Image processing apparatus, image processing method and medical imaging device
View Patent ↗An image processing apparatus includes a storage unit, a slice image generating unit, a region extracting unit and a tubular structure extracting unit. The storage unit stores a volume image of a three-dimensional region of a subject. The slice image generating unit generates a plurality of slice images corresponding to a plurality of slices each substantially perpendicular to a predetermined reference axis from the volume image. The region extracting unit extracts a target region from the plurality of slice images. The tubular structure extracting unit detects an end point from the extracted region, and extracts a tubular structure based on the end point.
1. An image processing apparatus, comprising:
a memory configured to store a volume image of a three-dimensional region of a subject; and
processing circuitry configured to
generate a plurality of slice images corresponding to a plurality of slices each substantially perpendicular to a predetermined reference axis from the volume image,
extract a target region from the plurality of slice images,
detect an end point from the extracted region, and
extract a tubular structure based on the end point,
wherein the processing circuitry is further configured to extract the tubular structure through
obtaining a first fused part of a tree-shaped tubular structure by fusing a first tree-shaped tubular structure together with a first part of candidate data based on spatial continuity of the first tree-shaped tubular structure, the first tree-shaped tubular structure being obtained by using first region growing, and the candidate data being obtained by using grayscale morphological reconstruction,
after obtaining the first fused part of the tree-shaped tubular structure, recognizing a twig of the obtained first fused part of tree-shaped tubular structure,
performing second region growing by using the twig to obtain an extended branch, and
obtaining a second fused part of the tree-shaped tubular structure by fusing the extended branch together with a second part of the candidate data based on spatial continuity of the extended branch.
2. The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to
perform the first region growing on the basis of the volume image, based on a seed point and a first preset threshold, to obtain the first fused tree-shaped tubular structure,
perform the grayscale morphological reconstruction based on local extrema for each one of a series of images, to obtain the candidate data, and
perform the second region growing based on the volume image to obtain the extended branch based on a pixel point corresponding to the recognized twig as the branch seed point and a second preset threshold.
3. The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to combine the first fused part of the tree-shaped tubular structure with the second fused part of the tree-shaped tubular structure, to obtain the tree-shaped tubular structure.
4. The image processing apparatus according to claim 3 , wherein the processing circuitry is further configured to cyclically obtain a higher-branching level tree-shaped tubular structure of the subject based on a tubular structure obtained in a previous operation cycle as a lower-branching level tree-shaped tubular structure until a given condition is met.
5. The image processing apparatus according to claim 4 , wherein the given condition is that the processing circuitry cannot obtain an extended branch or the higher-branching level tree-shaped tubular structure obtained is the same as the extended branch.
6. The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to determine a branching level of a tubular structure at the recognized twig in the fused first part of the tree-shaped tubular structure and reserve the corresponding twig only when the branching level is lower than a predetermined branching level.
7. The image processing apparatus according to claim 6 , wherein the processing circuitry is further configured to determine the branching level of the tubular structure at the recognized twig based on a sectional area of a lumen at the twig.
8. The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to
extract a central line of a tube in the first fused part of the tree-shaped tubular structure; and
recognize an end point of the central line in a direction away from a trunk of the tree-shaped tubular structure.
9. The image processing apparatus according to claim 8 , wherein the processing circuitry is further configured to take a point on the central line which is adjacent to only one of the other points as the end point.
10. The image processing apparatus according to claim 2 , wherein the processing circuitry is further configured to compare a pixel value of the recognized branch seed point with a predetermined seed point threshold range and discard the branch seed point when the pixel value of which is beyond the predetermined seed point threshold range.
11. The image processing apparatus according to claim 2 , wherein the processing circuitry is further configured to use different preset thresholds in the first region growing performed to obtain the first fused part of the tree-shaped tubular structure and in the second region growing performed to obtain the extended branch.
12. The image processing apparatus according to claim 2 , wherein the first preset threshold or the second preset threshold comprises a region growing threshold and a leakage controlling threshold.
13. The image processing apparatus according to claim 1 , wherein
the processing circuitry is further configured to
perform binary image region growing based on the first part of the candidate data on the first tree-shaped tubular structure, and
perform binary image region growing based on the second part of the candidate data on the extended branch,
the binary image region growing performed on the first tree-shaped tubular structure comprises growing a portion of the candidate data spatially connected with each branch of the first tree-shaped tubular structure into a second tree-shaped tubular structure,
the binary image region growing performed on the extended branch comprises growing another portion of the candidate data spatially connected with the extended branch into a third tree-shaped tubular structure, and
the first tree-shaped tubular structure and the second tree-shaped tubular structure form a lower-branching level tree-shaped tubular structure, and the extended branch and the third tree-shaped tubular structure form a higher-branching level tree-shaped tubular structure.
14. The image processing apparatus according to claim 1 , wherein the processing circuitry is further configured to obtain a plurality of groups of candidate data of the tree-shaped tubular structure different in dimension respectively.
15. The image processing apparatus according to claim claim 14 , wherein the processing circuitry is configured to
fuse the first tree-shaped tubular structure with the candidate data large in dimension in the plurality of groups of candidate data, and
fuse the extended branch with the candidate data small in dimension in the plurality of groups of candidate data.
16. The image processing apparatus according to claim 1 , wherein the image is a medical image formed by data obtained via a medical diagnostic apparatus.
17. The image processing apparatus according to claim 1 , wherein the subject is an airway tree or blood vessels.
18. The image processing apparatus according to claim 8 , wherein the processing circuitry is further configured to edit the central line in accordance with an instruction of an operator.
19. The image processing apparatus according to claim 2 , wherein the processing circuitry is further configured to update at least one of the first preset threshold for the first region growing and a set value for the grayscale morphological reconstruction in accordance with an instruction of an operator.
20. An image processing method executed by an image processing apparatus wherein the image processing apparatus comprises a memory configured to store a volume image of a three-dimensional region of a subject, the image processing method comprising:
generating a plurality of slice images corresponding to a plurality of slices each substantially perpendicular to a predetermined reference axis from the volume image;
extracting a target region from the plurality of slice images;
detecting an end point from the extracted region; and
extracting a tubular structure based on the end point,
wherein the image processing method further comprises extracting the tubular structure through
obtaining a first fused part of a tree-shaped tubular structure by fusing a first tree-shaped tubular structure together with a first part of candidate data based on spatial continuity of the first tree-shaped tubular structure, the first tree-shaped tubular structure being obtained by using first region growing, and the candidate data being obtained by using grayscale morphological reconstruction,
after obtaining the first fused part of the tree-shaped tubular structure, recognizing a twig of the obtained first fused part of tree-shaped tubular structure,
performing second region growing by using the twig to obtain an extended branch, and
obtaining a second fused part of the tree-shaped tubular structure by fusing the extended branch together with a second part of the candidate data based on spatial continuity of the extended branch.
21. A medical imaging device, comprising:
a memory configured to store a volume image of a three-dimensional region of a subject; and
processing circuitry configured to
generate a plurality of slice images corresponding to a plurality of slices each substantially perpendicular to a predetermined reference axis from the volume image,
extract a target region from the plurality of slice images,
detect an end point from the extracted region, and
extract a tubular structure based on the end point,
wherein the processing circuitry is further configured to extract the tubular structure through
obtaining a first fused part of a tree-shaped tubular structure by fusing a first tree-shaped tubular structure together with a first part of candidate data based on spatial continuity of the first tree-shaped tubular structure, the first tree-shaped tubular structure being obtained by using first region growing, and the candidate data being obtained by using grayscale morphological reconstruction,
after obtaining the first fused part of the tree-shaped tubular structure, recognizing a twig of the obtained first fused part of tree-shaped tubular structure,
performing second region growing by using the twig to obtain an extended branch, and
obtaining a second fused part of the tree-shaped tubular structure by fusing the extended branch together with a second part of the candidate data based on spatial continuity of the extended branch.
22. The medical imaging device according to claim 21 is a computer tomography device or a magnetic resonance imaging device.