Image processing apparatus, microscope system, and image processing method
An image processing apparatus includes an image acquisition unit that acquires image information representing a fluorescence observation image of a specimen stained with hematoxylin-eosin, a spectrum generation unit that generates a plurality of spectra each representing a wavelength distribution of fluorescence intensity in a plurality of pixels in the fluorescence observation image, a pixel extraction unit that extracts at least two pixel groups with a feature of a particular spectrum from the plurality of pixels, and an image generation unit that generates an image based on the extracted pixel groups.
1. An image processing apparatus comprising:
an image acquisition unit that acquires image information representing a fluorescence observation image of a specimen stained with hematoxylin-eosin;
a spectrum generation unit that generates a plurality of spectra each representing a wavelength distribution of fluorescence intensity in a plurality of pixels in the fluorescence observation image;
a pixel extraction unit that extracts at least two pixel groups with a feature of a particular spectrum from the plurality of pixels, wherein the pixel extraction unit is configured to:
extract the at least two pixel groups with reference to at least two fluorescence intensity spectra acquired respectively in advance with respect to at least two kinds of components in the specimen;
extract pixel groups having the same peak wavelengths as those of the at least two fluorescence intensity spectra, as the at least two pixel groups, respectively;
extract a pixel group having a peak wavelength of 560 nm as a pixel group representing an elastic fiber in the specimen; and
extract a pixel group having a peak wavelength of 570 nm as a pixel group representing a blood corpuscle in the specimen;
an image generation unit that generates an image based on the extracted pixel groups; and
an abnormality determination unit that determines a presence or absence of abnormality in a blood vessel in the fluorescence observation image based on the pixel group representing the elastic fiber.
2. The image processing apparatus according to claim 1 , wherein the pixel extraction unit extracts, as the pixel group representing the elastic fiber, a pixel group whose fluorescence intensity at a peak wavelength is greater than or equal to a specified threshold from among a plurality of pixels in the pixel group having a peak wavelength of 560 nm.
3. The image processing apparatus according to claim 1 , wherein
the image acquisition unit further acquires second image information representing a bright-field observation image of the specimen stained with hematoxylin-eosin, and
the image generation unit further generates a second image based on the second image information.
4. The image processing apparatus according to claim 3 , further comprising an image display unit that displays at least one of the image and the second image.
5. The image processing apparatus according to claim 3 , further comprising an image synthesis unit that generates a synthesis image obtained by overlapping the image on the second image.
6. The image processing apparatus according to claim 5 , further comprising an image display unit that displays at least one of the image, the second image, and the synthesis image.
7. The image processing apparatus according to claim 1 , wherein the abnormality determination unit includes:
a blood vessel feature data calculation unit that calculates morphological feature data of a blood vessel based on the pixel group representing the elastic fiber; and
a determination unit that determines the presence or absence of abnormality in the blood vessel based on the morphological feature data of the blood vessel.
8. The image processing apparatus according to claim 1 ,
wherein the abnormality determination unit includes:
an elastic fiber continuity determination unit that determines continuity of the elastic fiber; and
a determination unit that determines the presence or absence of abnormality in the blood vessel based on a determination result of the continuity.
9. The image processing apparatus according to claim 8 , wherein the elastic fiber continuity determination unit determines the continuity of the elastic fiber based on an area of a region surrounded by the elastic fiber and circularity of the elastic fiber.
10. The image processing apparatus according to claim 1 , wherein the abnormality determination unit includes:
a vascular wall thickness calculation unit that calculates a thickness of a vascular wall of the blood vessel based on the elastic fiber; and
a determination unit that determines whether the blood vessel is normal or abnormal based on the thickness.
11. The image processing apparatus according to claim 10 , wherein the vascular wall thickness calculation unit:
measures an outer diameter of the blood vessel based on the elastic fiber;
extracts a region inside the elastic fiber based on the elastic fiber;
measures an inner diameter of the blood vessel based on the region inside the elastic fiber; and
calculates the thickness of the vascular wall based on the outer diameter and the inner diameter of the blood vessel.
12. The image processing apparatus according to claim 7 , further comprising a storage unit that stores a lookup table in which the morphological feature data of the blood vessel are correlated with a determination result of the presence or absence of abnormality and/or a degree of abnormality in the blood vessel, wherein
the determination unit determines the presence or absence of abnormality and/or the degree of abnormality with reference to the lookup table.
13. The image processing apparatus according to claim 8 , further comprising a storage unit that stores a lookup table in which the determination result of the continuity of the elastic fiber is correlated with a determination result of the presence or absence of abnormality and/or a degree of abnormality in the blood vessel, wherein
the determination unit determines the presence or absence of abnormality and/or the degree of abnormality with reference to the lookup table.
14. The image processing apparatus according to claim 10 , further comprising a storage unit that stores a lookup table in which an evaluation value related to the thickness of the vascular wall is correlated with a determination result of the presence or absence of abnormality and/or a degree of abnormality in the blood vessel, wherein
the determination unit determines the presence or absence of abnormality and/or the degree of abnormality with reference to the lookup table.
15. A microscope system comprising:
the image processing apparatus according to claim 1 ;
a stage on which the specimen is configured to be placed;
an epi-illumination optical system that emits excitation light toward the stage;
an objective optical system that is provided to face the stage and receives light from a direction of the specimen;
a filter that extracts fluorescence light from the light transmitted through the objective optical system; and
an imaging unit that is provided on an optical path of the light transmitted through the objective optical system and generates image information by capturing an observation image of the specimen.
16. The microscope system according to claim 15 , further comprising:
a transmission illumination optical system that emits illumination light toward the stage; and
a switching unit that switches between the excitation light and the illumination light to be emitted toward the specimen, wherein
the filter is provided removably on the optical path of the light transmitted through the objective optical system and extracts the fluorescence light with a specified wavelength band from the light.
17. The microscope system according to claim 15 , wherein a wavelength band of the excitation light is 300 nm or more and 400 nm or less.
18. The microscope system according to claim 17 , wherein the wavelength band of the fluorescence light is 520 nm or more and 650 nm or less.
19. The microscope system according to claim 15 , wherein the imaging unit includes a camera that is capable of capturing images in a plurality of wavelength bands.
20. An image processing method comprising:
acquiring image information representing a fluorescence observation image of a specimen stained with hematoxylin-eosin;
generating a plurality of spectra each representing a wavelength distribution of fluorescence intensity in a plurality of pixels in the fluorescence observation image;
extracting at least two pixel groups with a feature of a particular spectrum from the plurality of pixels, wherein the extracting:
extracts the at least two pixel groups with reference to at least two fluorescence intensity spectra acquired respectively in advance with respect to at least two kinds of components in the specimen;
extracts pixel groups having the same peak wavelengths as those of the at least two fluorescence intensity spectra, as the at least two pixel groups, respectively;
extracts a pixel group having a peak wavelength of 560 nm as a pixel group representing an elastic fiber in the specimen; and
extracts a pixel group having a peak wavelength of 570 nm as a pixel group representing a blood corpuscle in the specimen;
generating an image based on the extracted pixel groups; and
determining a presence or absence of abnormality in a blood vessel in the fluorescence observation image based on the pixel group representing the elastic fiber.