Lesion evaluation information generator, and method and computer readable medium therefor

1. A lesion evaluation information generator comprising:

an image data acquirer configured to acquire endoscopic color image data that represents an endoscopic image showing a lesion;

a memory; and

a processor configured to, when executing processor-executable instructions stored in the memory, provide:

a color information determiner configured to determine a hue value and a saturation value of each of pixels included in the endoscopic image based on the acquired endoscopic color image data;

a correlation value determiner configured to determine, for at least a part of the pixels of the endoscopic image, a correlation value that represents a correlation between color information of each individual pixel and reference color data, based on:

a hue correlation value that represents a correlation between the determined hue value of each individual pixel and a reference hue value of the reference color data; and

a saturation correlation value that represents a correlation between the determined saturation value of each individual pixel and a reference saturation value of the reference color data; and

an evaluation value generator configured to generate an evaluation value for evaluating a severity of the lesion in the endoscopic image, by deriving a summation of the correlation values from integrating the correlation value determined for each individual pixel.

2. The lesion evaluation information generator according to claim 1 ,

wherein the correlation value determiner is further configured to:

determine the hue correlation value based on a hue distance between the determined hue value of each individual pixel and the reference hue value of the reference color data on a two-dimensional coordinates defined with a coordinate axis for hue values and a coordinate axis for saturation values;

determine the saturation correlation value based on a saturation distance between the determined saturation value of each individual pixel and the reference saturation value of the reference color data on the two-dimensional coordinates defined with the coordinate axis for hue values and the coordinate axis for saturation values; and

determine the correlation value between color information of each individual pixel and the reference color data, based on the determined hue correlation value and the determined saturation correlation value.

3. The lesion evaluation information generator according to claim 2 ,

wherein the correlation value determiner is further configured to determine the correlation value between color information of each individual pixel and the reference color data, by multiplying the determined hue correlation value by the determined saturation correlation value.

4. The lesion evaluation information generator according to claim 3 ,

wherein the hue correlation value is a normalized value ranging from 0 to 1,

wherein when an absolute value of the hue distance is more than a predetermined distance value, the hue correlation value is equal to 0, and

wherein when the absolute value of the hue distance is equal to or less than the predetermined distance value, the less the absolute value of the hue distance is, the closer to 1 the hue correlation value is.

5. The lesion evaluation information generator according to claim 3 ,

wherein the saturation correlation value is a normalized value ranging from 0 to 1,

wherein when the determined saturation value is less than the reference saturation value of the reference color data, and the saturation distance is less than a predetermined saturation value, the saturation correlation value is equal to 0,

wherein when the determined saturation value is less than the reference saturation value of the reference color data, and an absolute value of the saturation distance is equal to or less than the predetermined saturation value, the less the absolute value of the saturation distance is, the closer to 1 the saturation correlation value is, and

wherein when the determined saturation value is equal to or more than the reference saturation value of the reference color data, the saturation correlation value is equal to 1 regardless of the absolute value of the saturation distance.

6. The lesion evaluation information generator according to claim 1 ,

wherein the color information determiner is further configured to determine the hue value and the saturation value of each individual pixel, by converting a color space of the acquired endoscopic color image data into one of an HSI color space and an HSV color space.

7. The lesion evaluation information generator according to claim 1 ,

wherein the color information determiner is further configured to determine an intensity value of each individual pixel included in the endoscopic image based on the acquired endoscopic color image data, as well as the hue value and the saturation value,

wherein the correlation value determiner comprises a saturation value corrector configured to correct the saturation value using the determined intensity value, and

wherein the correlation value determiner is further configured to determine the correlation value between the color information of each individual pixel and the reference color data, using the corrected saturation value.

8. The lesion evaluation information generator according to claim 7 ,

wherein the saturation value corrector is further configured to correct the saturation value based on a following expression:

[

INT

-

correction

SAT

-

correction

]

=

[

cos

⁢

⁢

θ

-

sin

⁢

⁢

θ

sin

⁢

⁢

θ

cos

⁢

⁢

θ

]

⁡

[

INT

SAT

]

+

[

REFER

-

INT

REFER

-

SAT

]

,

where

INT and SAT represent the intensity value and the saturation value, respectively,

REFER_ INT and REFER_ SAT represent a reference intensity value and the reference saturation value of the reference color data, respectively,

θ represents an angle corresponding to a correlation coefficient between the reference intensity value and the reference saturation value of the reference color data, and

INT_ correction and SAT_ correction represent a corrected intensity value and the corrected saturation value, respectively.

9. The lesion evaluation information generator according to claim 1 ,

wherein the reference color data is color data of blood.

10. The lesion evaluation information generator according to claim 1 ,

wherein the color information determiner comprises a lesion pixel determiner configured to determine whether each individual pixel is a lesion pixel imaging at least a part of the lesion, and

wherein the correlation value determiner is further configured to determine the correlation value only for each of pixels determined as lesion pixels.

11. The lesion evaluation information generator according to claim 1 , further comprising a displayer configured to display the generated evaluation value.

12. The lesion evaluation information generator according to claim 11 , further comprising a color information replacer configured to replace the color information of each individual pixel with replacement color information associated with the correlation value determined for each individual pixel,

wherein the displayer is further configured to display an image in which each individual pixel has the replacement color information associated with the correlation value.

13. A method configured to be implemented by a processor coupled with an image data acquirer configured to acquire endoscopic color image data that represents an endoscopic image showing a lesion, the method comprising:

determining a hue value and a saturation value of each of pixels included in the endoscopic image based on the acquired endoscopic color image data;

determining, for at least a part of the pixels of the endoscopic image, a correlation value that represents a correlation between color information of each individual pixel and reference color data, based on:

a hue correlation value that represents a correlation between the determined hue value of each individual pixel and a reference hue value of the reference color data; and

a saturation correlation value that represents a correlation between the determined saturation value of each individual pixel and a reference saturation value of the reference color data; and

generating an evaluation value for evaluating a severity of the lesion in the endoscopic image, by deriving a summation of the correlation values from integrating the correlation value determined for each individual pixel.

14. A non-transitory computer readable medium storing processor-executable instructions configured to, when executed by a processor coupled with an image data acquirer configured to acquire endoscopic color image data that represents an endoscopic image showing a lesion, cause the processor to:

determine a hue value and a saturation value of each of pixels included in the endoscopic image based on the acquired endoscopic color image data;

determine, for at least a part of the pixels of the endoscopic image, a correlation value that represents a correlation between color information of each individual pixel and reference color data, based on:

a hue correlation value that represents a correlation between the determined hue value of each individual pixel and a reference hue value of the reference color data; and

a saturation correlation value that represents a correlation between the determined saturation value of each individual pixel and a reference saturation value of the reference color data; and

generate an evaluation value for evaluating a severity of the lesion in the endoscopic image, by deriving a summation of the correlation values from integrating the correlation value determined for each individual pixel.