APPARATUSES AND METHODS FOR NAVIGATION IN AND LOCAL SEGMENTATION EXTENSION OF ANATOMICAL TREELIKE STRUCTURES

• US 20190318484A1
• Filed: 04/13/2018
• Published: 10/17/2019
• Est. Priority Date: 04/12/2018
• Status: Active Grant

• Current Assignee: Veran Medical Technologies, Inc. (Olympus Corporation)
• Original Assignee: Veran Medical Technologies, Inc. (Olympus Corporation)
• Inventors: DOUGHERTY, Andrew, HUNTER, Mark
• Granted Patent: US 10,573,008 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 15/08 Volume rendering
• CPC Class Codes: G06T 17/005 Tree description, e.g. octree, quadtree
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/10132 Ultrasound image
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/20156 Automatic seed setting
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 2207/30064 Lung nodule
• CPC Class Codes: G06T 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 2207/30172 Centreline of tubular or elongated structure
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 2210/41 Medical
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/155 involving morphological operators
• CPC Class Codes: G06T 7/162 involving graph-based methods
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06T 7/215 : Motion-based segmentation
• CPC Class Codes: G06T 7/62 : of area, perimeter, diameter or volume
• CPC Class Codes: G06T 7/64 : of convexity or concavity
• CPC Class Codes: G06T 7/73 : using feature-based methods

Abstract

A method of extending a segmentation of an image using navigated image data from a navigation system includes tracking, with the navigation system, at least one of a traveled path and a position of an imaging device relative to an initial segmentation of 3D image data including an initial treelike structure. Navigated image data including image data including at least one 2D or 3D image is captured with the imaging device. A point from the navigated image data corresponding to a potential airway structure is obtained by the navigation system. The initial segmentation of 3D image data is extended by the navigation system using the point obtained from the navigated image data.

Claims

1. A method of extending a segmentation of an image using navigated image data from a navigation system, the method comprising:

tracking, with the navigation system, at least one of a traveled path and a position of an imaging device relative to an initial segmentation of 3D image data including an initial treelike structure;

capturing, with the imaging device, navigated image data comprising image data including at least one 2D or 3D image;

obtaining, by the navigation system, a point from the navigated image data corresponding to a potential airway structure; and

extending, by the navigation system, the initial segmentation of 3D image data using the point obtained from the navigated image data.

2. The method of claim 1, further comprising registering the navigated image data to the 3D image data.

3. The method of claim 1, further comprising constructing a 3D volume from the navigated image data.

4. The method of claim 3, wherein obtaining a point comprises automatically segmenting the constructed 3D volume to obtain a point from the navigated image data.

5. The method of claim 1, wherein obtaining a point comprises selecting the point using an I/O component of the navigation system.

6. The method of claim 1, wherein obtaining a point comprises obtaining a point cloud.

7. The method of claim 1, wherein extending the initial segmentation comprises:

extracting a region of interest from the 3D image data to create a sub-image;

extracting connected components based on spillage-constrained region growing using seed points from the sub-image;

pruning the extracted components to discard components not likely to be connected to the initial treelike structure and keep only candidate components likely to be a valid sub-tree of the initial treelike structure; and

connecting the candidate components to the initial treelike structure.

8. The method of claim 7, wherein extending the initial segmentation using the point obtained from the navigated image data comprises determining the region of interest in the 3D image data based on the point obtained from the navigated image data.

9. The method of claim 7, wherein extending the initial segmentation using the point obtained from the navigated image data further comprises performing the spillage-constrained region growing using the point obtained from the navigated image data as a seed point.

10. The method of claim 7, wherein pruning comprises:

discarding components based on whether they have genus zero and are relatively convex, including determining whether a ratio of a volume of the extracted component before morphological closing to a volume of the extracted component after morphological closing is greater than a threshold;

discarding or modifying components based on the components curving more than a threshold amount, including determining whether a dot product of a direction of the extracted component and a direction of a segment of the extracted component is below a threshold;

discarding components based on a shape analysis of the shape of the extracted component, including comparing shape analysis metrics including at least one of a minor axis length, an elongation, and an eccentricity of the extracted component to target metrics; and

discarding components based on a cylindrical score of the components, including determining a circle equivalent diameter of the extracted component.

11. The method of claim 10, wherein extending the initial segmentation using the point obtained from the navigated image data comprises relaxing the thresholds and analysis metrics in the pruning step based on the point obtained from the navigated image data.

12. The method of claim 7, wherein connecting comprises:

determining whether the candidate component has boundary voxels that are 4-connected to the initial segmentation and if so filling in voxels to fully connect the candidate component to the initial segmentation;

determining whether the radius of a candidate component is compatible with a terminal segment of the initial segmentation, and filling in voxels to connect the candidate component to the terminal segment if they are compatible;

determining if the candidate component includes a path of seed points to the initial segmentation, and if so identifying potential new growth based on a gradient ball method.

13. The method of claim 12, wherein extending the initial segmentation using the point obtained from the navigated image data comprises relaxing the determinations in the connecting step based on the point obtained from the navigated image data.

14. The method of claim 1, wherein capturing comprises capturing 2D ultrasound image data with the imaging device.

15. A method of extending a segmentation of an image using navigation data from a navigation system, the method comprising:

tracking, with the navigation system, at least one of a traveled path, a position, and a trajectory of a navigated instrument relative to an initial segmentation of 3D image data including an initial treelike structure to create navigation data; and

extending the initial segmentation of the 3D image data using the navigation data, wherein extending the initial segmentation comprises;

extracting a region of interest from the 3D image data to create a sub-image;

extracting connected components based on spillage-constrained region growing using seed points from the sub-image;

pruning the extracted components to discard components not likely to be connected to the initial treelike structure and keep only candidate components likely to be a valid sub-tree of the initial treelike structure; and

connecting the candidate components to the initial treelike structure.

16. The method of claim 15, wherein extending the initial segmentation further comprises determining a region of interest based on the navigation data.

17. The method of claim 15, wherein extending the initial segmentation further comprises performing the spillage-constrained region growing using the navigation data of the navigated instrument as seed points.

18. The method of claim 15, wherein pruning comprises:

discarding components based on whether they have genus zero and are relatively convex, including determining whether a ratio of a volume of the extracted component before morphological closing to a volume of the extracted component after morphological closing is greater than a threshold;

discarding or modifying components based on the components curving more than a threshold amount, including determining whether a dot product of a direction of the extracted component and a direction of a segment of the extracted component is below a threshold;

discarding components based on a shape analysis of the shape of the extracted component, including comparing shape analysis metrics including at least one of a minor axis length, an elongation, and an eccentricity of the extracted component to target metrics; and

discarding components based on a cylindrical score of the components, including determining a circle equivalent diameter of the extracted component.

19. The method of claim 18, wherein extending the initial segmentation comprises relaxing the thresholds and analysis metrics in the pruning step based on the navigation data.

20. The method of claim 15, wherein connecting comprises:

determining whether the candidate component has boundary voxels that are 4-connected to the initial segmentation and if so filling in voxels to fully connect the candidate component to the initial segmentation;

determining whether the radius of a candidate component is compatible with a terminal segment of the initial segmentation, and filling in voxels to connect the candidate component to the terminal segment if they are compatible;

determining if the candidate component includes a path of seed points to the initial segmentation, and if so identifying potential new growth based on a gradient ball method.

21. The method of claim 20, wherein extending the initial segmentation comprises relaxing the determinations in the connecting step based on the navigation data.