US 11,985,415 B2
Microscopy system and method for generating an overview image
Manuel Amthor, Jena (DE); and Daniel Haase, Zöllnitz (DE)
Assigned to Carl Zeiss Microscopy GmbH, Jena (DE)
Filed by Carl Zeiss Microscopy GmbH, Jena (DE)
Filed on Sep. 7, 2021, as Appl. No. 17/467,578.
Claims priority of application No. 10 2020 123 505.4 (DE), filed on Sep. 9, 2020.
Prior Publication US 2022/0078340 A1, Mar. 10, 2022
Int. Cl. G06N 20/00 (2019.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06T 5/50 (2006.01); G06T 7/11 (2017.01); G06V 30/262 (2022.01); H04N 23/60 (2023.01)
CPC H04N 23/64 (2023.01) [G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06N 20/00 (2019.01); G06T 5/50 (2013.01); G06T 7/11 (2017.01); G06V 30/274 (2022.01); G06T 2207/10056 (2013.01); G06T 2207/20221 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A microscopy system comprising
a microscope which is configured to capture a raw overview image of a sample environment; and
a computing device which is configured to control the microscope to capture a plurality of raw overview images showing the sample environment with different capture parameters, wherein the raw overview images differ in the capture parameters but do not differ in a sample state of the shown sample;
wherein the computing device comprises a machine learning model trained with training raw overview images which are annotated with regard to a suitability for use as an overview image, wherein annotations of the training raw overview images are assigned according to an image quality in a sample area or sample carrier area of the training raw overview images, while an image quality outside the sample area or sample carrier area is disregarded;
wherein the machine learning model receives the raw overview images as input and assesses, for each raw overview image, a respective suitability for use as an overview image, and wherein the machine learning model generates an output which is or which defines the overview image based on selecting at least one of the raw overview images which is determined to have a best suitability to be used as an overview image for its image quality in a sample area or sample carrier area, while an image quality outside the sample area or sample carrier area is disregarded.