Image processing apparatus, image processing method, image processing program, and virtual microscope system

1. An image processing apparatus for processing a stained sample image obtained by imaging a stained sample, the image processing apparatus comprising:

a dye spectrum storage portion for storing a dye spectrum of a dye used in staining the stained sample; and

an arithmetic portion including a variation characteristic calculating portion and a dye-amount/variation-amount estimating portion, the variation characteristic calculating portion calculating a variation characteristic based on the dye spectrum stored in the dye spectrum storage portion, the variation characteristic representing either a sharp or gradual change of the dye spectrum in the wavelength direction, the dye-amount/variation-amount estimating portion estimating, based on the dye spectrum stored in the dye spectrum storage portion and the variation characteristic calculated by the variation characteristic calculating portion, a dye-amount and a variation amount based on the variation characteristic from a pixel value of each pixel forming the stained sample image, the arithmetic portion analyzing the stained sample image at least based on the variation amount.

2. The image processing apparatus according to claim 1 ,

wherein the variation amount calculating portion calculates, as the variation characteristic, a second-order derivative spectrum obtained by subjecting the dye spectrum to a second-order differentiation.

3. The image processing apparatus according to claim 1 ,

wherein the arithmetic portion further includes a dye-spectrum/dye-amount correcting portion for correcting the dye spectrum and the dye amount, respectively, based on the dye spectrum, the variation characteristic, the dye amount, and the variation amount, and

wherein the arithmetic portion is configured to analyze the stained sample image, based on the corrected dye spectrum and the corrected dye amount.

4. The image processing apparatus according to claim 1 ,

wherein the arithmetic portion further includes a classification portion for classifying each pixel forming the stained sample image, based on the variation amount, and

wherein the arithmetic portion is configured to analyze the stained sample image, based on the classification results obtained by the classification portion.

5. The image processing apparatus according to claim 4 ,

wherein the stained sample is an H&E stained sample,

wherein the dye spectrum is a spectrum of E dye, and

wherein the classification portion distinguishes, based on the variation amount, at least one of a muscle fiber and a collagen fiber from the other.

6. The image processing apparatus according claim 4 , further comprising a display image creating portion for creating a display image, based on the classification results obtained by the classification portion.

7. The image processing apparatus according to claim 1 ,

wherein the arithmetic portion further includes a spectrum estimating portion for estimating an optical spectrum, based on a pixel value of each pixel forming the stained sample image, and

wherein the dye-amount/variation-amount estimating portion estimates, based on the optical spectrum estimated by the spectrum estimating portion, the dye amount and the variation amount.

8. The image processing apparatus according to claim 1 ,

wherein the variation characteristic calculating portion calculates, based on the dye spectrum, a plurality of variation characteristics including a variation characteristic representing a change different from the change represented by the variation characteristic,

wherein the dye-amount/variation-amount estimating portion estimates, based on the dye spectrum and the plurality of variation characteristics calculated by the variation characteristic calculating portion, a plurality of variation amounts including the variation amount, the plurality of variation amounts being different from each other, and

wherein the arithmetic portion analyzes the stained sample image, based on the plurality of variation amounts.

9. An image processing method of processing a stained sample image obtained by imaging a stained sample, the method comprising the steps of:

acquiring a dye spectrum of a dye used in staining the stained sample;

calculating, based on the dye spectrum thus acquired, a variation characteristic at least representing either a sharp or gradual change of the dye spectrum in the wavelength direction;

estimating, based on the dye spectrum and the variation characteristic, a dye-amount and a variation amount based on the variation characteristic from a pixel value of each pixel forming the stained sample image; and

analyzing the stained sample image at least based on the variation amount.

10. A non-transitory computer-readable storage medium having an image processing program, for processing a stained sample image obtained by imaging a stained sample, recorded thereon, the program causing a computer to execute the processes of:

acquiring a dye spectrum of a dye used in staining the stained sample;

calculating, based on the dye spectrum thus acquired, a variation characteristic at least representing either a sharp or gradual change of the dye spectrum in the wavelength direction;

estimating, based on the dye spectrum and the variation characteristic, a dye-amount and a variation amount based on the variation characteristic from a pixel value of each pixel forming the stained sample image; and

analyzing the stained sample image at least based on the variation amount.

11. A virtual microscope system for acquiring a virtual slide image of a stained sample, comprising:

an image acquiring portion for acquiring a stained sample image by imaging the stained sample using a microscope;

a dye spectrum storage portion for storing a dye spectrum of a dye used in staining the stained sample; and

an arithmetic portion including a variation characteristic calculating portion and a dye-amount/variation-amount estimating portion, the variation characteristic calculating portion calculating a variation characteristic based on the dye spectrum stored in the dye spectrum storage portion, the variation characteristic representing either a sharp or gradual change of the dye spectrum in the wavelength direction, the dye-amount/variation-amount estimating portion estimating, based on the dye spectrum stored in the dye spectrum storage portion and the variation characteristic calculated by the variation characteristic calculating portion, a dye-amount and a variation amount based on the variation characteristic from a pixel value of each pixel forming the stained sample image, the arithmetic portion analyzing the stained sample image at least based on the variation amount,

the virtual microscope system being configured to acquire a virtual slide image of the stained sample, based on the stained sample analyzed by the arithmetic portion.