Image processing apparatus, microscope system, image processing method, and computer-readable recording medium

1. An image processing apparatus comprising:

an interface configured to receive an input of a plurality of images acquired by imaging a specimen stained with non-fluorescent dye at a plurality of wavelength bands that are different from one another; and

a processor comprising hardware, wherein the processor is configured to:

calculate a characteristic amount representing auto-fluorescence emitted by the specimen based on the plurality of images; and

determine a wavelength band of fluorescence where a fluorescence labeled antibody is superimposable or not superimposable on the specimen stained with the non-fluorescent dye based on the characteristic amount.

2. The image processing apparatus according to claim 1 ,

wherein the characteristic amount is a fluorescence intensity calculated from a pixel value of a pixel in each image for each of the plurality of images, and

wherein the processor is configured to determine the wavelength band of fluorescence by comparing the fluorescence intensity with a specified threshold value.

3. The image processing apparatus according to claim 1 ,

wherein the processor is configured to:

extract an intensity spectrum defined according to a wavelength based on the pixel value of the pixel in the plurality of images, and

determine the wavelength band of fluorescence based on a correlation between the intensity spectrum and an intensity spectrum of known fluorescence.

4. The image processing apparatus according to claim 3 ,

wherein the processor is configured to:

calculate an eigenvector by principal component analysis computation with respect to a quantity based on the pixel value of the pixel in the plurality of images;

calculate an evaluation value representing a correlation between the eigenvector and a characteristic vector corresponding to the intensity spectrum of the known fluorescence; and

compare the evaluation value with a specified threshold value.

5. The image processing apparatus according to claim 4 ,

wherein the evaluation value is a value acquired by normalizing an inner product of the characteristic vector and the eigenvector, and

wherein the processor is configured to determine that fluorescence of a wavelength band corresponding to the characteristic vector is not superimposable, if the evaluation value is greater than the specified threshold value.

6. The image processing apparatus according to claim 4 ,

wherein the evaluation value is an inner product of difference vectors between the characteristic vector and a vector acquired by projecting the eigenvector in a direction of the characteristic vector, and

wherein the processor is configured to determine that fluorescence of a wavelength band corresponding to the characteristic vector is not superimposable, if the evaluation value is less than the specified threshold value.

7. The image processing apparatus according to claim 2 ,

wherein the processor is configured to:

extract an intensity spectrum defined according to a wavelength based on the pixel value of the pixel in the plurality of images;

determine a wavelength band of fluorescence that is superimposable or not superimposable based on a correlation between the intensity spectrum and an intensity spectrum of known fluorescence; and

determine a wavelength band of fluorescence that is superimposable or not superimposable, with respect to the wavelength band of the fluorescence determined to be superimposable.

8. The image processing apparatus according to claim 3 , further comprising:

a storage configured to store information on the known fluorescence.

9. A microscope system, comprising:

the image processing apparatus according to claim 1 ;

a microscope apparatus configured to perform fluorescence observation with respect to the specimen; and

an image sensor configured to acquire the plurality of images by performing imaging at the plurality of wavelength bands that are different from one another.

10. The microscope system according to claim 9 ,

wherein the image sensor is configured to perform imaging in a wavelength region including a visible region and a near infrared region.

11. An image processing method comprising:

receiving an input of a plurality of images acquired by imaging a specimen stained with non-fluorescent dye at a plurality of wavelength bands that are different from one another;

calculating a characteristic amount representing auto-fluorescence emitted by the specimen based on the plurality of images; and

determining a wavelength band of fluorescence where a fluorescence labeled antibody is superimposable or not superimposable on the specimen stained with the non-fluorescent dye based on the characteristic amount.

12. A non-transitory computer-readable recording medium with an executable program stored thereon, wherein the program instructs a processor to perform:

receiving an input of a plurality of images acquired by imaging a specimen stained with non-fluorescent dye at a plurality of wavelength bands that are different from one another;

calculating a characteristic amount representing auto-fluorescence emitted by the specimen based on the plurality of images; and

determining a wavelength band of fluorescence where a fluorescence labeled antibody is superimposable or not superimposable on the specimen stained with the non-fluorescent dye based on the characteristic amount.