Image processing apparatus, image processing method, and computer-readable recording medium
An image processing apparatus includes: a detecting unit that detects regions of interest that are estimated as an object to be detected, from a group of a series of images acquired by sequentially imaging a lumen of a living body, and to extract images of interest including the regions of interest; a neighborhood range setting unit that sets, as a time-series neighborhood range, a neighborhood range of the images of interest in the group of the series of images arranged in time series so as to be wider than an interval between images that are continuous in time series in the group of the series of images; an image-of-interest group extracting unit that extracts an image-of-interest group including identical regions of interest from the extracted images of interest, based on the time-series neighborhood range; and a representative-image extracting unit that extracts a representative image from the image-of-interest group.
1. An image processing apparatus comprising:
a processor comprising hardware, wherein the processor is configured to:
retrieve a series of images acquired by sequential imaging;
detect, in the series of images retrieved, one or more regions of interest based on predetermined criteria;
extract, from the series of images, images of interest including the one or more regions of interest detected;
for each of the images of interest extracted, set, from the series of images, a time-series neighborhood range of images,
wherein the time-series neighborhood range of images includes the each of the images of interest extracted and one or more images from the series of images continuous in time-series with the each of the images of interest extracted;
merge a plurality of time-series neighborhood ranges of images that are at least partly overlapped with one another into a merged time-series neighborhood range of images;
extract, from the images of interest that are included in the merged time-series neighborhood range of images, a group of images of interest;
extract, form the group of images of interest, a representative image; and
output image data of the representative image to a display.
2. The image processing apparatus according to claim 1 ,
wherein the processor is configured to:
acquire information on the one or more regions of interest; and
set the time-series neighborhood range of images based on the information on the one or more regions of interest acquired.
3. The image processing apparatus according to claim 2 ,
wherein the processor is configured to:
classify the one or more regions of interest into types of the regions of interest; and
acquire a classification result of the types of the regions of interest as information on the one or more regions of interest.
4. The image processing apparatus according to claim 3 ,
wherein the processor is configured to:
determine whether the one or more regions of interest are continuous regions of interest that are continuously observable; and
in a case where the one or more regions of interest are the continuous regions of interest, set the time-series neighborhood range of images to be wider than in a case where the one or more regions of interest are not the continuous regions of interest.
5. The image processing apparatus according to claim 4 ,
wherein the processor is configured to:
determine that the continuous regions of interest include a region corresponding to one of bleeding, mucosal abnormality, and vascular abnormality.
6. The image processing apparatus according to claim 3 ,
wherein the processor is configured to:
determine whether the one or more regions of interest are intermittent regions of interest that are intermittently observable; and
in a case where the one or more regions of interest are the intermittent regions of interest, set the time-series neighborhood range of images to be narrower than in a case where the one or more regions of interest are not the intermittent regions of interest.
7. The image processing apparatus according to claim 6 ,
wherein the processor is configured to:
determine that the intermittent regions of interest include a region corresponding to one of redness, a bleeding point, and an ulcer.
8. The image processing apparatus according to claim 2 ,
wherein the processor is configured to:
calculate red to calculate brightness of the one or more regions of interest as the information on the one or more regions of interest; and
set the time-series neighborhood range of images to be narrow as the brightness becomes higher.
9. The image processing apparatus according to claim 8 ,
wherein the processor is configured to:
calculate the brightness based on at least one of contrast and size of each of the one or more regions of interest.
10. The image processing apparatus according to claim 1 ,
wherein the processor is configured to:
detect, from the each of the images of interest extracted, a quantity of an unnecessary region that does not correlate with the one or more regions of interest; and
for the each of the images of interest extracted, set the time-series neighborhood range in accordance with the quantity of the unnecessary region.
11. The image processing apparatus according to claim 1 ,
wherein the processor is configured to:
classify types of an organ shown in the images of interest; and
for the each of the images of interest extracted, set the time-series neighborhood range of images in accordance with the types of the organ.
12. The image processing apparatus according to claim 11 ,
wherein the processor is configured to:
in a case where the types of the organ shown in the images of interest are an organ to be examined, for the each of the images of interest extracted, set the time-series neighborhood range of images to be narrower than in a case where the types of the organ shown in the images of interest are not the organ to be examined.
13. The image processing apparatus according to claim 1 ,
wherein the processor is configured to:
for the each of the images of interest extracted, set the time-series neighborhood range in accordance with a method for displaying the representative image.
14. The image processing apparatus according to claim 13 ,
wherein the processor is configured to:
in a case where the representative image is displayed as a still image, for the each of the images of interest extracted, set the time-series neighborhood range to be wider than in a case where the representative image is displayed as a moving image.
15. The image processing apparatus according to claim 1 ,
wherein the processor is configured to:
calculate a similarity between the regions of interest that are different from one another; and
extract, from the images of interest that are included in the merged time-series neighborhood range of images, the group of images of interest based on the similarity between the regions of interest.
16. The image processing apparatus according to claim 15 ,
wherein the processor is configured to:
extract, from the images of interest that are included in the merged time-series neighborhood range of images, images of interest in which the similarity between the regions of interest different from one another is higher than a threshold, as the group of images.
17. An image processing method comprising:
retrieving a series of images acquired by sequential imaging;
detecting, in the series of images retrieved, one or more regions of interest based on predetermined criteria;
extracting, from the series of images, images of interest including the one or more regions of interest detected;
for each of the images of interest extracted, setting, from the series of images, a time-series neighborhood range of images,
wherein the time-series neighborhood range of images includes the each of the images of interest extracted and one or more images from the series of images continuous in time-series with the each of the images of interest extracted;
merging a plurality of time-series neighborhood ranges of images that are at least partly overlapped with one another into a merged time-series neighborhood range of images;
extracting, from the images of interest that are included in the merged time-series neighborhood range of images, a group of images of interest;
extracting, from the group of images of interest, a representative image; and
outputting image data of the representative image to a display.
18. A non-transitory computer-readable recording medium with an executable program stored thereon, the program causing a computer to at least execute:
retrieving a series of images acquired by sequential imaging;
detecting, in the series of images retrieved, one or more regions of interest based on predetermined criteria;
extracting, from the series of images, images of interest including the one or more regions of interest detected;
for each of the images of interest extracted, setting, from the series of images, a time-series neighborhood range of images,
wherein the time-series neighborhood range of images includes the each of the images of interest extracted and one or more images from the series of images continuous in time-series with the each of the images of interest extracted;
merging a plurality of time-series neighborhood ranges of images that are at least partly overlapped with one another into a merged time-series neighborhood range of images;
extracting, from the images of interest that are included in the merged time-series neighborhood range of images, a group of images of interest;
extracting, from the group of images of interest, a representative image; and outputting image data of the representative image to a display.
19. The image processing apparatus according to claim 1 ,
wherein the processor is configured to:
for the each of the images of interest extracted, set the time-series neighborhood range of images symmetrically with respect to the each of the images of interest extracted.
20. The image processing apparatus according to claim 1 ,
wherein the processor is configured to:
for the each of the images of interest extracted, set the time-series neighborhood range of images so that the each of the images of interest extracted is located first in the time-series neighborhood range of images.