IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND COMPUTER-READABLE RECORDING MEDIUM

• US 20120051612A1
• Filed: 08/23/2011
• Published: 03/01/2012
• Est. Priority Date: 08/24/2010
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Corporation
• Inventors: KITAMURA, Makoto, KANDA, Yamato, MATSUDA, Takehiro, KONO, Takashi, HIROTA, Masashi
• Granted Patent: US 8,620,043 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/30028 Colon; Small intestine
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models

Abstract

An image processing apparatus includes a gradient strength calculating unit that calculates a gradient strength of respective pixel values based on an intraluminal image; an extracting unit that extracts a closed region satisfying conditions that the pixel of which gradient strength is a predetermined value or more is not included in the region and a boundary of the region does not bend with a predetermined curvature or higher toward an inner side of the region; and a detecting unit that detects an abnormal portion inside the region. The extracting unit includes a setting unit that sets an initial shape of the region; an energy calculating unit that calculates values of types of energy including at least energies determined respectively by an outer shape of the region and the gradient strength; and an energy-weighted sum calculating unit that calculates a weighted sum of the types of energy.

Claims

1. An image processing apparatus comprising:

a gradient strength calculating unit that calculates a gradient strength of a pixel value of each pixel based on an intraluminal image that is a captured image of an intralumen;

a closed region extracting unit that extracts a closed region from the intraluminal image, the closed region satisfying conditions that the pixel of which gradient strength is a predetermined value or more is not included in the closed region and a boundary of the closed region does not bend with a predetermined curvature or higher toward an inner side of the closed region; and

an abnormal portion detecting unit that detects an abnormal portion inside the closed region, wherein

the closed region extracting unit includes

an initial closed region setting unit that sets an initial shape of the closed region;

an energy calculating unit that calculates values of a plurality of types of energy including at least energy determined by an outer shape of the closed region and energy determined by the gradient strength in the closed region;

an energy-weighted sum calculating unit that calculates a weighted sum of the plurality of types of energy; and

a closed region updating unit that updates a shape of the closed region within an update range based on the weighted sum, and

the closed region updating unit includes an update range determining unit that determines the update range in which the shape of the closed region is updated based on any one of the values of the plurality of types of energy.

2. The image processing apparatus according to claim 1, wherein the energy calculating unit includes an edge inclusion energy calculating unit that calculates a value of edge inclusion energy indicating a larger value as more pixels having the gradient strength equal to or higher than the predetermined value are present in the closed region.

3. The image processing apparatus according to claim 2, wherein the edge inclusion energy calculating unit includes a closed region gradient strength calculating unit that calculates a closed region gradient strength based on the gradient strength in the closed region, and calculates the value of the edge inclusion energy indicating a larger value as the closed region gradient strength becomes larger.

4. The image processing apparatus according to claim 2, wherein the edge inclusion energy calculating unit includes an edge extracting unit that extracts a pixel having the gradient strength equal to or higher than the predetermined value as an edge, and calculates the value of the edge inclusion energy based on the edge in the closed region.

5. The image processing apparatus according to claim 4, wherein

the edge inclusion energy calculating unit includes

a bending point detecting unit that detects a bending point of the edge;

and

an end point detecting unit that detects an end point of the edge, and

the edge inclusion energy calculating unit calculates the value of the edge inclusion energy based on an inclusion state of the bending point and the end point in the closed region.

6. The image processing apparatus according to claim 5, wherein

the closed region is specified as a region obtained by connecting a plurality of control points, and the shape of the closed region is updated by moving the control points, and

the edge inclusion energy calculating unit includes an outer product calculating unit that calculates an outer product of vectors drawn from the control points to the bending point and the end point, and

the edge inclusion energy calculating unit calculates the value of the edge inclusion energy based on a value of the outer product.

7. The image processing apparatus according to claim 3, wherein the edge inclusion energy calculating unit includes an increase rate calculating unit that calculates an increase rate of the gradient strength in the closed region before and after update of the shape, and

the edge inclusion energy calculating unit calculates the value of the edge inclusion energy based on the increase rate.

8. The image processing apparatus according to claim 1, wherein the energy calculating unit includes a curvature energy calculating unit that calculates a value of curvature energy indicating a larger value as the boundary of the closed region bends more inwardly.

9. The image processing apparatus according to claim 8, wherein

the closed region is specified as a region obtained by connecting a plurality of control points, and the shape of the closed region is updated by moving the control points, and

the curvature energy calculating unit includes an outer product energy calculating unit that calculates a value of outer product energy based on an outer product of vectors drawn from each of the control points to another control point adjacent thereto, and

the curvature energy calculating unit determines the value of the outer product energy to be the value of the curvature energy.

10. The image processing apparatus according to claim 8, wherein

the closed region is specified as a region obtained by connecting a plurality of control points, and the shape of the closed region is updated by moving the control points, and

the curvature energy calculating unit includes a general outer product energy calculating unit that calculates a value of general outer product energy based on an outer product of vectors drawn from each of the control points to another control point apart therefrom by a predetermined distance or larger, and

the curvature energy calculating unit determines the value of the general outer product energy to be the value of the curvature energy.

11. The image processing apparatus according to claim 8, wherein

the closed region is specified as a region obtained by connecting a plurality of control points, and the shape of the closed region is updated by moving the control points, and

the curvature energy calculating unit includes a multiple outer product energy calculating unit that calculates a value of outer product energy based on an outer product of vectors drawn from each of the control points to be processed to another control point apart therefrom by a predetermined distance or larger, and when the value of the outer product energy is smaller than a predetermined threshold value, and repeats process for calculating the value of the outer product energy based on an outer product of vectors drawn from each of the control points to be processed to yet another control point closer thereto than the control point apart therefrom by the predetermined distance or larger, and

the curvature energy calculating unit determines the value of the outer product energy calculated by the multiple outer product energy calculating unit to be the value of the curvature energy.

12. The image processing apparatus according to claim 8, wherein

the closed region is specified as a region obtained by connecting a plurality of control points, and the shape of the closed region is updated by moving the control points, and

the curvature energy calculating unit includes a convex energy calculating unit that calculates a value of convex energy based on an inclusion state of vectors between the control points in the closed region, and determines the value of the convex energy to be the value of the curvature energy.

13. The image processing apparatus according to claim 1, wherein

the closed region is specified as a region obtained by connecting a plurality of control points, and the shape of the closed region is updated by moving the control points, and

the update range determining unit includes a control point distance determining unit that calculates a distance between each of the control points and another control point at which at least one of the values of the plurality of types of energy is equal to or higher than a predetermined threshold value, and

the update range determining unit selects a control point to be moved next time among the control points based on the distance to determine the update range.

14. The image processing apparatus according to claim 1, wherein the update range determining unit includes a shape information calculating unit that calculates shape information of the closed region, and

the update range determining unit determines the update range based on the shape information of the closed region.

15. The image processing apparatus according to claim 14, wherein the shape information calculating unit includes an area calculating unit that calculates an area of the closed region.

16. The image processing apparatus according to claim 14, wherein the shape information calculating unit includes a perimeter calculating unit that calculates a perimeter of the closed region.

17. The image processing apparatus according to claim 14, wherein the shape information calculating unit includes a curvature calculating unit that calculates a curvature of the closed region.

18. The image processing apparatus according to claim 1, wherein the update range determining unit includes an edge information detecting unit that extracts a pixel having at least the gradient strength equal to or higher than the predetermined threshold value as an edge, and

the update range determining unit determines the update range based on the edge.

19. The image processing apparatus according to claim 18, wherein the edge information detecting unit detects an end point of the edge and a bending point of the edge, includes an end point and bending point distance calculating unit that calculates a distance from the end point of the edge or the bending point of the edge, and

the update range determining unit determines the update range based on the distance from the end point of the edge or the bending point of the edge.

20. The image processing apparatus according to claim 18, wherein

the update range determining unit includes an edge distance calculating unit that calculates a distance from the edge, and

the update range determining unit determines the update range based on the distance from the edge.

21. The image processing apparatus according to claim 1, further comprising:

a region integrating unit that integrates the closed region extracted by the closed region extracting unit so as to satisfy the conditions.

22. The image processing apparatus according to claim 21, wherein

the region integrating unit includes

an integrating unit that integrates closed regions partially overlapping with each other within the closed region;

and

a post-integration energy calculating unit that calculates the values of the plurality of types of energy for the closed region thus integrated, and

the region integrating unit determines whether to permit integration based on the values of the plurality of types of energy calculated by the post-integration energy calculating unit.

23. An image processing method comprising:

calculating a gradient strength of a pixel value of each pixel based on an intraluminal image that is a captured image of an intralumen;

setting an initial shape of a closed region, the closed region satisfying conditions that the pixel of which gradient strength is a predetermined value or more is not included in the closed region and a boundary of the closed region does not bend with a predetermined curvature or higher toward an inner side of the closed region;

extracting the closed region from the intraluminal image; and

detecting an abnormal portion inside the closed region, wherein

the extracting includes

calculating values of a plurality of types of energy including at least energy determined by an outer shape of the closed region and energy determined by the gradient strength in the closed region;

calculating a weighted sum of the plurality of types of energy;

determining an update range in which the shape of the closed region is updated based on any one of the values of the plurality of types of energy; and

updating the shape of the closed region within the update range based on the weighted sum.

24. A non-transitory computer-readable recording medium with an executable program stored thereon, wherein the program instructs a processor to perform:

calculating a gradient strength of a pixel value of each pixel based on an intraluminal image that is a captured image of an intralumen;

setting an initial shape of a closed region, the closed region satisfying conditions that the pixel of which gradient strength is a predetermined value or more is not included in the closed region and a boundary of the closed region does not bend with a predetermined curvature or higher toward an inner side of the closed region;

extracting the closed region from the intraluminal image; and

detecting an abnormal portion inside the closed region, wherein

the extracting includes

calculating values of a plurality of types of energy including at least energy determined by an outer shape of the closed region and energy determined by the gradient strength in the closed region;

calculating a weighted sum of the plurality of types of energy;

determining an update range in which the shape of the closed region is updated based on any one of the values of the plurality of types of energy; and

updating the shape of the closed region within the update range based on the weighted sum.