US 12,087,041 B2
Microscopy system and method for generating a virtually stained image
Alexander Freytag, Erfurt (DE); Matthias Eibl, Jena (DE); Christian Kungel, Penzberg (DE); Anselm Brachmann, Jena (DE); Daniel Haase, Zoellnitz (DE); and Manuel Amthor, Jena (DE)
Assigned to Carl Zeiss Microscopy GmbH, Jena (DE)
Appl. No. 18/565,315
Filed by Carl Zeiss Microscopy GmbH, Jena (DE)
PCT Filed May 30, 2022, PCT No. PCT/EP2022/064646
§ 371(c)(1), (2) Date Nov. 29, 2023,
PCT Pub. No. WO2022/253773, PCT Pub. Date Dec. 8, 2022.
Claims priority of application No. 10 2021 114 290.3 (DE), filed on Jun. 2, 2021.
Prior Publication US 2024/0265682 A1, Aug. 8, 2024
Int. Cl. G06V 10/26 (2022.01); G06T 5/20 (2006.01); G06T 5/70 (2024.01); G06T 7/00 (2017.01); G06T 11/00 (2006.01); G06V 10/75 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/774 (2022.01) [G06T 5/20 (2013.01); G06T 5/70 (2024.01); G06T 7/0002 (2013.01); G06T 11/001 (2013.01); G06V 10/273 (2022.01); G06V 10/759 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06T 2207/10056 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30168 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for generating an image processing model in order to calculate a virtually stained image from a microscope image, comprising:
training of the image processing model using training data, wherein the training data comprises at least:
microscope images as input data into the image processing model, and
target images that are formed via chemically stained images registered locally in relation to the microscope images;
wherein the image processing model is trained to calculate virtually stained images from the input microscope images by optimizing an objective function that captures a difference between the virtually stained images and the target images;
defining at least one weighting mask after a number of training steps using at least one of the chemically stained images and an associated virtually stained image calculated after the number of training steps;
wherein, in the weighting mask, one or more image regions are weighted based on differences between locally corresponding image regions in the virtually stained image and in the chemically stained image; and
continuing the training, wherein the weighting mask is taken into account in the objective function.