Imaging device and a method for image generation of a specimen
An imaging device for image generation of a specimen is disclosed. Layers of images may be captured by an optical system and then compiled to create an integrated image. Each layer may include a different focal point. A consolidated image may then be created by combining one or more integrated images.
1. An imaging device for image generation of a specimen, wherein the imaging device comprises circuitry configured to:
capture a first plurality of images of a first location within a first area of interest of a specimen according to a first parameter set, wherein the first parameter set comprises a first plurality of focus distances, wherein at least a focus distance of the first plurality of focus distances corresponds to at least an image of the first plurality of images;
compile a first integrated image as a function of the first plurality of images, wherein compiling the first integrated image comprises:
removing a first artifact within the first plurality of images using an artifact machine learning model comprising a generative machine learning model;
capture a second plurality of images of a second location within the first area of interest of the specimen according to the second parameter set, wherein the second parameter set comprises a second plurality of focus distances, wherein at least a focus distance of the second plurality of focus distances corresponds to at least an image of the second plurality of images;
compile the second plurality of images into a second integrated image;
combine the first integrated image and the second integrated image into a consolidated image; and
display the consolidated image.
2. The imaging device of claim 1 , wherein removing the first artifact comprises:
inputting the first plurality of images into the artifact machine learning model; and
removing the first artifact within the first plurality of images using the artifact removal machine learning model.
3. The imaging device of claim 1 , wherein the imaging device comprises circuitry configured to:
receive a third parameter set associated with a second area of interest of the specimen, wherein the third parameter set comprises a third focus depth;
capture a third plurality of images of the second area of interest of the specimen according to the third parameter set; and
compile the third plurality of images into a third integrated image.
4. The imaging device of claim 3 , wherein the imaging device comprises circuitry configured to combine the first integrated image, the second integrated image, and the third integrated image into the consolidated image.
5. The imaging device of claim 3 , wherein the imaging device comprises circuitry configured to move an optical system from the first area of interest to the second area of interest, according to the third parameter set.
6. The imaging device of claim 1 , wherein the second plurality of focus distances is not coextensive with the first plurality of focus distances.
7. The imaging device of claim 1 , wherein the imaging device comprises circuitry configured to move an optical system from the first location to the second location.
8. The imaging device of claim 1 , wherein the imaging device comprises circuitry configured to:
compare the first integrated image to a fitness measure; and
flag the first integrated image if the first integrated image falls outside of a predetermined threshold of the fitness measure.
9. The imaging device of claim 8 , wherein:
comparing the first integrated image comprises using a fitness machine-learning model comprises, wherein using the fitness machine-learning model comprises:
training the fitness machine-learning model using fitness training data, wherein the fitness training data contains a plurality of data entries containing examples of integrated images as inputs correlated to examples of fitness measures as outputs; and
flagging the integrated image as a function of the comparison using the trained fitness machine-learning model.
10. The imaging device of claim 8 , wherein the imaging device comprises circuitry configured to:
update, if the first integrated image is flagged, the first plurality of images;
compile the updated first plurality of images to create an updated integrated image;
compare the updated integrated image to the fitness measure; and
identify an optimized integrated image if the updated integrated image falls within the predetermined threshold of the fitness measure.
11. A method of user for an imaging device for image generation of a specimen, wherein the method comprises:
capturing, using an imaging device, a first plurality of images of a first location within a first area of interest of a specimen according to a first parameter set, wherein the first parameter set comprises a first plurality of focus distances, wherein at least a focus distance of the first plurality of focus distances corresponds to at least an image of the first plurality of images;
compiling, using the imaging device, a first integrated image as a function of the first plurality of images, wherein compiling the first integrated image comprises:
removing, using the imaging device, a first artifact within the first plurality of images using an artifact machine learning model comprising a generative machine learning model;
capturing, using the imaging device, a second plurality of images of a second location within the first area of interest of the specimen according to the second parameter set, wherein the second parameter set comprises a second plurality of focus distances, wherein at least a focus distance of the second plurality of focus distances corresponds to at least an image of the second plurality of images;
compiling, using the imaging device, the second plurality of images into a second integrated image;
combining, using the imaging device, the first integrated image and the second integrated image into a consolidated image; and
displaying, using a graphical user interface, the consolidated image.
12. The method of claim 11 , wherein removing the first artifact and the second artifact comprises:
inputting the first plurality of images into the artifact machine learning model; and
removing the first artifact within the first plurality of images and the second artifact within the second plurality of images using the artifact removal machine learning model.
13. The method of claim 11 , wherein the method further comprises:
receiving, by the imaging device, a third parameter set associated with a second area of interest of the specimen, wherein the third parameter set comprises a third focus depth;
capturing, by the imaging device, a third plurality of images of the second area of interest of the specimen according to the third parameter set; and
compiling, by the imaging device, the third plurality of images into a third integrated image.
14. The method of claim 13 , wherein the method further comprises combining, by the imaging device, the first integrated image, the second integrated image, and the third integrated image into the consolidated image.
15. The method of claim 13 , wherein the method further comprises moving, by the imaging device, an optical system from the first area of interest to the second area of interest, according to the third parameter set.
16. The method of claim 11 , wherein the second plurality of focus distances is not coextensive with the first plurality of focus distances.
17. The method of claim 11 , wherein the method further comprises moving, by the imaging device, an optical system from the first location to the second location.
18. The method of claim 11 , wherein the method further comprises:
comparing, by the imaging device, the first integrated image to a fitness measure; and
flagging, by the imaging device, the first integrated image if the first integrated image falls outside of a predetermined threshold of the fitness measure.
19. The method of claim 18 , wherein:
comparing the first integrated image comprises using a fitness machine-learning model comprises, wherein using the fitness machine-learning mode comprises:
training the fitness machine-learning model using fitness training data, wherein the fitness training data contains a plurality of data entries containing examples of integrated images as inputs correlated to examples of fitness measures as outputs; and
flagging the integrated image as a function of the comparison using the trained fitness machine-learning model.
20. The method of claim 18 , wherein the method further comprises:
updating, by the imaging device, the first plurality of images if the first integrated image is flagged;
compiling, by the imaging device, the updated first plurality of images to create an updated integrated image;
comparing, by the imaging device, the updated integrated image to the fitness measure; and
identifying, by the imaging device, an optimized integrated image if the updated integrated image falls within the predetermined threshold of the fitness measure.