Image processing system selecting learned model based on setting information of a microscope system, and image processing method and computer-readable medium
An image processing system includes a microscope system that acquires an input image to be input to an image processing device, and the image processing device including a circuitry. The circuitry selects a learned model from a plurality of learned models that have learned image conversion that converts the input image into an output image having an image quality higher than an image quality of the input image, and performs the image conversion using the selected learned model. Each of the plurality of learned models is a learned model learned using an image that differs from an image(s) used by the other learned model(s) in at least sample type, or a learned model learned using an image that differs from an image(s) used by the other learned model(s) in at least image quality range.
1. An image processing system comprising:
an image processing device including circuitry;
an optical microscope system that includes a plurality of objective lenses having different numerical apertures, and that acquires an input image to be input to the image processing device; and
a storage storing a plurality of learned models,
wherein:
the circuitry (i) selects, based on setting information indicating a parameter of the optical microscope system when the optical microscope system acquired the input image, a learned model from the plurality of learned models stored in the storage, each of the plurality of learned models being a model having learned an image conversion that converts the input image acquired by the optical microscope system into an output image having an image quality higher than an image quality of the input image, and (ii) performs the image conversion using the selected learned model,
each of the plurality of learned models is a learned model having learned using an image that differs from an image used by the remainder of the plurality of learned models in at least one of a sample type and an image quality range,
the setting information includes the numerical apertures of the objective lenses included in the optical microscope system, and
the circuitry selects the learned model based on the numerical aperture of the objective lens set for the optical microscope system when the optical microscope system acquired the input image.
2. The image processing system according to claim 1 , wherein:
each of the plurality of learned models is a learned model having learned using an image that differs from an image used by the remainder of the plurality of learned models in at least image quality range,
the output image has a noise level lower than a noise level of the input image, and
the image quality range includes a noise level range.
3. The image processing system according to claim 2 , wherein each of the plurality of learned models is a learned model having learned using an image acquired with an image acquisition device of a type that is different from a type of an image acquisition device used for the remainder of the plurality of learned models.
4. The image processing system according to claim 3 , wherein the different types of image acquisition devices include a laser scanning microscope and a wide-field microscope having a digital camera.
5. The image processing system according to claim 1 , wherein:
each of the plurality of learned models is a learned model learned using an image that differs from an image used by the remainder of the plurality of learned models in at least image quality range,
the output image has a resolution higher than a resolution of the input image, and
the image quality range includes a resolution range.
6. The image processing system according to claim 5 , wherein each of the plurality of learned models is a learned model having learned using an image acquired with an objective lens having a numerical aperture that is different from a numerical aperture of an objective lens used for the remainder of the plurality of learned models.
7. The image processing system according to claim 5 , wherein each of the plurality of learned models is a learned model having learned using an image acquired with a pixel resolution that is different from a pixel resolution used for the remainder of the plurality of learned models.
8. The image processing system according to claim 5 , wherein each of the plurality of learned models is a learned model having learned using an image acquired with a laser scanning microscope having confocal pinholes of different diameters from one another.
9. The image processing system according to claim 1 , wherein:
each of the plurality of learned models is a learned model having learned using an image that differs from an image used by the remainder of the plurality of learned models in at least image quality range,
the output image has an aberration level lower than an aberration level of the input image, and
the image quality range includes an aberration level range.
10. The image processing system according to claim 9 , wherein each of the plurality of learned models is a learned model having learned using an image acquired with an objective lens having an aberration performance that is different from an aberration performance of an objective lens used for the remainder of the plurality of learned models.
11. The image processing system according to claim 1 , wherein:
the optical microscope system is a laser scanning microscope, and
the setting information includes at least one of a scan size of a galvano scanner and a pinhole diameter.
12. The image processing system according to claim 1 , wherein:
the optical microscope system is a laser scanning microscope, and
the setting information further includes a pinhole diameter.
13. An image processing system comprising:
an image processing device including circuitry;
an optical microscope system that includes a plurality of objective lenses with different magnifications, and that acquires an input image to be input to the image processing device; and
a storage storing a plurality of learned models,
wherein:
the circuitry (i) selects, based on setting information indicating a parameter of the optical microscope system when the optical microscope system acquired the input image, a learned model from the plurality of learned models stored in the storage, each of the plurality of learned models being a model having learned an image conversion that converts the input image acquired by the optical microscope system into an output image having an image quality higher than an image quality of the input image, and (ii) performs the image conversion using the selected learned model,
each of the plurality of learned models is a learned model having learned using an image that differs from an image used by the remainder of the plurality of learned models in at least one of a sample type and an image quality range,
the setting information includes the magnifications of the objective lenses included in the optical microscope system, and
the circuitry selects the learned model based on the magnification of the objective lens set for the optical microscope system when the optical microscope system acquired the input image.
14. The image processing system according to claim 13 , wherein the setting information further includes numerical apertures of the objective lenses included in the optical microscope system.
15. The image processing system according to claim 13 , wherein the setting information further includes a pixel resolution of an image acquired in the optical microscope system.
16. The image processing system according to claim 13 , wherein the setting information further includes an aberration level of the objective lenses included in the optical microscope system.
17. The image processing system according to claim 13 , wherein:
the optical microscope system is a laser scanning microscope, and
the setting information further includes a pinhole diameter.
18. An image processing method comprising:
selecting a learned model from a plurality of learned models stored in a storage, each of the plurality of learned models being a model having learned an image conversion that converts an input image acquired by an optical microscope system into an output image having an image quality higher than an image quality of the input image, the optical microscope system including a plurality of objective lenses having different numerical apertures, and the selected learned model being selected based on setting information indicating a parameter of the optical microscope system when the optical microscope system acquired the input image; and
performing the image conversion using the selected learned model,
wherein:
each of the plurality of learned models is a learned model having learned using an image that differs from an image used by the remainder of the plurality of learned models in at least one of a sample type and an image quality range,
the setting information includes the numerical apertures of the objective lenses included in the optical microscope system, and
the selecting comprises selecting the learned model based on the numerical aperture of the objective lens set for the optical microscope system when the optical microscope system acquired the input image.
19. A non-transitory computer-readable medium storing a program that is executable to control a computer to execute processing comprising:
selecting a learned model from a plurality of learned models stored in a storage, each of the plurality of learned models being a model having learned an image conversion that converts an input image acquired by an optical microscope system into an output image having an image quality higher than an image quality of the input image, the optical microscope system including a plurality of objective lenses having different numerical apertures, and the selected learned model being selected based on setting information indicating a parameter of the optical microscope system when the optical microscope system acquired the input image; and
performing the image conversion using the selected learned model,
wherein:
each of the plurality of learned models is a learned model having learned using an image that differs from an image used by the remainder of the plurality of learned models in at least one of a sample type and an image quality range,
the setting information includes the numerical apertures of the objective lenses included in the optical microscope system, and
the selecting comprises selecting the learned model based on the numerical aperture of the objective lens set for the optical microscope system when the optical microscope system acquired the input image.