Computer-aided classification of anomalies in anatomical structures

• US 7,260,250 B2
• Filed: 09/26/2003
• Issued: 08/21/2007
• Est. Priority Date: 09/30/2002
• Status: Active Grant

• Current Assignee: Health and Human Services United States of America As Represented By The SEC
• Original Assignee: United States Department Of Health And Human Services
• Inventors: Summers, Ronald M., Iordanescu, Gheorghe, Franaszek, Marek
• Primary Examiner(s): Johns; Andrew W.
• Assistant Examiner(s): WANG, CLAIRE X
• Application Number:
  US10/671,749
• Publication Number:
  US 20040064029A1
• Time in Patent Office: 1,425 Days
• Field of Search: 382/128, 382/131, 382/199, 382/173, 382/159, 382/224, 600/416
• US Class Current: 382/128
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

Candidate anomalies in an anatomical structure are processed for classification. For example, false positives can be reduced by techniques related to the anomaly'"'"'s neck, wall thickness associated with the anomaly, template matching performed for the anomaly, or some combination thereof. The various techniques can be combined for use in a classifier, which can determine whether the anomaly is of interest. For example, a computed tomography scan of a colon can be analyzed to determine whether a candidate anomaly is a polyp. The technologies can be applied to a variety of other scenarios involving other anatomical structures.

Claims

1. A computer-implemented method for processing a detected anomaly in an anatomical structure, the method comprising:

in a digital representation comprising a representation of the anomaly, measuring a characteristic of a neck of the anomaly; and

based at least on the characteristic of the anomaly neck, classifying the anomaly.

2. A computer-readable medium comprising computer-executable instructions for performing the method of claim 1.

3. The method of claim 1 wherein classifying comprises disqualifying the anomaly from being of interest.

4. The method of claim 1 wherein classifying comprises designating the anomaly as being of interest.

5. The method of claim 1 wherein the candidate anomaly comprises a surface anomaly.

6. The method of claim 1 wherein the candidate anomaly comprises a wall surface anomaly.

7. Performing the method of claim 1 for a plurality of candidate anomalies.

8. The method of claim 7 wherein the candidate anomalies are discovered via measured curvatures associated with regions in the digital representation.

9. The method of claim 1 wherein:

the anatomical structure comprises a colon; and

classifying the anomaly comprises designating the anomaly as a polyp.

10. The method of claim 1 wherein:

the anatomical structure comprises a bronchus; and

classifying the anomaly comprises designating the anomaly as a lesion.

11. The method of claim 1 wherein the characteristic comprises neck size.

12. The method of claim 1 wherein the characteristic comprises neck height.

13. The method of claim 1 wherein the characteristic comprises neck circumference.

14. The method of claim 1 wherein the characteristic comprises area enclosed by the neck.

15. The method of claim 1 wherein the characteristic comprises neck angle.

16. The method of claim 1 wherein the characteristic comprises orientation of the neck.

17. The method of claim 1 wherein the characteristic comprises irregularity of the neck.

18. The method of claim 17 wherein irregularity comprises jaggedness of the neck.

19. The method of claim 17 wherein irregularity of the neck is determined via a fractal technique.

20. The method of claim 1 wherein the characteristic comprises curvature of the neck.

21. The method of claim 20 wherein the curvature comprises Gaussian curvature.

22. The method of claim 20 wherein the curvature comprises mean curvature.

23. The method of claim 20 wherein the curvature comprises principal curvature.

24. The method of claim 23 wherein the curvature comprises maximum principal curvature.

25. The method of claim 23 wherein the curvature comprises minimum principal curvature.

26. The method of claim 20 wherein the curvature comprises shape index.

27. The method of claim 20 wherein the curvature comprises curvedness.

28. The method of claim 20 wherein the curvature is calculated via partial derivatives.

29. The method of claim 20 wherein the curvature is calculated via finite differences.

30. The method of claim 20 wherein the curvature is calculated via convolution kernels.

31. The method of claim 20 wherein the curvature is calculated via fitting approximating curves.

32. The method of claim 20 wherein the curvature is calculated via fitting approximating surfaces.

33. The method of claim 1 wherein the characteristic comprises relation of the neck to adjacent haustral folds.

34. The method of claim 1 further comprising:

fitting a plane to the circumference of the neck;

measuring protrusion of the anomaly; and

based also at least on the characteristic of the anomaly neck, classifying the anomaly.

35. The method of claim 1 further comprising:

identifying an edge in the representation of the anomaly and an adjacent wall of the representation of the anatomical structure;

wherein the characteristic comprises an angle made by a junction of the anomaly with the wall.

36. The method of claim 35 wherein the edge is identified via segmenting.

37. The method of claim 35 wherein the edge is identified via an isosurface technique.

38. The method of claim 35 wherein the edge is identified via a level set technique.

39. A computer-implemented method for processing a detected candidate polyp in a virtual colon, the method comprising:

via the virtual colon, measuring a characteristic of a neck of the detected candidate polyp; and

based at least on the characteristic of the neck, classifying the candidate polyp.

40. A computer-implemented method for processing an anomaly in an anatomical structure, the method comprising:

in a digital representation of the anatomical structure comprising a representation of the anomaly, identifying a neck of the anomaly;

based at least on the anomaly neck, measuring protrusion of the anomaly; and

based at least on the protrusion of the anomaly, classifying the anomaly.

41. The method of claim 40 wherein measuring protrusion comprises fitting a plane to the circumference of the neck.

42. A computer-generated user interface for presenting a graphical representation of an anatomical structure, the user interface comprising:

a depiction of the anatomical structure;

wherein regions of the anatomical structure having a curvature indicative of an anomaly neck are depicted specially.

43. The computer-generated usrer interface of claim 42 wherein regions of the anatomical structure having a curvature indicitave of an in a distinctive color.

44. The computer-generated user interface of claim 43 wherein the curvature indicative of an anomaly neck comprises hyperbolic curvature.