Region-growing algorithm

• US 9,836,850 B2
• Filed: 02/21/2017
• Issued: 12/05/2017
• Est. Priority Date: 02/01/2010
• Status: Active Grant

• Current Assignee: Covidien LP (Medtronic Plc)
• Original Assignee: Covidien LP (Medtronic Plc)
• Inventors: Averbuch, Dorian, Kreinin, Yuri
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US15/438,134
• Publication Number:
  US 20170161908A1
• Time in Patent Office: 287 Days
• Field of Search: 382100, 382103, 382106-107, 382128-134, 382154-155, 382168, 382172-173, 382181, 382199, 382224, 382254, 382276, 382305, 382312, 378 4, 378 21, 600415, 600425, 600432, 600109, 600532
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/20156 Automatic seed setting
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06V 10/267 by performing operations on regions, e.g. growing, shrinking or watersheds

Abstract

A technique for automatically generating a virtual model of a branched structure using as an input a plurality of images taken of the branched structure. The technique employs an algorithm that avoids inaccuracies associated with sub-optimal threshold settings by “patching” holes or leaks created due to the inherent inconsistencies with imaging technology. By “patching” the holes, the algorithm may continue to run using a more sensitive threshold value than was previously possible.

Claims

1. A method for performing a region growing comprising:

identifying a first seed voxel;

comparing a Hounsfield unit value of voxels adjacent to the first seed voxel with a threshold Hounsfield unit value for air;

identifying the adjacent voxels as seed voxels, when each of the adjacent voxels meets or exceeds the threshold Hounsfield unit value for air;

determining whether the identified adjacent voxels are a leakage object;

segmenting newly identified adjacent voxels, which are determined not to be a leakage object;

iterating the identifying, determining, and segmenting steps;

determining whether a new adjacent voxel is segmented in a previous iteration;

determining whether a leakage object is identified in the previous iteration when no new adjacent voxel is determined to have been segmented in the previous iteration, wherein leakage is determined based on (a) an inversely proportional relationship of a front size of adjacent voxels and an iteration number and (b) a linear relationship between the front size and bifurcations and changes in an airway shape; and

reducing the threshold Hounsfield unit value and performing the region growing algorithm only on the identified adjacent voxels, as seed voxels, in the previous iteration when at least one leakage object is determined being identified in the previous iteration,

wherein the method is performed by a processor.

2. The method according to claim 1, further comprising terminating the region growing process when no leakage object is identified in the previous iteration.

3. The method of claim 1, wherein the first seed voxel is a point in a trachea.

4. The method of claim 3, wherein the first seed voxel in the trachea meets a high threshold value.

5. The method of claim 1, further comprising counting a number of the segmented voxels in each iteration.

6. The method of claim 5, wherein the identified adjacent voxels are determined to be a leakage object when an increase in the number of segmented voxels exceeds a predefined rate.

7. The method of claim 6, wherein the segmented voxels are identified and recorded in each iteration.

8. The method of claim 7, creating a voxel list from the segmented voxels of each iteration.

9. The method of claim 8, generating a model from the voxel list.

10. The method of claim 9, wherein the model is of an anatomical structure.