Image processing apparatus

1. An image processing apparatus, comprising:

an imager configured to obtain image data acquired by photographing biological tissue;

a processor; and

a memory storing instructions that, when executed by the processor, cause the processor to perform operations including:

converting pixel values of the image data into pixel values of a predetermined color space;

determining whether a pixel is a pixel photographing an inflammation part, for each pixel, based on a saturation value and a hue value included in the converted pixel value;

calculating, for each pixel, a hue correlation value between a hue value of blood and the hue value of the converted pixel value, and a saturation correlation value between a saturation value of blood and the saturation value of the converted pixel value;

calculating a score representing a degree of severity of inflammation of the biological tissue photographed in an image represented by the image data for each pixel determined as the pixel photographing an inflammation part, based on the calculated saturation correlation value and the calculated hue correlation value included in the converted pixel value;

evaluating a reliability of the score for each said pixel determined as the pixel photographing an inflammation part, based on the saturation correlation value or the hue correlation value included in the converted pixel value; and

calculating a score reliability which represents a ratio of pixels of which scores having predetermined reliability to all the pixels of the image data.

2. The image processing apparatus according to claim 1 ,

wherein the evaluating includes determining whether each pixel is in a halation state based on a pixel value, and

wherein the evaluating includes excluding pixels determined to be in the halation state from the pixels of which scores having the predetermined reliability.

3. The image processing apparatus according to claim 1 ,

wherein the evaluating includes determining whether a pixel is of a dark part based on a pixel value thereof, and

wherein the evaluating includes excluding pixels determined to be of the dark part from the pixels of which scores having the predetermined reliability.

4. The image processing apparatus according to claim 1 , wherein the operations further include converting the pixel values of the image data into pixel values of a hue-saturation-intensity space, and

wherein the evaluating includes evaluating the reliability of the scores based on intensity of each pixel output by the converting.

5. The image processing apparatus according to claim 1 ,

wherein the evaluating includes determining whether each pixel is a saturated pixel of which any one of color channels is saturated based on a pixel value thereof, and

wherein the evaluating includes excluding pixels determined to be the saturated pixels from the pixels of which scores having the predetermined reliability.

6. The image processing apparatus according to claim 5 ,

wherein the determining whether each pixel is a saturated pixel of which any one of color channels is saturated includes counting the number of saturated color channels based on the pixel values, and

wherein the determining whether each pixel is a saturated pixel of which any one of color channels is saturated includes determining the pixels having a predetermined number or more of saturated color channels as the saturated pixel.

7. The image processing apparatus according to claim 1 ,

wherein the operations further include applying marks indicating a distribution of the scores on the image, and

wherein the applying includes changing modes of the marks depending on the score reliability.

8. The image processing apparatus according to claim 7 ,

wherein the applying includes executing a first color mapping to change pixel colors of a lesion part to a color corresponding to the score.

9. The image processing apparatus according to claim 8 ,

wherein the applying includes excluding the image area in which pixels of which reliabilities are low are locally existing.

10. The image processing apparatus according to claim 8 ,

wherein the applying includes applying the first color mapping with use of different colors for pixels of which scores have the predetermined reliability and pixels of which scored do not have the predetermined reliability.

11. The image processing apparatus according to claim 7 ,

wherein the applying includes applying a first type simplified marking process in which a mark is applied on an area, of which score is equal to or greater than a predetermined value, in the image.

12. The image processing apparatus according to claim 7 ,

wherein the applying includes applying a second type simplified marking process in which a mark is applied such that the mark encircles an area of which score is relatively high in the image.

13. The image processing apparatus according to claim 1 ,

wherein the operations further include displaying an evaluation result of the reliability of the score.

14. The image processing apparatus according to claim 1 ,

wherein quality of a photographing condition is determined in accordance with a color balance of the image.

15. The image processing apparatus according to claim 1 ,

wherein the image is photographed with use of a single-broadband illumination light.

16. The image processing apparatus according to claim 2 ,

wherein the evaluating includes determining whether a pixel is of a dark part based on a pixel value thereof, and

wherein the evaluating includes excluding pixels determined to be of the dark part from the pixels of which scores having the predetermined reliability.

17. The image processing apparatus according to claim 16 ,

wherein the operations further include converting the pixel values of the image data into pixel values of a hue-saturation-intensity space,

wherein the evaluating includes evaluating the reliability of the scores based on intensity of each pixel output by the converting.

18. The image processing apparatus according to claim 17 ,

wherein the evaluating comprises determining whether each pixel is a saturated pixel of which any one of color channels is saturated based on a pixel value thereof, and

wherein the evaluating includes excluding pixels determined to be the saturated pixels from the pixels of which scores having the predetermined reliability.

19. The image processing apparatus according to claim 18 ,

wherein the determining whether each pixel is a saturated pixel comprises counting the number of saturated color channels based on the pixel values, and

wherein the determining whether each pixel is a saturated pixel comprises determining the pixels each having a predetermined or more number of saturated color channels as the saturated pixel.

20. The image processing apparatus according to claim 19 ,

wherein the operations further include applying marks indicating a distribution of the scores on the image, and

wherein the applying includes changing modes of the marks depending on the score reliability.