Method and microscope for generating an overview image of a sample

Patent metadata

Field	Value
Publication number	US-12099174-B2
Application number	US-202117498339-A
Country	US
Kind code	B2
Filing date	Oct 11, 2021
Priority date	Oct 12, 2020
Publication date	Sep 24, 2024
Grant date	Sep 24, 2024

Abstract

A method for generating an overview image of a sample which is arranged in an observation volume of a microscope by means of a sample carrier is proposed, wherein the sample carrier is illuminated by a first illumination, wherein a preliminary overview image is generated using the first illumination and an overview camera of the microscope, wherein an overview image illumination is chosen on the basis of the preliminary overview image, wherein the sample carrier is illuminated by the overview illumination, and wherein the overview image is generated using the overview image illumination and the overview camera.

First claim

What is claimed is:

1. A method for generating an overview image of a sample which is arranged in an observation volume of a microscope by means of a sample carrier,
wherein the sample carrier is illuminated by a first illumination,
wherein a preliminary overview image is generated using the first illumination and an overview camera of the microscope,
wherein an overview image illumination is automatically chosen on the basis of the preliminary overview image,
wherein the sample carrier is illuminated by the overview illumination, and
wherein the overview image is generated using the overview image illumination and the overview camera.

2. The method according to claim 1 , wherein the overview image illumination comprises a reflected light illumination and/or a transmitted light illumination.

3. The method according to claim 1 ,
wherein the preliminary overview image is processed in a trained machine learning-based system, ML system,
wherein the overview image illumination is chosen on the basis of an output of the ML system.

4. The method according to claim 3 ,
wherein the output of the trained ML system comprises a statement about the sample carrier type of the sample carrier and
wherein the overview image illumination is determined on the basis of the sample carrier type.

5. The method according to any one of preceding claim 1 ,
wherein a calibration plate is arranged in the observation volume,
wherein the calibration plate is illuminated using a calibration illumination,
wherein calibration overview images are generated using the calibration illumination and the overview camera,
wherein calibration data are obtained by means of the calibration overview images, and
wherein the preliminary overview image and/or the overview image are generated using the calibration data.

6. The method according to claim 5 ,
wherein the calibration plate comprises a first calibration structure,
wherein the calibration overview image comprises an image representation of the first calibration structure,
wherein a first detailed image of the first calibration structure is generated using a microscope objective of the microscope, and
wherein further calibration data for locating a sample detail image of the sample in the overview image are obtained on the basis of the calibration overview images and the first detailed image.

7. The method according to claim 6 ,
wherein the calibration plate comprises at least one further calibration structure,
wherein, following the generation of the first detailed image, the position of the calibration plate in relation to the microscope objective is altered by at least one further predefined translation vector, wherein at least one second detailed image of the further calibration structures/calibration structure is generated using the microscope objective of the microscope, and
wherein the calibration data are obtained by additional use of the further predefined translation vectors and the evaluation of the positions of the calibration structures in the further detailed images.

8. The method according to claim 6 , wherein the sample detail image is generated using the microscope objective or a further microscope objective.

9. The method according to claim 1 , wherein at least two preliminary raw overview images are recorded by the overview camera for the purposes of generating the preliminary overview image, with the first illumination differing in the preliminary raw overview images.

10. The method according to claim 1 , wherein at least two raw overview images are recorded for the purposes of generating the overview image, with the overview image illumination of the raw overview images differing.

11. The method according to claim 1 ,
wherein at least two preliminary raw overview images are recorded by the overview camera for the purposes of generating the preliminary overview image, with the position of the sample carrier being altered by a known translation vector between the raw overview images,
wherein mutually corresponding structures are recognized in the preliminary raw overview images, and wherein an approximate focus position is determined from the mutually corresponding structures in the preliminary raw overview images, the known translation vector and the calibration data.

12. The method according to claim 1 , wherein at least two raw overview images are recorded by the overview camera, with the position of the sample carrier being altered by a displacement vector between the raw overview images, and wherein the overview image is generated as a mosaic overview image on the basis of the raw overview images and, optionally, on the basis of the displacement vector.

13. A microscope,
comprising an overview camera,
comprising at least one microscope objective,
comprising a transmitted light unit,
comprising a reflected light unit,
comprising a control unit,
wherein the control unit is set up to carry out a method according to claim 1 .

14. A non-transitory computer-readable medium comprising computer-executable instructions that, upon execution of the program by a control unit of a microscope, cause the latter to carry out a method according to claim 1 .

15. The method according to claim 1 , further comprising automatically recognizing the sample in the overview image.

16. The method according to claim 1 , further comprising performing segmentation of the overview image to generate a mask image that visualizes structures of the sample carrier.

17. The method according to claim 1 , further comprising performing segmentation of the overview image to identify one or more sample regions that contain the sample.

Assignees

• Zeiss Carl Microscopy Gmbh

Inventors

• Haase Daniel
• Amthor Manuel
• Sticker Markus
• Backs Sebastian
• Ohrt Thomas
• Dietrich Christian

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G02B21/06

  Means for illuminating specimens · CPC title

• G02B21/367 Primary

  providing an output produced by processing a plurality of individual source images, e.g. image tiling, montage, composite images, depth sectioning, image comparison · CPC title

• G06N20/00

  Machine learning · CPC title