System and method for tree-model visualization for pulmonary embolism detection
View Patent ↗A system and method for tree-model visualization for detecting an abnormality in an anatomical tree structure are provided. The method comprises: fitting a tree-model to an anatomical tree structure; converting branches of the tree-model into first two-dimensional branch images; and arranging the first two-dimensional branch images in a hierarchical order to form a second two-dimensional image.
1. A method for tree-model visualization for detecting an abnormality in an anatomical tree structure, comprising:
fitting a tree-model to a three-dimensional (3D) image of a segmented anatomical tree structure, said fitting further comprising the steps of:
defining a root site for the anatomical tree structure;
computing a skeleton of the segmented anatomical tree structure;
forming a raw tree-structure using the skeleton;
eliminating false branches in the raw tree-structure;
smoothing and centering the skeleton; and
assigning direction vectors to points in the segmented anatomical tree structure;
converting each branch of the tree-model into a two-dimensional (2D) branch image; and
forming a 2D image that presents the 2D branch images.
2. The method of claim 1 , wherein the anatomical tree structure is segmented by using one of a thresholding and size-based labeling, line-filter based or structure tensor-based segmentation technique.
3. The method of claim 1 , wherein the tree-model is fit by using one of a vessel-based tracking technique, skeletonization, distance transform or level-set based tree-model computation technique.
4. The method of claim 1 , wherein the branches of the tree-model are converted into the 2D branch images by using one of an unrolling, side-by-side display, rotating structure or 2D maximum intensity projection technique.
5. The method of claim 1 , wherein the anatomical tree structure is one of a vessel tree or airway tree.
6. The method of claim 1 , wherein the anatomical tree structure is acquired using one of a computed tomography or magnetic resonance imaging technique.
7. The method of claim 1 , wherein the abnormality is one of a pulmonary embolism, airway stenosis or brain aneurysm.
8. A computer readable medium tangibly embodying a program of instructions executable by a processor to perform method steps for tree-model visualization to detect an abnormality in an anatomical tree structure, the method steps comprising:
fitting a tree-model to a three-dimensional (3D) image of a segmented anatomical tree structure, said fitting further comprising the steps of:
defining a root site for the anatomical tree structure;
computing a skeleton of the segmented anatomical tree structure;
forming a raw tree-structure using the skeleton;
eliminating false branches in the raw tree-structure;
smoothing and centering the skeleton; and
assigning direction vectors to points in the segmented anatomical tree structure;
converting each branch of the tree-model into a two-dimensional (2D) branch image; and
forming a 2D image that presents the 2D branch images.
9. The method of claim 8 , further comprising:
displaying the 2D image that presents the 2D branch images in a hierarchical order.
10. The method of claim 9 , further comprising:
observing branches in the 2D image that presents the 2D branch images in a hierarchical order.
11. The method of claim 10 , further comprising:
receiving a branch selection; and
obtaining an original axial view of image data of the branch or 3D rendering of the branch.
12. The method of claim 11 , wherein when the selected branch includes an abnormality, the abnormality is one of a pulmonary embolism, airway stenosis or brain aneurysm.
13. A system for tree-model visualization for detecting an abnormality in an anatomical tree structure, comprising:
a memory device for storing a program;
a processor in communication with the memory device, the processor operative with the program to:
fit a tree-model to a three-dimensional (3D) image of a segmented anatomical tree structure, the fitting further comprising the steps of:
define a root site for the anatomical tree structure;
compute a skeleton of the segmented anatomical tree structure;
form a raw tree-structure using the skeleton;
eliminate false branches in the raw tree-structure;
smooth and center the skeleton; and
assign direction vectors to points in the segmented anatomical tree structure;
convert each branch of the tree-model into a two-dimensional (2D) branch image; and
form a 2D image that presents the 2D branch images.
14. The system of claim 13 , wherein the anatomical tree structure is segmented by using one of a thresholding and size-based labeling, line-filter based or structure tensor-based segmentation technique.
15. The system of claim 13 , wherein the tree-model is fit by using one of a vessel-based tracking technique, skeletonization, distance transform or level-set based tree-model computation technique.
16. The system of claim 13 , wherein the branches of the tree-model are converted into the 2D branch images by using one of an unrolling, side-by-side display, rotating structure or 2D maximum intensity projection technique.
17. The system of claim 13 , wherein the anatomical tree structure is one of a vessel tree or airway tree.
18. The system of claim 13 , wherein the anatomical tree structure is acquired using one of a computed tomography or magnetic resonance imaging device.
19. The system of claim 13 , wherein the abnormality is one of a pulmonary embolism, airway stenosis or brain aneurysm.