Computer assisted analysis of tomographic mammography data

• US 6,748,044 B2
• Filed: 09/13/2002
• Issued: 06/08/2004
• Est. Priority Date: 09/13/2002
• Status: Expired due to Term

• Current Assignee: GE Medical Systems Global Technology Company LLC (GE Healthcare Technologies, Inc.)
• Original Assignee: GE Medical Systems Global Technology Company LLC (GE Healthcare Technologies, Inc.)
• Inventors: Walker, Matthew J., Avinash, Gopal B., Sabol, John M.
• Primary Examiner(s): Bruce, David V
• Application Number:
  US10/243,056
• Publication Number:
  US 20040052328A1
• Time in Patent Office: 634 Days
• Field of Search: 378/4, 378/8, 378/15, 378/901, 250/363.04, 250/370.09, 382/131
• US Class Current: 378/4
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: Y10S 378/901 Computer tomography program or processor

Abstract

The present technique provides a method and system for generating tomographic mammography data and processing the data using a computer aided detection and diagnosis (CAD) algorithm. The CAD algorithm may perform various types of analysis, including segmentation, feature extraction, and feature classification. The acquired data may be processed in parallel by the CAD algorithm such that information derived from one processing path may be used to enhance or alter the processing of data in a parallel processing path. The processed data may be used to provide an enhanced mammographic image with features of interest marked for inspection by a radiologist. The features of interest may also be classified to aid the inspection by the radiologist.

Claims

1. A method for analyzing mammography data acquired by a tomographic system, comprising:

acquiring a tomographic data set from a tomographic mammography system;

segmenting the tomographic data set into one or more segmented data sets;

processing one or more features of the one or more segmented data sets to produce one or more feature-processed data sets; and

providing the one or more feature-processed data sets to a reviewer.

2. The method as recited in claim 1, wherein acquiring the tomographic data set comprises acquiring the tomographic data set from a computed tomography mammography system.

3. The method as recited in claim 1, wherein acquiring the tomographic data set comprises acquiring the tomographic data set from a PET mammography system.

4. The method as recited in claim 1, wherein acquiring the tomographic data set comprises acquiring the tomographic data set from a thermoacoustic mammography system.

5. The method as recited in claim 1, wherein acquiring the tomographic data set comprises acquiring the tomographic data set from a nuclear medicine breast imaging system.

6. The method as recited in claim 1, wherein acquiring the tomographic data set comprises acquiring the tomographic data set from an electrical impedance mammography system.

7. The method as recited in claim 1, wherein acquiring the tomographic data set comprises acquiring the tomographic data set from a near-infrared mammography system.

8. The method as recited in claim 1, wherein acquiring the tomographic data set comprises acquiring the tomographic data set from an X-ray tomosynthesis mammography system.

9. The method as recited in claim 1, wherein segmenting the tomographic data comprises segmenting the tomographic data based upon the manual delineation of one or more regions by an operator.

10. The method as recited in claim 1, wherein segmenting the tomographic data comprises segmenting the tomographic data based upon the automated delineation of one or more regions by an automated algorithm.

11. The method as recited in claim 1, wherein processing one or more features of the one or more segmented data sets comprises extracting one or more features from the one or more segmented data sets.

12. The method as recited in claim 11, wherein processing one or more features of the one or more segmented data sets further comprises at least one of evaluating the one or more features using a distance criteria, ranking the features based upon the distance criteria, eliminating one or more features based upon a degree of correlation, and optimizing a selected feature set using a performance algorithm to produce the one or more feature-processed data sets.

13. The method as recited in claim 11, further comprising training a processing system to process the one or more features of the one or more segmented data sets.

14. The method as recited in claim 1, further comprising classifying each of the one or more features of the one or more feature-processed data sets based upon one or more feature measurements of each feature to produce the one or more feature-processed data sets.

15. The method as recited in claim 14, wherein classifying the one or more features comprises normalizing the feature measurements based upon two or more prior measurements of known normal and abnormal features, grouping the one or more features based upon their normalized feature measurements, and labeling the groups of one or more features.

16. The method as recited in claim 15, wherein at least one of grouping the one or more features and labeling the groups is performed by an automated algorithm utilizing one or more stored data sets.

17. The method as recited in claim 1, wherein providing the one or more feature-processed data sets to the reviewer comprises displaying the one or more feature-processed data sets to an operator for review.

18. The method as recited in claim 1, wherein providing the one or more feature-processed data sets to the reviewer comprises providing the one or more feature-processed data sets to a subsequent automated process for at least one of further processing and analysis.

19. The method as recited in claim 1, wherein providing the one or more feature-processed data sets to the reviewer comprises superposing one or more markers on the feature-processed data sets.

20. The method as recited in claim 19, wherein the one or more markers convey at least one of a feature classification, a classification probability, and a three-dimensional location.

21. A method for analyzing tomographic data in Radon space, comprising:

acquiring a tomographic projection data set from a tomographic imaging system;

identifying a feature of interest in the tomographic projection data set;

processing a reconstructed data set derived from the tomographic projection data set based upon the feature of interest such that the feature of interest is enhanced in the reconstructed data set.

22. The method as recited in claim 21, wherein processing the reconstructed data set comprises processing a two-dimensional data set.

23. The method as recited in claim 21, wherein processing the reconstructed data set comprises processing a three-dimensional data set.

24. A method for analyzing tomographic data comprising:

analyzing a tomographic data set via a first processing path;

identifying a feature of interest within the tomographic data set; and

processing a related tomographic data set via a second processing path based upon the feature of interest.

25. The method as recited in claim 24, wherein analyzing the tomographic data set comprises analyzing a set of tomographic projection data and wherein processing the related tomographic data set comprises processing a set of reconstructed image data.

26. The method as recited in claim 24, wherein analyzing the tomographic data set comprises analyzing a set of reconstructed image data and wherein processing the related tomographic data set comprises processing a set of tomographic projection data.

27. A tomographic mammography system comprising:

a tomographic scanner generally comprising a detector,

a computer system operably coupled to the tomographic scanner via a system controller and operably coupled to a memory element, an operator workstation, and one or more output devices, wherein the computer system is configured to acquire a tomographic data set from the tomographic scanner, segment the tomographic data set into one or more segmented data sets, process one or more features of the one or more segmented data sets to produce one or more feature-processed data sets, and provide the one or more feature-processed data sets to a reviewer.

28. The system as recited in claim 27, wherein the tomographic scanner further comprises a source.

29. The system as recited in claim 28, wherein the source is an injected radionucleotide.

30. The system as recited in claim 29, wherein the tomographic scanner is a PET mammography system.

31. The system as recited in claim 29, wherein the tomographic scanner is a nuclear medicine breast imaging system.

32. The system as recited in claim 28, wherein the tomographic scanner is a computed tomography mammography system.

33. The system as recited in claim 28, wherein the tomographic scanner is a thermoacoustic mammography system.

34. The system as recited in claim 28, wherein the tomographic scanner is an electrical impedance mammography system.

35. The system as recited in claim 28, wherein the tomographic scanner is a near-infrared mammography system.

36. The system as recited in claim 28, wherein the tomographic scanner is an X-ray tomosynthesis mammography system.

37. The system as recited in claim 27, wherein the computer system is configured to segment the tomographic data set based upon the manual delineation of one or more regions performed by an operator at the operator workstation.

38. The system as recited in claim 27, wherein the computer system is configured to segment the tomographic data set based upon the calculated delineation of one or more regions by a stored algorithm.

39. The system as recited in claim 27, wherein the computer system is configured to process one or more features of the one or more segmented data sets by extracting one or more features from the one or more segmented data sets.

40. The system as recited in claim 39, wherein the computer system is further configured to evaluate the one or more features using a distance criteria, rank the features based upon the distance criteria, eliminate one or more features based upon a degree of correlation, and optimize a selected feature set using a performance algorithm to produce the one or more feature-processed data sets.

41. The system as recited in claim 27, wherein the computer system is further configured to classify each of the one or more features of the one or more feature-processed data sets based upon one or more feature measurements of each feature to produce the one or more feature-processed data sets.

42. The system as recited in claim 41, wherein the computer system is configured to classify the one or more features by normalizing the feature measurements based upon two or more prior measurements of known normal and abnormal features;

grouping the one or more features based upon their normalized feature measurements, and labeling the groups of one or more features.

43. The system as recited in claim 27, wherein the computer system provides the one or more feature-processed data sets to the reviewer by displaying the one or more feature-processed data sets to an operator via the one or more output devices.

44. The system as recited in claim 27, wherein the computer system provides the one or more feature-processed data sets to the reviewer by providing the one or more feature-processed data sets to a subsequent automated process located within the computer or on a remote client for at least one of further processing and analysis.

45. The system as recited in claim 27, wherein the computer system provides the one or more feature-processed data sets to the reviewer such that one or more markers are superposed on the feature-processed data set.

46. The system as recited in claim 45, wherein the one or more markers convey at least one of a feature classification, a classification probability, and a three-dimensional location.

49. The system as recited in claim 38, further comprising a means for classifying each of the one or more features to produce the one or more feature-processed data sets.

47. A tomographic imaging system comprising:

a tomographic scanner generally comprising a source and a detector;

a computer system operably coupled to the tomographic scanner via a system controller and operably coupled to a memory element, an operator workstation, and one or more output devices, wherein;

the computer system is configured to analyze a tomographic data set via a first processing path, identify a feature of interest within the tomographic data set; and

process a related tomographic data set via a second processing path based upon the feature of interest.

48. A tomographic mammography system comprising:

a means for acquiring a tomographic image data set;

a means for segmenting the tomographic image data set into one or more segmented data sets;

a means for processing one or more features of the one or more segmented data sets to produce one or more feature-processed data sets; and

a means for providing the one or more feature-processed data sets to a reviewer.

50. A tangible medium for analyzing mammography data acquired by a tomographic system, comprising:

a routine for acquiring a tomographic data set from a tomographic mammography system;

a routine for segmenting the tomographic data set into one or more segmented data sets;

a routing for processing one or more features of the one or more segmented data sets to produce one or more feature-processed data sets; and

a routine for providing the one or more feature-processed data sets to a reviewer.

51. The tangible medium as recited in claim 50, wherein the routine for segmenting the tomographic data comprises segmenting the tomographic data based upon the manual delineation of one or more regions by an operator.

52. The tangible medium as recited in claim 50, wherein the routine for segmenting the tomographic data comprises segmenting the tomographic data based upon the automated delineation of one or more regions by an automated algorithm.

53. The tangible medium as recited in claim 50, wherein the routine for processing one or more features of the one or more segmented data sets comprises extracting one or more features from the one or more segmented data sets.

54. The tangible medium as recited in claim 53, wherein the routine for processing one or more features of the one or more segmented data sets further comprises at least one of evaluating the one or more features using a distance criteria, ranking the features based upon the distance criteria, eliminating one or more features based upon a degree of correlation, optimizing a selected feature set using a performance algorithm to produce the one or more feature-processed data sets.

55. The tangible medium as recited in claim 54, further comprising a routine for training a processing system to process the one or more features of the one or more segmented data sets.

56. The tangible medium as recited in claim 50, further comprising a routine for classifying each of the one or more features of the one or more feature-processed data sets based upon one or more feature measurements of each feature to produce the one or more feature-processed data sets.

57. The tangible medium as recited in claim 56, wherein the routine for classifying the one or more features comprises normalizing the feature measurements based upon two or more prior measurements of known normal and abnormal features;

grouping the one or more features based upon their normalized feature measurements, and labeling the groups of one or more features.

58. The tangible medium as recited in claim 57, wherein at least one of grouping the one or more features and labeling the groups is performed by an automated algorithm utilizing one or more stored data sets.

59. The tangible medium as recited in claim 50, wherein the routine for providing the one or more feature-processed data sets to the reviewer comprises displaying the one or more feature-processed data sets to an operator for review.

60. The tangible medium as recited in claim 50, wherein the routine for providing the one or more feature-processed data sets to the reviewer comprises providing the one or more feature-processed data sets to a subsequent automated process for at least one of further processing and analysis.

61. The tangible medium as recited in claim 50, wherein the routine for providing the one or more feature-processed data sets to the reviewer comprises superposing one or more markers on the feature-processed data sets.

62. The tangible medium as recited in claim 61, wherein the one or more markers comprises at least one of a feature classification, a classification probability, and a three-dimensional location.