Skeletonization of medical images from incomplete and noisy voxel data

Patent metadata

Field	Value
Publication number	US-12456237-B2
Application number	US-202217687802-A
Country	US
Kind code	B2
Filing date	Mar 7, 2022
Priority date	Mar 7, 2022
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

A method for generating a skeleton in an image of a cavity of an organ of a body includes receiving a map of the cavity, the map including surface voxels and interior voxels. A subset of the interior voxels is generated, of candidate locations to be on the skeleton. The subset is pruned by removing outlier candidate locations. Using a geometrical model including a statistical model, the candidate locations remaining in the pruned subset are spatially compressed. The compressed candidate locations are connected to produce one or more centerlines of the skeleton. At least the skeleton is displayed to user.

First claim

The invention claimed is:

1. A method for generating a skeleton in an image of a cavity of an organ of a body, the method comprising:
receiving a map of the cavity, the map comprising surface voxels and interior voxels;
generating a subset of the interior voxels that are candidate locations to be on the skeleton;
pruning the subset by removing outlier candidate locations based on at least one of an angular dispersion of generative surface voxels or a variance in location of the candidate locations;
using a geometrical model comprising a statistical model, spatially compressing the candidate locations remaining in the pruned subset;
connecting the compressed candidate locations to produce one or more centerlines of the skeleton; and
displaying at least the skeleton to user.

2. The method according to claim 1 , wherein removing the outlier candidate locations comprises estimating the angular dispersion of generative surface voxels corresponding to a candidate location, and removing the candidate location upon finding that the angular dispersion is below a given minimal dispersion value.

3. The method according to claim 1 , wherein removing the outlier candidate locations comprises estimating the variance in a location of a candidate location, and removing the candidate location upon finding that the variance is above a given maximal location variance value.

4. The method according to claim 1 , wherein spatially compressing the candidate locations comprises, for at least some of the candidate locations:
estimating respective magnitudes and directions of displacement for the candidate locations;
displacing the candidate locations in the respective estimated directions by the respective estimated magnitudes; and
iteratively performing further statistical spatial compression of one or more of the candidate locations.

5. The method according to claim 4 , wherein estimating a magnitude of displacement for a candidate location comprises applying an optimization algorithm to calculate an average distance of the candidate location from its generating surface voxels.

6. The method according to claim 4 , wherein performing the further statistical spatial compression comprises defining a region of interest (ROI) comprising a subset of candidate locations for the further statistical spatial compression.

7. The method according to claim 6 , wherein a volume of the ROI monotonically decreases with iteration number.

8. The method according to claim 4 , wherein estimating a direction of displacement for a candidate location comprises:
estimating a spatial distribution of the candidate location using one of Principal Component Analysis (PCA) and regression analysis; and
estimating the direction based on the estimated spatial distribution.

9. The method according to claim 4 , wherein iteratively performing the further statistical spatial compression comprises stopping iterations of the further statistical spatial compression when a directionality measure of a spatial distribution of candidate locations exceeds a predefined value.

10. The method according to claim 9 , wherein the directionality measure is given as an eccentricity of an ellipsoid used as a region of interest (ROI) in the statistical spatial compression model.

11. The method according to claim 4 , wherein connecting the compressed candidate locations comprises finding a root location among the candidate locations and hierarchically connecting the candidate locations starting at the root.

12. A system for generating a skeleton in an image of a cavity of an organ of a body, the system comprising:
a memory configured to store a map of the cavity, the map comprising surface voxels and cavity voxels; and
a processor, which is configured to:
generate a subset of the interior voxels that are candidate locations to be on the skeleton;
prune the subset by removing outlier candidate locations based on at least one of an angular dispersion of generative surface voxels or a variance in location of the candidate locations;
using a geometrical model comprising a statistical model, spatially compress the candidate locations remaining in the pruned subset;
connect the compressed candidate locations to produce one or more centerlines of the skeleton; and
display at least the skeleton to user.

13. The system according to claim 12 , wherein the processor is configured to remove the outlier candidate locations by estimating the angular dispersion of generative surface voxels corresponding to a candidate location, and removing the candidate location upon finding that the angular dispersion is below a given minimal dispersion value.

14. The system according to claim 12 , wherein the processor is configured to remove the outlier candidate locations by estimating the variance in a location of a candidate location, and removing the candidate location upon finding that the variance is above a given maximal location variance value.

15. The system according to claim 12 , wherein the processor is configured to spatially compress the candidate locations by, for at least some of the candidate locations:
estimating respective magnitudes and directions of displacement for the candidate locations;
displacing the candidate locations in the respective estimated directions by the respective estimated magnitudes; and
iteratively performing further statistical spatial compression of one or more of the candidate locations.

16. The system according to claim 15 , wherein the processor is configured to estimate a magnitude of displacement for a candidate location by applying an optimization algorithm to calculate an average distance of the candidate location from its generating surface voxels.

17. The system according to claim 15 , wherein the processor is configured to perform the further statistical spatial compression by defining a region of interest (ROI) comprising a subset of candidate locations for the further statistical spatial compression.

18. The system according to claim 17 , wherein a volume of the ROI monotonically decreases with iteration number.

19. The system according to claim 15 , wherein the processor is configured to estimate a direction of displacement for a candidate location by:
estimating a spatial distribution of the candidate location using one of Principal Component Analysis (PCA) and regression analysis; and
estimating the direction based on the estimated spatial distribution.

20. The system according to claim 15 , wherein the processor is configured to iteratively perform the further statistical spatial compression by stopping iterations of the further statistical spatial compression when a directionality measure of a spatial distribution of candidate locations exceeds a predefined value.

21. The system according to claim 20 , wherein the directionality measure is given as an eccentricity of an ellipsoid used as a region of interest (ROI) in the statistical spatial compression model.

22. The system according to claim 15 , wherein the processor is configured to connect the compressed candidate locations by finding a root location among the candidate locations and hierarchically connecting the candidate locations starting at the root.

Assignees

• Biosense Webster Israel Ltd

Inventors

• Zaides Leonid
• Massarwa Fady
• Zar Lior

Classifications

• G06T12/30 Primary

  Image post-processing, e.g. metal artefact correction · CPC title

• G06T2211/424

  Iterative · CPC title

• G06V10/476

  using statistical shape modelling, e.g. point distribution models · CPC title

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/457

  by analysing connectivity, e.g. edge linking, connected component analysis or slices · CPC title