Medical Image Processing Apparatus, Luminal Image Processing Apparatus, Luminal Image Processing Method, and Programs for the Same

• US 20090208071A1
• Filed: 02/10/2006
• Published: 08/20/2009
• Est. Priority Date: 02/15/2005
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Corporation
• Inventors: Nishimura, Hirokazu, Hasegawa, Jun, Nonami, Tetsuo, Inoue, Ryoko, Tanaka, Hideki
• Granted Patent: US 8,055,033 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: A61B 1/2733 Oesophagoscopes
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/20168 Radial search
• CPC Class Codes: G06T 2207/30092 Stomach; Gastric
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

There is provided a medical image processing apparatus including an image-extracting section extracting a frame image from in vivo motion picture data picked up by an in vivo image pickup device or a plurality of consecutively picked-up still image data, and an image analysis section analyzing the frame image extracted by the image-extracting section to output an image analysis result. The image analysis section includes a first biological-feature detection section detecting a first biological feature, a second biological-feature detection section detecting, based on a detection result obtained by the first biological feature detection section, a second biological feature in a frame image picked up temporally before or after the image used for detection by the first biological feature detection section; and a condition determination section making a determination for a biological condition based on a detection result obtained by the second biological feature detection section to output the determination.

Claims

1. A medical image processing apparatus comprising:

an image extracting section that extracts a frame image from in vivo motion picture data picked up by an in vivo image pickup device or a plurality of consecutively picked-up still image data; and

an image analysis section that analyzes the frame image extracted by the image extracting section to output an image analysis result,

the image analysis section comprising;

a first biological feature detection section that detects a first biological feature;

a second biological feature detection section that detects, on the basis of a detection result obtained by the first biological feature detection section, a second biological feature in a frame image picked up temporally before or after the image used for detection by the first biological feature detection section; and

a condition determination section that makes a determination for a biological condition on the basis of a detection result obtained by the second biological feature detection section to output the determination.

2. The medical image processing apparatus according to claim 1, wherein on the basis of the detection result obtained by the first biological feature detection section, the second biological feature detection section acquires a predetermined number of frame images to execute a process of detecting the second biological feature on the frame image.

3. The medical image processing apparatus according to claim 1, wherein

on the basis of the detection result obtained by the first biological feature detection section, the second biological feature detection section sequentially acquires a frame image picked up temporally before or after the frame image processed by the first biological feature detection section, and

on the basis of the detection result obtained by the first biological feature detection section by processing the frame image acquired, the second biological feature detection section suspends the acquisition of the frame image.

4. The medical image processing apparatus according to claim 1 , wherein the condition determination section makes a determination for the biological condition by determining whether or not the Barrett esophagus as an intraesophageal disease is present.

5. The medical image processing apparatus according to claim 4, wherein the first biological feature detected by the first biological feature detection section is an EG junction located in the esophagus as a boundary between the stomach and the esophagus.

6. The medical image processing apparatus according to claim 5, wherein the first biological feature detection section detects the EG junction by extracting coordinates of end points of palisade vessels and obtaining a palisade vessel end point boundary line formed of a segment connecting the extracted end point coordinates.

7. The medical image processing apparatus according to claim 6, wherein when a segment obtained by executing a thinning process on the frame image has at least a predetermined length, the first biological feature detection section determines the segment to be the palisade vessel.

8. The medical image processing apparatus according to claim 7, wherein the first biological feature detection section determines the segment obtained by executing the thinning process on the frame image data to be the palisade vessel, further taking into account the numbers of branching points, intersecting points, and bending points on the segment.

9. The medical image processing apparatus according to claim 8, wherein the first biological feature detection section determines the segment obtained by executing the thinning process on the frame image data to be the palisade vessel, further taking into account an angle between a segment connecting opposite ends of the segment and a vector connecting a dark portion center of an image dark portion of the frame image to one of the opposite ends which is closer to the image dark portion.

10. The medical image processing apparatus according to claim 5, wherein the second biological feature detected by the second biological feature detection section is an epithelium boundary in the esophagus.

11. The medical image processing apparatus according to claim 10, wherein the condition determination section determines whether or not the Barrett esophagus is present on the basis of a distance between a plurality of intersecting points between the epithelium boundary and each of a plurality of radial lines radiating from a predetermined point and between the EG junction and the radial line.

12. The medical image processing apparatus according to claim 11, wherein the condition determination section determines whether or not the Barrett esophagus is present, taking into account distances between a predetermined point and the epithelium boundary crossing each of the plurality of radial lines radiating from the predetermined point or distances between the EG junction and the predetermined point.

13. The medical image processing apparatus according to claim 10, wherein the condition determination section determines whether or not the Barrett esophagus is present, further on the basis of the number of points at which the palisade vessel crosses the epithelium boundary.

14. The medical image processing apparatus according to claim 13, wherein when a segment obtained by executing a thinning process on the frame image has at least a predetermined length, the first biological feature detection section determines the segment to be the palisade vessel.

15. The medical image processing apparatus according to claim 14, wherein the first biological feature detection section determines the segment obtained by executing the thinning process on the frame image data to be the palisade vessel, further taking into account the numbers of branching points, intersecting points, and bending points on the segment.

16. The medical image processing apparatus according to claim 15, wherein the first biological feature detection section determines the segment obtained by executing the thinning process on the frame image data to be the palisade vessel, further taking into account an angle between a segment connecting opposite ends of the segment and a vector connecting a dark portion center of an image dark portion of the frame image to one of the opposite ends which is closer to the image dark portion.

17. The medical image processing apparatus according to claim 1, wherein

the first biological feature detected by the first biological feature detection section is the cardia serving as an inlet through which the apparatus moves from the esophagus into the cardia, an inlet of the stomach,

on the basis of the detection result obtained by the first biological feature detection section, the second biological feature detection section detects the second biological feature in the frame image picked up temporally before the image used for detection by the first biological feature detection section.

18. The medical image processing apparatus according to claim 17, wherein the first biological feature detection section detects a thin line obtained by executing a thinning process on the frame image, as the closed cardia on the basis of a concentration level of the calculated number of branching points or intersecting points.

19. The medical image processing apparatus according to claim 18, wherein the first biological feature detection section detects the cardia as the open cardia on the basis of a thinned image generated by executing an edge extraction process and a binarization on the frame image and a dark portion image obtained by executing a dark portion extraction process of extracting an image dark portion on the frame image.

20. The medical image processing apparatus according to claim 19, wherein the cardia is detected on the basis of a region in which or an angle at which a thin line in the thinned image is present in a circumferential direction around a feature point in the dark portion.

21. The medical image processing apparatus according to claim 1, wherein the first biological feature detected by the first biological feature detection section is the epithelium boundary corresponding to a boundary between the squamous epithelium in the esophagus and a columnar epithelium in the stomach.

22. The medical image processing apparatus according to claim 21, wherein the condition determination section makes a determination for the biological condition only for the frame image in which the epithelium boundary has been detected, on the basis of the detection result obtained by the second biological feature detection section.

23. A medical image processing method comprising:

a step of extracting a frame image from in vivo motion picture data picked up by an in vivo image pickup device or a plurality of consecutively picked-up still image data;

a step of analyzing the extracted frame image to detect a first biological feature;

a step of detecting, on the basis of a result of the detection of the first biological feature, a second biological feature in a frame image picked up temporally before or after the image used for detection by the first biological feature detection section; and

a step of making a determination for a biological condition on the basis of a result of the detection of the second biological feature to output the determination.

24. A program allowing a computer to execute:

a function of extracting a frame image from in vivo motion picture data picked up by an in vivo image pickup device or a plurality of consecutively picked-up still image data;

a function of analyzing the extracted frame image to detect a first biological feature;

a function of detecting, on the basis of a result of the detection of the first biological feature, a second biological feature in a frame image picked up temporally before or after the image used for detection by the first biological feature detection section; and

a function of making a determination for a biological condition on the basis of a result of the detection of the second biological feature to output the determination.

25. A luminal image processing apparatus comprising:

a feature value calculating section that calculates a predetermined feature value by executing image processing on one or a plurality of intraluminal images obtained by picking up an image of the gastrointestinal tract; and

a boundary detection section that detects a boundary of the gastrointestinal tract on the basis of the calculated feature value.

26. The luminal image processing apparatus according to claim 25, further comprising a determination section that determines that the intraluminal image shows a part extending from the esophagus to the cardia, on the basis of a detection result obtained by the boundary detection portion.

27. The luminal image processing apparatus according to claim 25, wherein the predetermined feature value is a color tone of the one or plurality of intraluminal images.

28. The luminal image processing apparatus according to claim 25, wherein the predetermined feature value is a brightness of the one or plurality of intraluminal images.

29. The luminal image processing apparatus according to claim 25, wherein the boundary is the EG junction.

30. The luminal image processing apparatus according to claim 25, wherein the feature value calculation section calculates the feature value for pixels in the one or plurality of intraluminal images other than dark portion pixels and halation pixels.

31. The luminal image processing apparatus according to claim 25, wherein if the predetermined feature value is calculated from the plurality of intraluminal images, the determination section determines that the image shows the boundary when a differential value of moving average of the calculated predetermined feature values is at least a predetermined threshold.

32. The luminal image processing apparatus according to claim 25, wherein the feature value calculation section executes image processing on pixels in a predetermined region in each of the one or plurality of intraluminal images to calculate the predetermined feature value.

33. The luminal image processing apparatus according to claim 25, wherein the predetermined feature value is an area of a dark portion region or a non-dark portion region in the one or plurality of intraluminal images.

34. The luminal image processing apparatus according to claim 33, wherein

the boundary is the open cardia, and

the boundary detection section detects the boundary by comparing the area with a predetermined threshold.

35. The luminal image processing apparatus according to claim 25, wherein the predetermined feature value is a shape of the dark portion region in the one or plurality of intraluminal images.

36. The luminal image processing apparatus according to claim 35, wherein the boundary detection section detects the boundary depending on whether or not the shape is a circle.

37. The luminal image processing apparatus according to claim 35, wherein

the shape of the dark portion region includes a shape of a boundary of the dark portion region and an edge portion, and

the boundary detection section detects the boundary by comparing a coincidence between the boundary and the edge portion with a predetermined threshold.

38. The luminal image processing apparatus according to claim 35, wherein

the shape of the dark portion region includes the edge portion of the dark portion region, and

the boundary detection section detects the boundary by comparing a rate at which the edge portion is present around a predetermined point in the dark portion region, with a predetermined threshold.

39. The luminal image processing apparatus according to claim 38, wherein the boundary detection section determines the rate on the basis of whether or not the edge portion is present in a plurality of predetermined areas in each of the one or plurality of intraluminal images.

40. The luminal image processing apparatus according to claim 38, wherein the boundary detection section determines the rate on the basis of an angular range in which the edge portion is present around a predetermined point in the dark portion region.

41. The luminal image processing apparatus according to claim 25, wherein the predetermined feature value is an area of the dark portion region in the one or plurality of intraluminal images.

42. The luminal image processing apparatus according to claim 33, wherein

the boundary is the closed cardia, and

the boundary detection section detects the boundary by comparing the area with a predetermined threshold.

43. The luminal image processing apparatus according to claim 42, wherein the boundary detection section detects the boundary by executing a labeling process to label a plurality of regions of a dark portion pixel in each of the one or plurality of intraluminal images and determining whether or not an area of one of the labeled plurality of regions which has the largest area is smaller than the predetermined threshold.

44. The luminal image processing apparatus according to claim 25, wherein the boundary detection section detects the boundary by executing a thinning process on the dark portion pixel in each of the one or plurality of intraluminal images, calculating branching or intersecting points on each segment obtained by the thinning process, and executing the detection on the basis of a concentration level of the branching or intersecting points in each of the images.

45. The luminal image processing apparatus according to claim 44, wherein

the boundary is the closed cardia, and

the boundary detection section detects the boundary by comparing the concentration level with a predetermined threshold.

46. A luminal image processing method comprising:

a step of calculating a predetermined feature value by executing image processing on one or a plurality of intraluminal images obtained by picking up an image of the gastrointestinal tract; and

a step of detecting a boundary of the gastrointestinal tract on the basis of the calculated feature value.

47. A program allowing a computer to execute:

a function of calculating a predetermined feature value from one or a plurality of intraluminal images obtained by picking up an image of the gastrointestinal tract; and

a function of detecting a boundary of the gastrointestinal tract on the basis of the calculated feature value.