the preset threshold, to obtain at least one part of the tree-shaped tubular structure.

17. An image segmentation method for segmenting an object having a tree-shaped tubular structure from a volume image consisting of a series of images photographed on the basis of slices, comprising:

performing region growing on the basis of the volume image, based on a seed point and a preset threshold, to obtain at least one part of the tree-shaped tubular structure;

determining whether or not the at least one part of the obtained tree-shaped tubular structure is correct;

changing, when determining that the at least one part of the tree-shaped tubular structure is incorrect and a given condition is not met, the preset threshold to re-perform the region growing until a given condition is met; and

performing, when determining that the at least one part of the tree-shaped tubular structure is correct and the given condition is met, centricity-limited region growing on the basis of the volume image, based on the seed point and the preset threshold, to obtain at least one part of the tree-shaped tubular structure.