Pathological tissue mapping

• US 7,483,554 B2
• Filed: 11/17/2004
• Issued: 01/27/2009
• Est. Priority Date: 11/17/2003
• Status: Expired due to Fees

• Current Assignee: David Sans
• Original Assignee: Aureon Biosciences, Inc.
• Inventors: Kotsianti, Angeliki, Saidi, Olivier, Teverovskiy, Mikhail
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US10/991,897
• Publication Number:
  US 20050165290A1
• Time in Patent Office: 1,532 Days
• Field of Search: 382/100, 382/128, 382/129, 382/130, 382131-133, 382/155, 382/162, 382/168, 382/177, 382/180, 382/181, 382190-195, 382/203, 382/219, 382/224, 382/232, 382/260, 382/274, 382/276, 382/305, 382/134, 707/6, 706/12, 250/458.1, 435/7.23, 435/7.24, 435/42, 435/451
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/20036 Morphological image processing
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 2207/30056 Liver; Hepatic
• 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 7/155 involving morphological operators
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06V 20/69 Microscopic objects, e.g. biological cells or cellular parts

Abstract

Embodiments of the present invention are directed to quantitative analysis of tissues enabling the measurement of objects and parameters of objects found in images of tissues including perimeter, area, and other metrics of such objects. Measurement results may be input into a relational database where they can be statistically analyzed and compared across studies. The measurement results may be used to create a pathological tissue map of a tissue image, to allow a pathologist to determine a pathological condition of the imaged tissue more quickly.

Claims

1. A method for tissue analysis comprising:

using one or more computers to perform the operation of;

acquisition of a tissue image corresponding to a tissue sample;

segmentation of the image into a plurality of objects;

classifying the plurality of objects into one or more object types;

quantifying at least one parameter corresponding to at least one of said object types to produce a quantification result for each corresponding object of the at least one of said object types;

establishing a range of the quantification results;

dividing the range into a plurality of bins, wherein each bin represents a visual indicator for producing a modified image of the tissue image;

assigning each object of the at least one of said object types to a bin based on the quantification result for each object; and

modifying corresponding pixels for each object of the at least one of said object types in the modified image with the visual indicator of the bin corresponding to the respective object.

2. The method according to claim 1, further comprising classifying the tissue sample based on the modified image.

3. The method according to claim 2, wherein the tissue is classified as normal or abnormal.

4. The method according to claim 1, wherein the visual indicator is selected from the group consisting of:

color, color intensity, size, shape, symbol, letter and number.

5. The method according to claim 1, wherein the tissue image comprises an image of liver tissue and the at least one of said object types comprises a hepatocyte and the parameter comprises fat content.

6. The method according to claim 5, wherein quantification comprises a ratio of the area of fat contained in each hepatocyte, to the area of the respective hepatocyte.

7. The method according to claim 1, wherein the method is used to identify toxic effect or response.

8. The method according to claim 1, wherein the method is used to identify immunological reactions.

9. The method according to claim 1, wherein the method is used to identify morphological lesions caused by disease selected from the group consisting of:

acute, sub-acute or chronic hepatitis;

inflammatory or necrotic cholestasis;

fibrosis;

granulomatous hepatitis;

macro or microvesicular steatosis;

vascular lesions; and

hepatic tumors.

10. The method according to claim 1, further comprising training a neural network and/or a support vector machine using the modified image.

11. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying micro-anatomic data corresponding to at least one of said object types.

12. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying molecular data corresponding to at least one of said object types.

13. The method of claim 1, wherein said tissue image comprises an image of prostate tissue, said at least one of said object types comprises lumen, and said quantifying at least one parameter comprises quantifying lumen area relative to tissue area.

14. The method of claim 1, wherein said tissue image comprises an image of prostate tissue, said at least one of said object types comprises a gland unit, and said quantifying at least one parameter comprises determining a Gleason grade corresponding to said gland unit.

15. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying a size corresponding to at least one of said object types.

16. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying a shape corresponding to at least one of said object types.

17. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying a color corresponding to at least one of said object types.

18. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying a color intensity corresponding to at least one of said object types.

19. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying an area corresponding to at least one of said object types.

20. The method of claim 1, wherein said quantifying at least one parameter comprises determining a quantity corresponding to at least one of said object types.

21. The method of claim 1, wherein said quantifying at least one parameter comprises quantifying at least one parameter corresponding to at least one of said object types relative to a granularity unit of the tissue image.

22. The method of claim 21, wherein said granularity unit comprises a cell and said at least one of said object types comprises a cell component.

23. The method of claim 1, wherein said classifying the plurality of objects comprises classifying the plurality of objects into a plurality of object types.

24. The method of claim 1, wherein said one or more object types comprises at least one tissue object.

25. The method of claim 24, wherein said at least one tissue object comprises a bile duct.

26. The method of claim 24, wherein said at least one tissue object comprises a vein.

27. The method of claim 24, wherein said at least one tissue object comprises an artery.

28. The method of claim 24, wherein said at least one tissue object comprises a gland.

29. The method of claim 1, wherein said one or more object types comprises at least one histopathological object.

30. The method of claim 1, wherein said one or more object types comprises at least one cell component.

31. The method of claim 30, wherein said at least one cell component comprises nuclei.

32. The method of claim 30, wherein said at least one cell component comprises cytoplasm.

33. The method of claim 30, wherein said at least one cell component comprises a vacuole.

34. The method of claim 30, wherein said at least one cell component comprises fat.

35. The method of claim 1, wherein classifying the plurality of objects into one or more object types comprises:

designating a first object type as a seed; and

implementing region growing based on said seed to form a second object type.

36. The method of claim 1, wherein modifying corresponding pixels for each object of the at least one of said object types comprises replacing pixels of said object with pixels of a color of the bin corresponding to the respective object.

37. The method of claim 1, further comprising preprocessing the tissue image to correct color variation.

38. The method of claim 1, further comprising applying a filter to enhance at least one object type of said one or more object types.

39. The method of claim 1, further comprising applying a filter to suppress at least one object type of said one or more object types.

40. A computer readable medium having computer instructions for enabling a computer system to perform a method for tissue analysis, the method comprising:

acquisition of a tissue image corresponding to a tissue sample;

segmentation of the image into a plurality of objects;

classifying the plurality of objects into one or more object types;

quantifying at least one parameter corresponding to at least one of said object types to produce a quantification result for each corresponding object of the at least one of said object types;

establishing a range of the quantification results;

dividing the range into a plurality of bins, wherein each bin represents a visual indicator for producing a modified image of the tissue image;

assigning each object of the at least one of said object types to a bin based on the quantification result for each object; and

modifying corresponding pixels for each object of the at least one of said object types in the modified image with the visual indicator of the bin corresponding to the respective object.

41. The computer readable medium according to claim 40, where the method further includes displaying and/or printing the modified image.

42. A system for tissue analysis comprising:

acquisition means for acquiring a tissue image corresponding to a tissue sample;

segmentation means for segmenting the image into a plurality of objects;

classifying means for classifying the plurality of objects into one or more object types;

quantifying means for quantifying at least one parameter corresponding to at least one of said object types to produce a quantification result for each corresponding object of the at least one of said object types;

establishment means for establishing a range of the quantification results;

dividing means for dividing the range into a plurality of bins, wherein each bin represents a visual indicator for producing a modified image of the tissue image;

assigning means for assigning each object of the at least one of said object types to a bin based on the quantification result for each object; and

modifying means for modifying corresponding pixels for each object of the at least one of said object types in the modified image with the visual indicator of the bin corresponding to the respective object.

43. A system for tissue analysis comprising:

an input for inputting a digital image;

an output comprising at least one of a display and a printer;

a processor for processing computer instructions and data, the processor configured to;

segment the image into a plurality of objects;

classify the plurality of objects into one or more object types;

quantifying at least one parameter corresponding to at least one of said object types to produce a quantification result for each corresponding object of the at least one of said object types;

establish a range of the quantification results;

divide the range into a plurality of bins, wherein each bin represents a visual indicator for producing a modified image of the tissue image;

assign each object of the at least one of said object types to a bin based on the quantification result for each object; and

modify corresponding pixels for each object of the at least one of said object types in the modified image with the visual indicator of the bin corresponding to the respective object.

44. The system according to claim 43, wherein the processor is further configured to classify the tissue sample based on the modified image.

45. The system according to claim 44, wherein the tissue is classified as normal or abnormal.

46. The system according to claim 43, wherein the visual indicator is selected from the group consisting of:

color, color intensity, size, shape, symbol, letter and number.

47. The system according to claim 43, wherein the tissue image comprises an image of liver tissue and the at least one of said object types comprises a hepatocyte and the parameter comprises fat content.

48. The system according to claim 47, wherein said parameter comprises a ratio of the area of fat contained in each hepatocyte, to the area of the respective hepatocyte.

49. The system according to claim 43, wherein said processor is configured to quantify micro-anatomic data corresponding to at least one of said object types.

50. The system according to claim 43, wherein said processor is configured to quantify molecular data corresponding to at least one of said object types.

51. The system according to claim 43, wherein said tissue image comprises an image of prostate tissue, said at least one of said object types comprises lumen, and said processor is configured to quantify lumen area relative to tissue area.

52. The system according to claim 43, wherein said tissue image comprises an image of prostate tissue, said at least one of said object types comprises a gland unit, and said processor is configured to determine a Gleason grade corresponding to said gland unit.

53. The system according to claim 43, wherein said processor is configured to quantify a size corresponding to at least one of said object types.

54. The system according to claim 43, wherein said processor is configured to quantify a shape corresponding to at least one of said object types.

55. The system according to claim 43, wherein said processor is configured to quantify a color corresponding to at least one of said object types.

56. The system according to claim 43, wherein said processor is configured to quantify a color intensity corresponding to at least one of said object types.

57. The system according to claim 43, wherein said processor is configured to quantify an area corresponding to at least one of said object types.

58. The system according to claim 43, wherein said processor is configured to determine a quantity corresponding to at least one of said object types.

59. The system according to claim 43, wherein said processor is configured to quantify at least one parameter corresponding to at least one of said object types relative to a granularity unit of the tissue image.

60. The system according to claim 59, wherein said granularity unit comprises a cell and said at least one of said object types comprises a cell component.

61. The system according to claim 43, wherein said processor is configured to classify the plurality of objects into a plurality of object types.

62. The system according to claim 43, wherein said one or more object types comprises at least one tissue object.

63. The system according to claim 62, wherein said at least one tissue object comprises a bile duct.

64. The system according to claim 62, wherein said at least one tissue object comprises a vein.

65. The system according to claim 62, wherein said at least one tissue object comprises an artery.

66. The system according to claim 62, wherein said at least one tissue object comprises a gland.

67. The system according to claim 43, wherein said one or more object types comprises at least one histopathological object.

68. The system according to claim 43, wherein said one or more object types comprises at least one cell component.

69. The system according to claim 68, wherein said at least one cell component comprises nuclei.

70. The system according to claim 68, wherein said at least one cell component comprises cytoplasm.

71. The system according to claim 68, wherein said at least one cell component comprises a vacuole.

72. The system according to claim 68, wherein said at least one cell component comprises fat.

73. The system according to claim 43, wherein said processor is configured to:

designate a first object type as a seed; and

implement region growing based on said seed to form a second object type.

74. The system according to claim 43, wherein said processor is configured to replace pixels of said object with pixels of a color of the bin corresponding to the respective object.

75. The system according to claim 43, wherein said processor is further configured to preprocess the tissue image to correct color variation.

76. The system according to claim 43, wherein said processor is further configured to apply a filter to enhance at least one object type of said one or more object types.

77. The system according to claim 43, wherein said processor is further configured to apply a filter to suppress at least one object type of said one or more object types.