Virtual endoscopy with improved image segmentation and lesion detection

• US 8,682,045 B2
• Filed: 06/29/2010
• Issued: 03/25/2014
• Est. Priority Date: 02/25/1997
• Status: Expired due to Fees

• Current Assignee: Wake Forest University
• Original Assignee: Wake Forest University Health Sciences
• Inventors: Vining, David J., Hunt, Gordon W., Ahn, David K., Stelts, David R., Ge, Yaorong, Hemler, Paul F., Salido, Tiffany W.
• Primary Examiner(s): Seth, Manav
• Application Number:
  US12/826,268
• Publication Number:
  US 20100265251A1
• Time in Patent Office: 1,365 Days
• Field of Search: None
• US Class Current: 382/128
• CPC Class Codes: A61B 5/107 Measuring physical dimensions, e.g. size of the entire body or parts thereof
• CPC Class Codes: A61B 5/1076 for measuring dimensions inside body cavities, e.g. using catheters A61B3/1005 takes precedence
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 2207/30032 Colon polyp
• CPC Class Codes: G06T 2207/30064 Lung nodule
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• 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: G09B 23/285 for injections, endoscopy, bronchoscopy, sigmoidscopy, insertion of contraceptive devices or enemas
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics

Abstract

A system, and computer implemented method are provided for interactively displaying three-dimensional structures. Three-dimensional volume data (34) is formed from a series of two-dimensional images (33) representing at least one physical property associated with the three-dimensional structure, such as a body organ having a lumen. A wire frame model of a selected region of interest is generated (38b). The wireframe model is then deformed or reshaped to more accurately represent the region of interest (40b). Vertices of the wire frame model may be grouped into regions having a characteristic indicating abnormal structure, such as a lesion. Finally, the deformed wire frame model may be rendered in an interactive three-dimensional display.

Claims

1. A computer-implemented method for interactively displaying a three-dimensional rendering of a structure having a lumen comprising the steps of:

a. forming a three-dimensional volume of data from a series of two-dimensional images representing at least one physical property associated with the three-dimensional structure;

b. generating a wireframe model of a selected region of interest;

c. deforming the wire frame model using a geometric deformable model to more accurately represent the region of interest; and

d. rendering the wireframe model in an interactive three-dimensional display.

2. A computer-implemented method for interactively displaying a three-dimensional rendering of a structure having a lumen comprising the steps of:

a. providing a three-dimensional volume of data representing at least one physical property associated with the structure having the lumen;

b. generating a wireframe model having vertices representing a region of interest of the structure having the lumen;

c. refining the wire frame model using a geometric deformable model; and

d. rendering the wireframe model in an interactive three-dimensional display.

3. The method of claim 2 wherein the wireframe model comprises a plurality of vertices, the method comprising:

grouping the vertices of the wireframe model into regions having a characteristic indicating abnormal structure;

analyzing the regions having abnormal structure to identify regions having a high degree of abnormality; and

rendering the wire frame model in an interactive three-dimensional display to indicate the regions having abnormal structure.

4. The method of claim 3 wherein the grouping step comprises:

calculating a mean curvature at selected vertices;

calculating a gaussian curvature at the selected vertices;

classifying the selected vertices according to the mean curvature and the gaussian curvature; and

grouping adjoining selected vertices into patches of same vertex classification.

5. The method of claim 4 wherein the analyzing step comprises labeling patches having an elliptical classification as a potential lesion.

6. The method of claim 5 wherein the analyzing step comprises eliminating from the grouping selected elliptical patches which point outwardly from the lumen.

7. The method of claim 6 wherein the analyzing step comprises calculating principal curvatures of the patches from the mean and gaussian curvatures and eliminating from the grouping any elliptical patches having substantially different principal curvatures.

8. The method of claim 2 comprising calculating a normal vector for each vertex in the wire frame model.

9. The method of claim 8 wherein the refinement step comprises moving each vertex of the wireframe model along its normal vector direction at a speed that is a function of a surface curvature and a doubt level of a boundary estimate at that point.

10. The method of claim 8 wherein the refinement step uses a three-dimensional region growing model as a starting point for the geometric deformable model.

11. The method of claim 2 wherein the step of generating a wireframe model comprises the steps of identifying a surface model of the region of interest and generating a wireframe model of the surface model.

12. The method of claim 11 comprising:

grouping the vertices of the wireframe model into regions having a characteristic indicating abnormal structure;

analyzing the regions having abnormal structure to identify regions having a high degree of abnormality; and

rendering the wire frame model in an interactive three-dimensional display to indicate the regions having abnormal structure.

13. The method of claim 12 wherein the grouping step comprises:

calculating a mean curvature at selected vertices;

calculating a gaussian curvature at the selected vertices;

classifying the selected vertices according to the mean curvature and the gaussian curvature; and

grouping adjoining selected vertices into patches of same vertex classification.

14. The method of claim 13 wherein the analyzing step comprises labeling patches having an elliptical classification as a potential lesion.

15. The method of claim 14 wherein the analyzing step comprises eliminating from the grouping selected elliptical patches which point outwardly from the lumen.

16. The method of claim 15 wherein the analyzing step comprises calculating principal curvatures of the patches from the mean and gaussian curvatures and eliminating from the grouping any elliptical patches having substantially different principal curvatures.

17. The method of claim 2 comprising isolating the region of interest from the volume of data based on a selected value of the physical property representing the region of interest.

18. The method of claim 17 wherein the step of isolating comprises segmenting the region of interest.

19. The method of claim 18 comprising creating an isosurface of the region of interest.

20. The method of claim 19 wherein the step of generating a wireframe model comprises generating a wireframe model of the isosurface.

21. The method of claim 20 wherein, the wire frame model comprises a plurality of vertices, the method comprising:

grouping the vertices of the wireframe model into regions having a characteristic indicating abnormal structure;

analyzing the regions having abnormal structure to identify regions having a high degree of abnormality; and

rendering the wire frame model in an interactive three-dimensional display to indicate the regions having abnormal structure.

22. The method of claim 21 wherein the grouping step comprises:

calculating a mean curvature at selected vertices;

calculating a gaussian curvature at the selected vertices;

classifying the selected vertices according to the mean curvature and the gaussian curvature; and

grouping adjoining selected vertices into patches of same vertex classification.

23. The method of claim 22 wherein the analyzing step comprises labeling patches having an elliptical classification as a potential lesion.

24. The method of claim 23 wherein the analyzing step comprises eliminating from the grouping selected elliptical patches which point outwardly from the lumen.

25. The method of claim 24 wherein the analyzing step comprises calculating principal curvatures of the patches from the mean and gaussian curvatures and eliminating from the grouping any elliptical patches having substantially different principal curvatures.