Capsule endoscope image display controller

1. A capsule endoscope image display controller that controls display of an image sequence including a plurality of images captured by a capsule endoscope which moves within digestive organs, said controller comprising:

an image-to-image similarity calculating unit operable to calculate, for each image included in the image sequence, a similarity between the image and a temporally consecutive image;

an amount-of-movement calculating unit operable to calculate, for each image included in the image sequence, an amount of movement of a feature area included in the image;

a video state classifying unit operable to classify, for each image included in the image sequence, a video state of the image into one of a plurality of states including at least the following states, based on the similarity and the amount of movement of the image:

(a) “stationary state” indicating that the capsule endoscope is stationary;

(b) “digestive organs deformation state” indicating that the digestive organs are deformed; and

(c) “capsule moving state” indicating that the capsule endoscope is moving;

a rendering duration determining unit operable to determine, for each image included in the image sequence, a rendering duration between the image and the temporally consecutive image, based on the video state, the similarity, and the amount of movement of the image; and

a display controlling unit operable to sequentially display, on a screen, the images included in the image sequence with the determined rendering durations.

2. The capsule endoscope image display controller according to claim 1 ,

wherein said image-to-image similarity calculating unit includes:

a whole image similarity calculating unit operable to calculate, for each image included in the image sequence, a whole image similarity between the image and the temporally consecutive image, the whole image similarity being a similarity between a whole area of the image and a whole area of the temporally consecutive image areas; and

a partial image similarity calculating unit operable to calculate, for each image included in the image sequence, a partial image similarity between each of blocks divided from the image and a corresponding block in the temporally consecutive image, the partial image similarity being a similarity between the blocks,

wherein said rendering duration determining unit is operable to determine, for each image included in the image sequence, a rendering duration between the image and the temporally consecutive image, based on the video state, the whole image similarity, the partial image similarity, and the amount of movement of the image.

3. The capsule endoscope image display controller according to claim 2 ,

wherein said partial image similarity calculating unit is operable to calculate, for each image included in the image sequence, a histogram-to-histogram distance between each of the blocks divided from the image and the corresponding block in the temporally consecutive image, and calculate a partial image similarity based on the histogram-to-histogram distance, the histogram-to-histogram distance being a sum of absolute values of differences between pixel values and the partial image similarity being a similarity between the blocks, and

said video state classifying unit is operable to classify, for each image included in the image sequence, the image into the “stationary state” when the following condition (i) or condition (ii) is satisfied:

the condition (i) being that the whole image similarity of the image is greater than a first threshold value and a maximum value among a plurality of histogram-to-histogram distances of a plurality of blocks included in the image is less than or equal to a second threshold value; and

the condition (ii) being that the whole image similarity of the image is greater than the first threshold value, the maximum value among the plurality of histogram-to-histogram distances of the plurality of blocks included in the image is greater than the second threshold value, and a maximum amount of movement is less than or equal to a third threshold value, the maximum amount of movement being a maximum value among amounts of movement of the feature area included in the image.

4. The capsule endoscope image display controller according to claim 2 ,

wherein said partial image similarity calculating unit is operable to calculate, for each image included in the image sequence, a histogram-to-histogram distance between each of the blocks divided from the image and the corresponding block in the temporally consecutive image, and calculate a partial image similarity based on the histogram-to-histogram distance, the histogram-to-histogram distance being a sum of absolute values of differences between pixel values and the partial image similarity being a similarity between the blocks, and

said video state classifying unit is operable to classify, for each image included in the image sequence, the image into the “digestive organs deformation state” when the following condition (iii) or condition (iv) is satisfied:

the condition (iii) being that the whole image similarity of the image is greater than a first threshold value, a maximum value among a plurality of histogram-to-histogram distances of a plurality of blocks included in the image is greater than a second threshold value, and a maximum amount of movement is greater than a third threshold value, the maximum amount of movement being a maximum value among amounts of movement of the feature area included in the image; and

the condition (iv) being that the whole image similarity of the image is less than or equal to the first threshold value, a minimum value among the plurality of histogram-to-histogram distances of the plurality of blocks included in the image is less than a fourth threshold value, and the maximum amount of movement is less than a fifth threshold value, the maximum amount of movement being the maximum value among the amounts of movement of the feature area included in the image.

5. The capsule endoscope image display controller according to claim 2 ,

wherein said partial image similarity calculating unit is operable to calculate, for each image included in the image sequence, a histogram-to-histogram distance between each of the blocks divided from the image and the corresponding block in the temporally consecutive image, and calculate a partial image similarity based on the histogram-to-histogram distance, the histogram-to-histogram distance being a sum of absolute values of differences between pixel values and the partial image similarity being a similarity between the blocks, and

said video state classifying unit is operable to classify, for each image included in the image sequence, the image into the “capsule moving state” when the following condition (v) or condition (vi) is satisfied:

the condition (v) being that the whole image similarity of the image is less than or equal to a first threshold value and a minimum value among a plurality of histogram-to-histogram distances of a plurality of blocks included in the image is greater than or equal to a fourth threshold value; and

the condition (vi) being that the whole image similarity of the image is less than or equal to the first threshold value, the minimum value among the plurality of histogram-to-histogram distances of the plurality of blocks included in the image is less than the fourth threshold value, and a maximum amount of movement is greater than or equal to a fifth threshold value, the maximum amount of movement being a maximum value among amounts of movement of the feature area included in the image.

6. The capsule endoscope image display controller according to claim 1 ,

wherein said amount-of-movement calculating unit includes:

an edge calculating unit operable to calculate, for each image included in the image sequence, a direction component of an edge included in the image and an edge strength;

a feature area extracting unit operable to extract, from each image, a feature area based on the edge direction component and the edge strength;

an amount-of-movement-of-feature-area calculating unit operable to extract an area corresponding to the feature area from each image and the temporally consecutive image, and calculate an amount of movement of the feature area; and

a maximum-amount-of-movement calculating unit operable to calculate a maximum amount of movement which is a maximum value among amounts of movement of the feature area,

wherein said rendering duration determining unit is operable to determine, for each image included in the image sequence, a rendering duration between the image and the temporally consecutive image, based on the video state, the similarity, and the maximum amount of movement of the image.

7. The capsule endoscope image display controller according to claim 1 , further comprising

a focused-feature-value extracting unit operable to extract a predetermined feature value from each image included in the image sequence,

wherein said rendering duration determining unit is operable to determine, for each image included in the image sequence, a rendering duration between the image and the temporally consecutive image, based on the video state, the similarity, the amount of movement, and the predetermined feature value of the image.

8. The capsule endoscope image display controller according to claim 7 ,

wherein the predetermined feature value is a proportion of a red area in a whole area of the image.

9. The capsule endoscope image display controller according to claim 1 ,

wherein said rendering duration determining unit is further operable to determine the rendering duration based on a skill level of a user who monitors the image sequence to be displayed on the screen and carries out an endoscopic examination.

10. The capsule endoscope image display controller according to claim 1 ,

wherein said rendering duration determining unit is further operable to smooth the plurality of rendering durations of the obtained image sequence.

11. A capsule endoscope image display control method for controlling display of an image sequence including a plurality of images captured by a capsule endoscope which moves within digestive organs, said method comprising:

a step of calculating, for each image included in the image sequence, a similarity between the image and a temporally consecutive image;

a step of calculating, for each image included in the image sequence, an amount of movement of a feature area included in the image;

a step of classifying, for each image included in the image sequence, a video state of the image into one of a plurality of states including at least the following states, based on the similarity and the amount of movement of the image:

(a) “stationary state” indicating that the capsule endoscope is stationary;

(b) “digestive organs deformation state” indicating that the digestive organs are deformed; and

(c) “capsule moving state” indicating that the capsule endoscope is moving;

a step of determining, for each image included in the image sequence, a rendering duration between the image and the temporally consecutive image, based on the video state, the similarity, and the amount of movement of the image; and

a step of sequentially displaying, on a screen, the images included in the image sequence with the determined rendering durations.

12. A non-transitory computer-readable storage medium having stored therein a program that controls display of an image sequence including a plurality of images captured by a capsule endoscope which moves within digestive organs, said program causing a computer to perform:

a step of calculating, for each image included in the image sequence, a similarity between the image and a temporally consecutive image;

a step of calculating, for each image included in the image sequence, an amount of movement of a feature area included in the image;

a step of classifying, for each image included in the image sequence, a video state of the image into one of a plurality of states including at least the following states, based on the similarity and the amount of movement of the image:

(a) “stationary state” indicating that the capsule endoscope is stationary;

(b) “digestive organs deformation state” indicating that the digestive organs are deformed; and

(c) “capsule moving state” indicating that the capsule endoscope is moving;

a step of determining, for each image included in the image sequence, a rendering duration between the image and the temporally consecutive image, based on the video state, the similarity, and the amount of movement of the image; and

a step of sequentially displaying, on a screen, the images included in the image sequence with the determined rendering durations.