Methods and systems for generating a lung report

• US 20050251021A1
• Filed: 05/27/2005
• Published: 11/10/2005
• Est. Priority Date: 07/17/2001
• Status: Abandoned Application

• Current Assignee: Merative US LP
• Original Assignee: AccuImage Diagnostics Corp. (International Business Machines Corporation)
• Inventors: Kaufman, Leon, Powers, Shelley, Goldhaber, David, Mineyev, Mikhail
• Application Number:
  US11/139,157
• Publication Number:
  US 20050251021A1
• Time in Patent Office: Days
• US Class Current: 600/407
• CPC Class Codes: A61B 5/055 involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/7289 Retrospective gating, i.e. associating measured signals or images with a physiological event after the actual measurement or image acquisition, e.g. by simultaneously recording an additional physiological signal during the measurement or image acquisition
• CPC Class Codes: A61B 5/7292 Prospective gating, i.e. predicting the occurrence of a physiological event for use as a synchronisation signal
• CPC Class Codes: A61B 6/00 Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment instruments measuring radiation intensity for application in the field of nuclear medicine, e.g. in vivo counting, G01T1/161; apparatus for taking X-ray photographs G03B42/02
• CPC Class Codes: A61B 6/463 characterised by displaying multiple images or images and diagnostic data on one display
• CPC Class Codes: A61B 6/5288 involving retrospective matching to a physiological signal
• CPC Class Codes: A61B 6/541 involving acquisition triggered by a physiological signal
• CPC Class Codes: Y10S 128/922 including image analysis

Abstract

Software, methods and user interfaces for viewing and generating a lung report. In exemplary methods, a first baseline image is analyzed to localize lung nodules. The lung nodule information can be stored and used to relocate the previously localized lung nodules in a second, follow-up imaging scan. The follow-up scan can be analyzed—either manually or automatically—to generate statistics for the lung nodules localized in the follow-up scan. Information derived from the baseline scan can be used to ease the localization of the lung nodules in the follow-up scan. In some exemplary methods, both the baseline scan and follow-up scan are displayed and the nodules are selected for comparison. Typically, the graphical user interface can display a third, composite image that displays the change of size of the nodules.

Claims

1-30. -30. (canceled)

31. A computer program for displaying a comparison of multiple images of a body organ, the computer program comprising:

code for displaying a first image along a body slice taken at t₁;

code for displaying a second image along the body slice taken at t₂;

code for localizing lesions in the first image and second image;

code for registering the first image and second image;

code for comparing the lesion in the first and second images; and

a computer-readable medium for storing the codes.

32. The computer program of claim 31 further comprising code for computing a third image which is a subtraction of the first image and second image.

33. The computer program of claim 31 further comprising code for computing a third image which is the absolute difference of the first image and second image.

34. The computer program of claim 31 further comprising code for computing a third image which is a sum of the first image and second image.

35. The computer program of claim 31 further comprising code for storing at least one of the lesion number, anatomic position, size, volume, surface area, roundness, density and standard deviation, major and minor axes of the nodule.

36. The method of claim 31 wherein the code for registering the lesions comprises code for demanding that the lesion have at least one voxel be overlapped.

37. The method of claim 31 wherein the code for registering the lesions comprises code for demanding that the edges of the lesion be no more than a fixed number of pixels apart.

38. The method of claim 31 wherein the code for registering the lesions comprises code for demanding that the edges of the lesion be no more than one pixel apart.

39. The method of claim 31 wherein the code for registering the lesions comprises code for demanding that the edges of the lesion be no more than three pixels apart.

40. The computer program of claim 31 further comprising code for displaying lesions in the first image in a first color and nodules in the second image in a second color.

41. The computer program of claim 31 further comprising code for removing surrounding tissues or organs from the first and second images.

42. The computer program of claim 31 further comprising code for generating a body report.

43. The computer program of claim 31 further comprising code for marking the lesions.

55. The method of claim 43 wherein providing comprises automatically locating lesions in the images.

56. The method of claim 43 wherein providing comprises manually locating lesions in the images.

44. A method of comparing a first image dataset with a second image dataset, the method comprising:

displaying an image from both the first dataset and the second dataset;

registering the image from the first dataset with the image from the second dataset; and

displaying an image which displays one of a sum of the image from the first dataset and the image from the second dataset and a subtraction or absolute difference of the image from the first dataset and the image from the second dataset.

45. The method of claim 44 wherein registering comprises matching at least one lesion in the image from the first dataset with at least one corresponding lesion in the image from the second dataset.

46. The method of claim 45 wherein the lesions are matched by demanding that at least one voxel be overlapped.

47. The method of claim 45 wherein the lesions are matched by demanding that the edges of the lesion be no more than a fixed number of pixels apart.

48. The method of claim 45 wherein the lesions are matched by demanding that the edges of the lesion be no more than one pixel apart.

49. The method of claim 45 further comprising highlighting lesions in the images.

50. The method of claim 49 wherein highlighting comprises coloring the lesion in the first image dataset a different color from the lesion in the second dataset.

51. The method of claim 45 further comprising segmenting the images.

52. The method of claim 45 further comprising automatically measuring at least one of a volume and dimensions of the lesions.

53. The method of claim 45 further comprising calculating a change of size of lesions between the image of the first dataset and the image of the second dataset.

54. The method of claim 45 further comprising calculating a change of the signal intensity characteristics of lesions between the image of the first dataset and the image of the second dataset.

57. The method of claim 45 wherein matching comprises manually matching the lesion in the images.

58. The method of claim 45 wherein matching comprises automatically matching the lesion in the images.

59. The method of claim 45 wherein lesions are matched by demanding that the edges of the lesion be no more than three pixels apart.