Image Processing Apparatus and Image Processing Method

• US 20070292011A1
• Filed: 03/14/2006
• Published: 12/20/2007
• Est. Priority Date: 04/13/2005
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Medical Systems Corporation (Olympus Corporation)
• Inventors: Nishimura, Hirokazu, Nonami, Tetsuo
• Granted Patent: US 7,953,261 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 1/00016 using wireless means
• CPC Class Codes: A61B 1/00036 Means for power saving, e.g. sleeping mode
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: A61B 5/065 Determining position of the probe employing exclusively positioning means located on or in the probe, e.g. using position sensors arranged on the probe
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/30092 Stomach; Gastric
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 20/69 Microscopic objects, e.g. biological cells or cellular parts
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

An image processing apparatus and an image processing method which can improve efficiency of observation by a user are provided. The image processing apparatus of the present invention includes an image inputting unit configured to input a medical image including a plurality of color signals; a determining unit configured to determine whether the biological mucosa is sufficiently captured in the inputted medical image or not; and a controlling unit configured to control at least either of display or storage of the medical image based on the determination result in the determining unit.

Claims

1. An image processing apparatus comprising;

an image inputting unit configured to input a medical image having a plurality of color signals;

a determining unit configured to determine whether a biological mucosa is sufficiently captured in the inputted medical image or not; and

a controlling unit configured to control at least either displaying or storing of the medical image based on the determination result in the determining unit.

2. The image processing apparatus according to claim 1, further including:

an image dividing unit configured to divide the medical image into a plurality of areas;

a feature value calculating unit configured to calculate one or more feature values in each of the plurality of areas of the medical image;

an area classifying unit configured to identify which class of the plurality of classes each of the plurality of areas belongs to based on the feature value and classify each of the plurality of areas by the identification result;

a classification determining value calculating unit configured to calculate a proportion of a group of areas classified in a predetermined class among the plurality of classes in the plurality of areas based on the classification result by the area classifying unit; and

an image classifying unit configured to classify the image having the group of areas classified in the predetermined classes based on the proportion calculated by the classification determining value calculating unit and a predetermined threshold relating to the proportion;

wherein the determining unit determines that the medical image is an image in which a biological mucosa is not sufficiently captured if the proportion is a predetermined threshold or less based on the classification result by the image classifying unit, and determines that the medical image is an image in which a biological mucosa is sufficiently captured if the proportion is larger than the predetermined threshold.

3. The image processing apparatus according to claim 2, wherein the controlling unit controls not to display the medical image which is determined that the biological mucosa is not sufficiently captured by the determining unit.

4. The image processing apparatus according to claim 2, wherein the controlling unit controls not to store the medical image which is determined that the biological mucosa is not sufficiently captured by the determining unit.

5. The image processing apparatus according to claim 3, wherein the controlling unit controls not to store the medical image which is determined that the biological mucosa is not sufficiently captured by the determining unit.

6. The image processing apparatus according to claim 2, further including an image deleting unit configured to delete the medical image which is determined that the biological mucosa is not sufficiently captured by the determining unit.

7. The image processing apparatus according to claim 3, further including an image deleting unit configured to delete the medical image which is determined that the biological mucosa is not sufficiently captured by the determining unit.

8. The image processing apparatus according to claim 4, further including an image deleting unit configured to delete the medical image which is determined that the biological mucosa is not sufficiently captured by the determining unit.

9. The image processing apparatus according to claim 5, further including an image deleting unit configured to delete the medical image which is determined that the biological mucosa is not sufficiently captured by the determining unit.

10. The image processing apparatus according to claim 2, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

11. An image processing apparatus including:

an image inputting unit configured to input a plurality of medical images including a plurality of color signals;

an area setting unit configured to set a plurality of areas for the inputted medical images;

a detecting unit configured to detect an area which is suspected to have a lesion from the plurality of areas;

an area determining unit configured to determine whether the plurality of areas set by the area setting unit are areas in each of which a biological mucosa is captured or not; and

a detection result determining unit configured to determine whether a detection result by the detecting unit is right or wrong based on the determination result in the area determining unit.

12. The image processing apparatus according to claim 11, further including:

a feature value calculating unit configured to calculate one or more feature values in each of the plurality of areas of the medical image;

an area classifying unit configured to classify the plurality of areas into any of a plurality of classes including a class relating to a biological mucosa and a class relating to a non-biological mucosa based on the feature value;

an edge detecting unit configured to detect an area having an edge in the plurality of areas based on a density value of a green component of the medical image;

a bleeding site determining unit configured to determine whether an area having the edge is an area including a bleeding site or not based on a density value of a red component of the image; and

a classification result determining unit configured to determine whether the classification result of the area classifying unit is right or wrong based on the determination result of the bleeding site determining unit, wherein the detecting unit detects an area including the bleeding site as an area which is suspected to have a lesion.

13. The image processing apparatus according to claim 12, wherein the area determining unit determines, if an area is classified into a class relating to a biological mucosa, that the area is the area in which a biological mucosa is captured based on the classification result of the area classifying unit.

14. The image processing apparatus according to claim 13, wherein the detection result determining unit determines that the detection result of the detection unit is correct, if the area which is suspected to have a lesion is the area in which a biological mucosa is captured based on the detection result of the detecting unit and the determination result of the area determining unit.

15. The image processing apparatus according to claim 12, wherein the feature value has at least either a feature value relating to a color or a feature value relating to a texture.

16. An image processing apparatus including:

an image inputting unit configured to input a plurality of medical images captured serially in time order;

an area setting unit configured to set a plurality of areas in the medical image;

a determining unit configured to determine an object of image capturing in the plurality of areas set by the area setting unit;

an identifying unit configured to identify an organ whose image is captured in the medical image based on a determination result of the determining unit; and

an identification result displaying unit configured to display an identification result by the identifying unit.

17. The image processing apparatus according to claim 16, further including:

an image dividing unit configured to divide the medical image into a plurality of areas;

a feature value calculating unit configured to calculate one or more feature values in each of the plurality of areas of the medical image;

an area classifying unit configured to identify which class of a plurality of classes each of the plurality of areas belongs to based on the feature value and classify each of the plurality of areas by the identification result;

a classification determination value calculating unit configured to calculate a proportion of a group of areas classified in a predetermined class among the plurality of classes in the plurality of areas based on the classification result by the area classifying unit; and

an image classifying unit configured to classify the image having the group of areas classified into the predetermined class based on the proportion calculated by the classification determination value calculating unit and the predetermined threshold relating to the proportion;

wherein the identifying unit identifies an organ whose image is captured in the medical image based on the classification result of the image classifying unit.

18. The image processing apparatus according to claim 17, wherein the plurality of classes has at least a gastric mucosa class, a villi class, and a feces class

19. The image processing apparatus according to claim 18, wherein, if the predetermined class is the gastric mucosa class, the identifying unit determines that the organ whose image is captured in the medical image is the gaster.

20. The image processing apparatus according to claim 18, wherein, if the predetermined class is the villi class, the identifying unit determines that the organ whose image is captured in the medical image is the small intestine.

21. The image processing apparatus according to claim 18, wherein, if the predetermined class is the feces class, the identifying unit determines that the organ whose image is captured in the medical image is the large intestine.

22. The image processing apparatus according to claim 17, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

23. An image processing apparatus includes:

an image signal inputting unit configured to input an image signal based on an image captured by a medical appliance having an image capturing function;

an image dividing unit configured to divide an image captured by the medical appliance into a plurality of areas based on the image signals inputted by the image signal inputting unit;

a feature value calculating unit configured to calculate one or more feature values in each of the plurality of areas divided by the image dividing unit;

a first area classifying unit configured to classify the plurality of areas into any of the plurality of classes based on the feature value calculated by the feature value calculating unit and a predetermined first classifying criterion;

a classifying criterion setting unit configured to set a second classifying criterion based on the feature value and the classification result by the first area classifying unit; and

a second area classifying unit configured to classify the plurality of areas into any of the plurality of classes based on the feature value and the second classifying criterion.

24. The image processing apparatus according to claim 23, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

25. The image processing apparatus according to claim 23, wherein the first area classifying unit classifies each of the plurality of areas into any of the plurality of classes by using a statistical discriminator which uses a parameter for determining the first classifying criterion, and the second area classifying unit classifies each of the plurality of areas into any of the plurality of classes by using a statistical discriminator which uses a parameter for determining the second classifying criterion.

26. An image processing apparatus including:

an image signal inputting unit configured to input an image signal based on an image captured by a medical appliance having an image capturing function;

an image dividing unit configured to divide an image captured by the medical appliance into a plurality of areas based on the image signal inputted by the image signal inputting unit;

a feature value calculating unit configured to calculate one or more feature values in each of the plurality of areas divided by the image dividing unit;

a first area classifying unit configured to classify the plurality of areas into any of the plurality of classes based on the feature value calculated by the feature value calculating unit and a predetermined first classifying criterion;

an evaluated value calculating unit configured to evaluate the classification result by the first area classifying unit of one area among the plurality of areas by calculating an evaluated value based on the classification result by the first area classifying unit of the area placed near the one area; and

a second area classifying unit configured to classify the one area into any of the plurality of classes based on the evaluated value in the evaluated value calculating unit.

27. The image processing apparatus according to claim 26, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

28. An image processing apparatus including:

an image signal inputting unit configured to input an image signal based on an image captured by a medical appliance having an image capturing function;

an image dividing unit configured to divide an image captured by the medical appliance into a plurality of areas based on the image signal inputted by the image signal inputting unit;

a feature value calculating unit configured to calculate one or more feature values in each of the plurality of areas divided by the image dividing unit;

a notice area setting unit configured to set one area among the plurality of areas as a notice area;

a close circumference area detecting unit configured to detect a close circumference area which is an area at a predetermined distance from the notice area;

an approximately round shape detecting unit configured to detect the presence of at least a part of a contour part of the approximately round shape based on the feature value in the close circumference area; and

an area extracting unit configured to extract the notice area, if the approximately round shape is detected by the approximately round shape detecting unit.

29. The image processing apparatus according to claim 28, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

30. The image processing apparatus according to claim 28, wherein the approximately round shape detecting unit detects an approximately round shape if it is determined that a proportion of an area in which at least a part of the contour part of the approximately round shape is a predetermined threshold or more in the close circumference area, and the area extracting unit extracts the notice area as an area in which a center part of the approximately round shape is present.

31. The image processing apparatus according to claim 29, wherein the approximately round shape is a bubble

32. The image processing apparatus according to claim 30, wherein the approximately round shape is a bubble.

33. An image processing apparatus including:

an image signal inputting unit configured to input an image signal based on an image captured by a medical appliance having an image capturing function;

an image dividing unit configured to divide an image captured by the medical appliance into a plurality of areas based on the image signal inputted by the image signal inputting unit;

a feature value calculating unit configured to calculate one or more feature values in each of the plurality of areas divided by the image dividing unit;

an area classifying unit configured to classify each of the plurality of areas into any of a plurality of classes based on the feature value calculated at the feature value calculating unit and a predetermined classifying criterion;

an area detecting unit configured to detect an area classified into a predetermined class previously set as a class having a structurally definite feature among the plurality of classes from the plurality of areas; and

a classifying criterion setting unit configured to set the predetermined classifying criterion in the area classifying unit based on the feature value of the area detected in the area detecting unit.

34. The image processing apparatus according to claim 33, wherein the predetermined class is at least either a bubble class or a villi class.

35. The image processing apparatus according to claim 33, wherein the feature value has at least either of the feature value relating to a color or the feature value relating to a texture.

36. An image processing method including:

an image inputting step for inputting an image captured by a medical appliance having an image capturing function;

an area dividing step for dividing the image into a plurality of areas;

a feature value calculating step for calculating one or more feature values from each of the plurality of areas; and

an area classifying step for classifying each of the plurality of areas into either an area in which a surface of a biological mucosa is captured or an area in which a non-biological mucosa is captured based on the feature value.

40. The image processing method according to claim 36, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

43. The image processing method according to claim 36, further including a determining step for determining whether a surface of a biological mucosa is captured in the image or not based on the classification result of each of the plurality of areas at the area classifying step.

46. The image processing method according to claim 43, further including:

a classification determining value calculating step for calculating a proportion of a group of areas classified into a predetermined class among the plurality of different classes in the plurality of areas based on the classified result by the area classifying step; and

an image classifying step for classifying the image having the group of areas classified into the predetermined class based on the proportion calculated at the classification determining value calculating step and a predetermined threshold relating to the proportion;

wherein the determining step determines that the image is an image in which a biological mucosa is not sufficiently captured if the proportion is a predetermined threshold or less, and determines that the image is an image in which a biological mucosa is sufficiently captured if the proportion is more than the predetermined threshold, based on the classification result at the image classifying step.

37. An image processing method including:

an image inputting step for inputting an image captured by a medical appliance having an image capturing function;

an area dividing step for dividing the image into a plurality of areas;

a feature value calculating step for calculating one or more feature values from each of the plurality of areas; and

an area classifying step for classifying each area of the plurality of areas into any one of a plurality of different classes based on the feature value;

wherein the area classifying step classifies each area of the plurality of areas into any of an area in which a surface of a biological mucosa is captured, an area in which a non-biological mucosa is captured, and an area which is neither the surface of the biological mucosa nor the non-biological mucosa.

41. The image processing method to claim 37, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

44. The image processing method according to claim 37, further including a determining step for determining whether a surface of a biological mucosa is captured in the image or not based on the classification result of each of the plurality of areas at the area classifying step.

47. The image processing method according to claim 44, further including:

a classification determining value calculating step for calculating a proportion of a group of areas classified in a predetermined class among the plurality of different classes in the plurality of areas based on classification result at the area classifying step; and

an image classifying step for classifying the image having the group of areas classified into the predetermined class based on the proportion calculated at the classification determining value calculating step and a predetermined threshold relating to the proportion;

wherein the determining step determines that the image is an image in which a biological mucosa is not sufficiently captured if the proportion is a predetermined threshold or less, and determines that the image is an image in which a biological mucosa is sufficiently captured if the proportion is more than the predetermined threshold, based on the classification result at the image classifying step.

38. An image processing method including:

an image inputting step for inputting an image captured by a medical appliance having an image capturing function;

an area dividing step for dividing the image into a plurality of areas;

a feature value calculating step for calculating one or more feature values from each of the plurality of areas;

an area classifying step for classifying each area of the plurality of areas into any one class among a plurality of different classes based on the feature value;

an excluded class setting step for setting combinations of excluded classes which are not permitted to be mixed on the image in the plurality of different classes; and

a preferential class setting step for setting which class is to be preferred among the combinations of the excluded classes;

wherein if an area classified into any class of the combinations of the excluded classes set at the excluded class setting step is present, the area classifying step classifies the area into a class set at the preferential class setting step.

39. The image processing method according to claim 38, further including:

a classification determining value calculating step for calculating a proportion of a group of areas classified in one class among the classes included in the combinations of the excluded classes in the plurality of areas based on the classification result by the area classifying step;

wherein the preferential class setting step sets which class among the combinations of excluded classes is to be preferred by comparing the proportion calculated at the classification determining value calculating step and a predetermined threshold relating to the proportion.

42. The image processing method to claim 38, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

45. The image processing method according to claim 39, further including a determining step for determining whether a surface of a biological mucosa is captured in the image or not based on the classification result of each of the plurality of areas at the area classifying step.

48. The image processing method according to claim 45, further including:

a classification determining value calculating step for calculating a proportion of a group of areas classified in a predetermined class among the plurality of different classes in the plurality of areas based on classification result at the area classifying step; and

an image classifying step for classifying the image having the group of areas classified into the predetermined class based on the proportion calculated at the classification determining value calculating step and a predetermined threshold relating to the proportion;

wherein the determining step determines that the image is an image in which a biological mucosa is not sufficiently captured if the proportion is a predetermined threshold or less, and determines that the image is an image in which a biological mucosa is sufficiently captured if the proportion is more than the predetermined threshold, based on the classification result at the image classifying step.

49. An image processing method including:

an image inputting step for inputting an image captured by a medical appliance having an image capturing function;

an area dividing step for dividing the image into a plurality of areas;

a feature value calculating step for calculating one or more feature values in each of the plurality of areas;

an area classifying step for identifying which class of a plurality of classes each of the plurality of areas belongs to based on the feature value and classifying each of the plurality of areas by the identification result; and

an image-captured organ estimating step for estimating an organ whose image is captured by the medical appliance based on the classification result at the area classifying step.

50. The image processing method according to claim 49, further including:

a classification determining value calculating step for calculating a proportion of a group of areas classified in a predetermined class among the plurality of classes in the plurality of areas based on the classification result at the area classifying step;

an image classifying step for classifying the image having the group of areas classified into the predetermined class based on the proportion calculated at the classification determining value calculating step and a predetermined threshold relating to the proportion;

wherein the image-captured organ estimating step identifies the organ captured in the image based on the classification result at the image classifying step.

51. The image processing method according to claim 50, wherein the plurality of classes has at least a gastric mucosa class, a villi class, and a feces class.

52. The image processing method according to claim 51, wherein, if the predetermined class is the gastric mucosa class, the identifying unit determines that the organ whose image is captured in the image is the gaster.

53. The image processing method according to claim 51, wherein, if the predetermined class is the villi class, the identifying unit determines that the organ whose image is captured in the image is the small intestine.

54. The image processing method according to claim 51, wherein, if the predetermined class is the feces class, the identifying unit determines that the organ whose image is captured in the image is the large intestine.

55. The image processing method according to claim 49, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

56. An image processing method including:

an image dividing step for dividing the image captured by the medical appliance into a plurality of areas based on the image signal inputted at the image signals inputting unit configured to input an image signal according to an image captured by the medical appliance having an image capturing function;

a feature value calculating step for calculating one or more feature values in each of a plurality of areas divided at the image dividing step;

a first area classifying step for classifying each of the plurality of areas into any of a plurality of classes based on the feature value calculated at the feature value calculating step and a predetermined first classifying criterion;

a classifying criterion setting step for setting a second classifying criterion based on the feature value and the classification result at the first area classifying step; and

a second area classifying step for classifying each of the plurality of areas into any of the plurality of classes based on the feature value and the second classifying criterion.

57. The image processing method according to claim 56, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

58. The image processing method according to claim 56, wherein the first area classifying step classifies each of the plurality of areas into any of the plurality of classes by using a statistical discriminator which uses a parameter for determining the first classifying criterion, and the second area classifying step classifies each of the plurality of areas into any of the plurality of classes by using a statistical discriminator which uses a parameter for determining the second classifying criterion.

59. An image processing method including:

an image dividing step for dividing the image captured by the medical appliance into a plurality of areas based on the image signal inputted by the image signal inputting unit configured to input an image signal according to an image captured by the medical appliance having an image capturing function;

a feature value calculating step for calculating one or more feature values in each of a plurality of areas divided at the image dividing step;

a first area classifying step for classifying each of the plurality of areas into any of a plurality of classes based on the feature value calculated at the feature value calculating step and a predetermined first classifying criterion;

an evaluated value calculating step for evaluating the classification result at the first area classifying step of one area among the plurality of areas by calculating an evaluated value based on the classification result at the first area classifying step of the area placed near the one area; and

a second area classifying step for classifying the one area into any of the plurality of classes based on the evaluated value at the evaluated value calculating step.

60. The image processing method according to claim 59, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

61. An image processing method including:

an image dividing step for dividing the image captured by the medical appliance into a plurality of areas based on the image signal inputted at the image signals inputting unit configured to input an image signal according to an image captured by the medical appliance having an image capturing function;

a feature value calculating step for calculating one or more feature values in each of the plurality of areas divided at the image dividing step;

a notice area setting step for setting an area among the plurality of areas as a notice area;

a close circumference area detecting step for detecting a close circumference area which is an area at a predetermined distance from the notice area;

an approximately round shape detecting step for detecting a presence of at least a part of a contour part of the approximately round shape based on the feature value in the close circumference area; and

an area extracting step for extracting the notice area, if the approximately round shape is detected at the approximately round shape detecting step.

62. The image processing method according to claim 61, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

63. The image processing method according to claim 61, wherein the approximately round shape detecting step detects an approximately round shape if it is determined that a proportion of an area in which at least a part of the contour part of the approximately round shape is a predetermined threshold or more in the close circumference area, and the area extracting step extracts the notice area as an area in which a center part of the approximately round shape exists.

64. The image processing method according to claim 61, wherein the approximately round shape is a bubble.

65. The image processing method according to claim 63, wherein the approximately round shape is a bubble.

66. An image processing method including:

an image dividing step for dividing the image captured by the medical appliance into a plurality of areas based on the image signal inputted by the image signal inputting unit configured to input an image signal according to an image captured by the medical appliance having an image capturing function;

a feature value calculating step for calculating one or more feature values in each of the plurality of areas divided at the image dividing step;

an area classifying step for classifying each of the plurality of areas into any of a plurality of classes based on the feature value calculated at the feature value calculating step and a predetermined classifying criterion;

an area detecting step for detecting an area classified into a predetermined class previously set as a class having a structurally definite feature among the plurality of classes from the plurality of areas; and

a classifying criterion setting step for setting the predetermined classifying criterion at the area classifying step based on the feature value of the area detected at the area detecting step.

67. The image processing apparatus according to claim 66, wherein the feature value has at least either the feature value relating to a color or the feature value relating to a texture.

68. The image processing method according to claim 66, wherein the predetermined class is at least either a bubble class or a villi class.

69. An image processing method including:

inputting an image captured by a medical appliance;

dividing the image into a plurality of areas;

calculating one or more feature values from each of the plurality of areas; and

classifying each of the plurality of areas into either an area in which a surface of a biological mucosa is captured or an area in which a non-biological mucosa is captured based on the feature value.

70. An image processing method including:

inputting an image captured by a medical appliance;

dividing the image into a plurality of areas;

calculating one or more feature values from each of the plurality of areas; and

classifying each area of the plurality of areas into any one class among a plurality of different classes based on the feature value and classifying each area of the plurality of areas into any of an area in which a surface of a biological mucosa is captured, an area in which a non-biological mucosa is captured, and an area which is neither the surface of the biological mucosa nor the non-biological mucosa.

71. An image processing method including:

inputting an image captured by a medical appliance;

dividing the image into a plurality of areas;

calculating one or more feature values from each of the plurality of areas;

classifying each area of the plurality of areas into any one class among a plurality of different classes based on the feature value;

setting combinations of excluded classes which are not permitted to be mixed on the image in the plurality of different classes;

setting one class to be preferentially classified among the combinations of the excluded classes; and

classifying the area into the one class, if an area classified into any class of the combinations of the excluded classes is present.

72. An image processing method including:

inputting an image captured by a medical appliance;

dividing the image into a plurality of areas;

calculating one or more feature values in each of the plurality of areas;

identifying which class of a plurality of classes each of the plurality of areas belongs to based on the feature value and classifying each of the plurality of areas by the identification result; and

estimating an organ whose image is captured by the medical appliance based on the classification result.

73. An image processing method including:

dividing the image captured by the medical appliance into a plurality of areas based on the image signal inputted at an image signals inputting unit configured to input an image signal according to an image captured by a medical appliance;

calculating one or more feature values in each of a plurality of areas;

classifying each of the plurality of areas into any of a plurality of classes based on the feature value and a predetermined first classifying criterion;

setting a second classifying criterion based on the feature value and the classification result; and

classifying each of the plurality of areas into any of the plurality of classes based on the feature value and the second classifying criterion.

74. An image processing method including:

inputting an image signal according to an image captured by a medical appliance and dividing the image captured by the medical appliance into a plurality of areas based on the image signal;

calculating one or more feature values in each of a plurality of areas;

classifying each of the plurality of areas into any of a plurality of classes based on the feature value and a predetermined first classifying criterion;

evaluating the classification result of one area among the plurality of areas by calculating an evaluated value based on the classification result of the area placed near the one area; and

classifying the one area into any of the plurality of classes based on the evaluated value.

75. An image processing method including:

inputting an image signal according to an image captured by a medical appliance and dividing the image captured by the medical appliance into a plurality of areas based on the image signal;

calculating one or more feature values in each of the plurality of areas;

setting an area among the plurality of areas as a notice area;

detecting a close circumference area which is an area at a predetermined distance from the notice area;

detecting a presence of at least a part of a contour part of the approximately round shape based on the feature value in the close circumference area; and

extracting the notice area, if the approximately round shape is detected.

76. An image processing method including:

inputting an image signal according to an image captured by a medical appliance and dividing the image captured by the medical appliance into a plurality of areas based on the image signal;

calculating one or more feature values in each of the plurality of areas;

classifying each of the plurality of areas into any of a plurality of classes based on the feature value and a predetermined classifying criterion;

detecting an area group classified into a predetermined class previously set as a class having a structurally definite feature among the plurality of classes from the plurality of areas; and

setting the predetermined classifying criterion based on the feature value of the area group.