Image processing apparatus for identifying whether or not microstructure in set examination region is abnormal, image processing method, and computer-readable recording device

1. An image processing apparatus, comprising:

a processor comprising hardware, wherein the processor is configured to:

estimate imaging distances to a subject shown in pixels within an intraluminal image;

set a plurality of rectangular examination candidate regions in the intraluminal image; and

set at least one of the plurality of rectangular examination candidate regions as an examination region based on a determination that a distribution of the imaging distances to the subject shown in the pixels within the at least one of the plurality of rectangular examination candidate regions is within a predetermined range;

identify whether or not a microstructure of the subject shown in the examination region is abnormal, by using texture feature data that enables identification of an abnormality in the microstructure of the subject shown in the examination region, the texture feature data being specified according to the examination region; and

generate a processed image for display, the processed image showing a result of the identification of the abnormality in the microstructure of the subject shown in the examination region.

2. The image processing apparatus according to claim 1 , wherein the processor is configured to:

acquire a representative imaging distance to the subject shown at a position where the at least one of the plurality of rectangular examination candidate regions is to be set; and

set the at least one of the plurality of rectangular examination candidate regions of a size according to the representative imaging distance.

3. The image processing apparatus according to claim 1 , wherein the processor is configured to:

calculate a representative imaging distance gradient of the subject shown at a position where the at least one of the plurality of rectangular examination candidate regions is to be set; and

set the at least one of the plurality of rectangular examination candidate regions of a size according to the representative imaging distance gradient.

4. The image processing apparatus according to claim 1 , wherein the processor is configured to:

calculate a distribution range of the imaging distances to the subject shown in the pixels within the at least one of the plurality of rectangular examination candidate regions; and

set the at least one of the plurality of rectangular examination candidate regions as the examination region based on a determination that the distribution range is equal to or less than a predetermined threshold value.

5. The image processing apparatus according to claim 1 , wherein the processor is configured to:

calculate a variance of the imaging distances to the subject shown in the pixels within the at least one of the plurality of rectangular examination candidate regions;

set the at least one of the plurality of rectangular examination candidate regions as the examination region based on a determination that the variance is equal to or less than a predetermined threshold value.

6. The image processing apparatus according to claim 1 , wherein the processor is configured to:

classify values of the imaging distances into one level or a plurality of levels;

divide the intraluminal image into one region or a plurality of regions, for each region where the subject at a same level of imaging distance is shown; and

set each of the one region or the plurality of regions acquired as an individual examination region.

7. The image processing apparatus according to claim 1 , wherein the processor is configured to:

calculate, as the texture feature data, a particular spatial frequency component that enables identification of the abnormality in the microstructure of the subject shown in the examination region; and

perform statistical classification based on the particular spatial frequency component.

8. The image processing apparatus according to claim 7 , wherein the processor is configured to:

select a particular wavelength component specified according to a degree of absorption or scattering in a living body; and

calculate the particular spatial frequency component with respect to the particular wavelength component.

9. The image processing apparatus according to claim 7 , wherein the processor is configured to:

calculate a ratio between particular wavelength components having different degrees of absorption or scattering in the living body; and

calculate the particular spatial frequency component with respect to the ratio between the particular wavelength components.

10. The image processing apparatus according to claim 7 , wherein the processor is configured to:

acquire a representative imaging distance to the subject shown in the examination region; and

specify a frequency of the particular spatial frequency component according to the representative imaging distance and calculate the particular spatial frequency component.

11. The image processing apparatus according to claim 1 ,

wherein the processor is configured to deform an image in the examination region.

12. The image processing apparatus according to claim 11 , wherein the processor is configured to:

acquire a representative imaging distance to the subject shown in the examination region;

normalize a size of the examination region according to the representative imaging distance;

identify whether or not the microstructure of the subject shown in the examination region is abnormal, by using the texture feature data that enables identification of the abnormality in the microstructure of the subject shown in the examination region, the texture feature data being specified according to the examination region having the size that has been normalized.

13. The image processing apparatus according to claim 11 , wherein the processor is configured to:

estimate three dimensional coordinates for at least three reference points on the subject shown in the examination region, based on the imaging distances and coordinates of corresponding pixels in the intraluminal image; and

transform on the examination region such that an image of the examination region is acquired by imaging the examination region in a plane passing through the at least three reference points from a front at a given distance.

14. The image processing apparatus according to claim 1 , wherein the intraluminal image is formed of a plurality of wavelength components, and wherein the processor is configured to:

select, from the plurality of wavelength components, a low absorbance wavelength component that is a wavelength component with a lowest degree of absorption or scattering in a living body; and

estimate the imaging distances to the subject shown in the pixels within the intraluminal image, based on the low absorbance wavelength component.

15. The image processing apparatus according to claim 1 , wherein the processor is configured to:

set at least one of the plurality of rectangular examination candidate regions not set as an examination region as a non-examination target region; and

exclude the non-examination target region included in the intraluminal image.

16. The image processing apparatus according to claim 15 , wherein the non-examination target region is any one of a dark region, a bright region, and a region where a residue or bubble is shown, in the intraluminal image.

17. An image processing method comprising:

estimating imaging distances to a subject shown in pixels within an intraluminal image;

setting a plurality of rectangular examination candidate regions in the intraluminal image; and

setting the at least one of the plurality of rectangular examination candidate regions as an examination region based on a determination that a distribution of the imaging distances to the subject shown in the pixels within the at least one of the plurality of rectangular examination candidate regions is within a predetermined range; identifying whether or not a microstructure of the subject shown in the examination region is abnormal, by using texture feature data that enables identification of an abnormality in the microstructure of the subject shown in the examination region, the texture feature data being specified according to the examination region; and

generating a processed image for display, the processed image showing a result of the identification of the abnormality in the microstructure of the subject shown in the examination region.

18. A non-transitory computer-readable recording device with an executable program stored thereon, the program instructing a processor to perform a process comprising:

estimating imaging distances to a subject shown in pixels within an intraluminal image;

setting a plurality of rectangular examination candidate regions in the intraluminal image; and

setting at least one of the plurality of rectangular examination candidate regions as an examination region based on a determination that a distribution of the imaging distances to the subject shown in the pixels within the at least one of the plurality of rectangular examination candidate regions is within a predetermined range; identifying whether or not a microstructure of the subject shown in the examination region is abnormal, by using texture feature data that enables identification of an abnormality in the microstructure of the subject shown in the examination region, the texture feature data being specified according to the examination region; and

generating a processed image for display, the processed image showing a result of the identification of the abnormality in the microstructure of the subject shown in the examination region.