Image processing apparatus and method of operating image processing apparatus

1. An image processing apparatus comprising:

a fluorescence intensity information storage configured to store therein fluorescence intensity information on predetermined body tissue and fluorescence intensity information on a detection target cell; and

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

calculate intensities of fluorescence in a plurality of fluorescence images that are associated with different cross sections of a same living body, each fluorescence image being obtained by removing an effect of a piece of fluorescence other than a piece of fluorescence on an imaging surface, from among pieces of fluorescence emitted from a living body that has been irradiated with excitation light;

create a three-dimensional fluorescence intensity distribution of the same living body from the calculated intensities of fluorescence of the plurality of fluorescence images;

identify, by using the created fluorescence intensity distribution, body tissue that is matched with the fluorescence intensity information on the predetermined body tissue read from the fluorescence intensity information storage;

identify, by using the created fluorescence intensity distribution, for each of pieces of the identified body tissue, a cell that is matched with the fluorescence intensity information on the detection target cell read from the fluorescence intensity information storage; and

determine a state of the identified body tissue based on information on the identified cell.

2. The image processing apparatus according to claim 1 , wherein the processor is configured to identify, by performing a particle analysis on a binarized image obtained by performing a threshold process of a fluorescence intensity on each of the plurality of fluorescence images, pieces of the predetermined body tissue that are present in the same living body, one by one.

3. The image processing apparatus according to claim 1 , wherein the processor is configured to identify, by performing machine learning on each of the plurality of fluorescence images, pieces of the predetermined body tissue that are present in the same living body, one by one.

4. The image processing apparatus according to claim 1 , wherein the processor is configured to measure feature data of the identified cell for each of the pieces of the identified body tissue and determine the state of the body tissue in accordance with the measured feature data.

5. The image processing apparatus according to claim 4 , wherein the feature data is the number of detection target cells included in the identified body tissue.

6. The image processing apparatus according to claim 4 , wherein the feature data is a statistical value of volumes of detection target cells included in the identified body tissue.

7. The image processing apparatus according to claim 4 , wherein the feature data is a sum total of volumes of detection target cells included in the identified body tissue.

8. The image processing apparatus according to claim 4 , wherein the feature data is a statistical value of surface areas of detection target cells included in the identified body tissue.

9. The image processing apparatus according to claim 4 , wherein the feature data is a sum total of surface areas of detection target cells included in the identified body tissue.

10. The image processing apparatus according to claim 1 , wherein the predetermined body tissue is a gland duct of a digestive tract.

11. The image processing apparatus according to claim 10 , wherein the gland duct is unstained.

12. The image processing apparatus according to claim 1 , wherein

the detection target cell is an enterochromaffin cell,

a wavelength band of the excitation light is from 340 nm to 390 nm, and

a wavelength band for capturing the fluorescence image is from 420 nm to 700 nm.

13. A method of operating an image processing apparatus comprising:

calculating intensities of fluorescence in a plurality of fluorescence images that are associated with different cross sections of a same living body, each fluorescence image being obtained by removing an effect of a piece of fluorescence other than a piece of fluorescence on an imaging surface, from among pieces of fluorescence emitted from a living body that has been irradiated with excitation light;

creating a three-dimensional fluorescence intensity distribution of the same living body from the calculated fluorescence intensity of the plurality of fluorescence images;

identifying by using the created fluorescence intensity distribution, body tissue that is matched with fluorescence intensity information on predetermined body tissue that has been read from a fluorescence intensity information storage configured to store therein the fluorescence intensity information on the predetermined body tissue and fluorescence intensity information on a detection target cell;

identifying, by using the created fluorescence intensity distribution, for each of pieces of the identified body tissue, a cell that is matched with the fluorescence intensity information on the detection target cell read from the fluorescence intensity information storage; and

determining a state of the identified body tissue based on information on the identified cell.