Method for processing digital images of a microscopic sample and microscope system
The present inventive concept relates to a microscope system and a method for processing a plurality of digital images of a sample. The method comprises: acquiring a first input set of digital images by: illuminating, by an illumination system, the sample with a first subset of a plurality of illumination patterns, and capturing a digital image of the sample for each illumination pattern of the first subset of the plurality of illumination patterns, thereby forming the first input set of digital images; inputting the first input set of digital images into a first set of machine learning models configured to output a first inference output; acquiring a second input set of digital images by: illuminating, by the illumination system, the sample with a second subset of the plurality of illumination patterns, and capturing a digital image of the sample for each illumination pattern of the second subset of the plurality of illumination patterns, thereby forming the second input set of digital images; inputting the second input set of digital images into a second set of machine learning models configured to output a second inference output, wherein the second set of machine learning models is different from the first set of machine learning models; and inputting the first inference output and the second inference output into an image processing machine learning model being trained to process the plurality of digital images of the sample using the first inference output and the second inference output.
1 . A method for processing a plurality of digital images of a sample, the method comprising:
a. acquiring a first input set of digital images by:
illuminating, by an illumination system, the sample with a first subset of a plurality of illumination patterns, wherein the illumination system comprises a plurality of light sources, wherein each light source of the plurality of light sources is configured to illuminate the sample from one direction of a plurality of directions, and wherein each illumination pattern of the plurality of illumination patterns is formed by one or more light sources of the plurality of light sources, and
capturing a digital image of the sample for each illumination pattern of the first subset of the plurality of illumination patterns, thereby forming the first input set of digital images;
b. inputting the first input set of digital images into a first set of machine learning models configured to output a first inference output;
c. acquiring a second input set of digital images by:
illuminating, by the illumination system, the sample with a second subset of the plurality of illumination patterns, and
capturing a digital image of the sample for each illumination pattern of the second subset of the plurality of illumination patterns, thereby forming the second input set of digital images;
d. inputting the second input set of digital images into a second set of machine learning models configured to output a second inference output, wherein the second set of machine learning models is different from the first set of machine learning models; and
e. inputting the first inference output and the second inference output into an image processing machine learning model being trained to process the plurality of digital images of the sample using the first inference output and the second inference output; and
wherein steps b and c are performed at least partially in parallel.
2 . The method according to claim 1 , wherein at least one direction of the plurality of directions corresponds to an angle larger than a numerical aperture of a microscope objective used to image the sample.
3 . The method according to claim 1 , wherein the first subset of illumination patterns is different from the second subset of illumination patterns.
4 . The method according to claim 1 , wherein the image processing machine learning model is trained to process the plurality of digital images using the first inference output and the second inference output by being trained to one or more of:
construct a digital image of the sample;
classify the sample into one or more classes; and
detect one or more objects within the sample.
5 . A microscope system comprising:
an illumination system configured to illuminate a sample with a plurality of illumination patterns, wherein the illumination system comprises a plurality of light sources, wherein each light source of the plurality light sources is configured to illuminate the sample from one direction of a plurality of directions, and wherein each illumination pattern of the plurality of illumination patterns is formed by one or more light sources of the plurality of light sources;
an image sensor configured to capture digital images of the sample;
a microscope objective configured to image the sample onto the image sensor; and
circuitry configured to execute:
a first acquisition function configured to control the illumination system to illuminate the sample with a first subset of the plurality of illumination patterns, and to control the image sensor to capture a digital image of the sample for each illumination pattern of the first subset of the plurality of illumination patterns, thereby forming a first input set of digital images,
a first inference function configured to input the first input set of digital images into a first set of machine learning models configured to output a first inference output,
a second acquisition function configured to control the illumination system to illuminate the sample with a second subset of the plurality of illumination patterns, and to control the image sensor to capture a digital image of the sample for each illumination pattern of the second subset of the plurality of illumination patterns, thereby forming a second input set of digital images,
a second inference function configured to input the second input set of digital images into a second set of machine learning models configured to output a second inference output, wherein the second set of machine learning models is different from the first set of machine learning models, and
a processing function configured to input the first inference output and the second inference output into an image processing machine learning model being trained to process the plurality of digital images of the sample using the first inference output and the second inference output;
wherein the circuitry is configured to execute the first inference function and the second acquisition function at least partially in parallel.
6 . The microscope system according to claim 5 , wherein at least one direction of the plurality of directions corresponds to an angle larger than a numerical aperture of the microscope objective being configured to image the sample onto the image sensor.
7 . The microscope system according to claim 5 , wherein the plurality of light sources is arranged on a curved surface being concave along at least one direction along the surface.
8 . The microscope system according to claim 7 , wherein the curved surface is formed of facets.
9 . The microscope system according to claim 5 , wherein a numerical aperture of the microscope objective is 0.4 or lower.
10 . The microscope system according to claim 5 , wherein the image processing machine learning model is trained to process the plurality of digital images using the first inference output and the second inference output by being trained to:
construct a digital image of the sample; and/or
classify the sample into one or more classes; and/or
detect one or more objects within the sample.