Abstract: A microscopy system forms a result image from a microscope image using an ordinal classification model. The ordinal classification model comprises classifiers and is defined by a training designed as follows: predetermined microscope images are input into the ordinal classification model in the training; a target image is given for each predetermined microscope image, wherein binary masks are generated from each target image via a comparison with pixel threshold values; the binary masks are used in the training as classification targets of the classifiers. The training of different classifiers differs in the pixel threshold value that is used to generate the classification targets; In the training, discrepancies between the classification masks and the binary masks are reduced. After the training, each classifier calculates a classification mask for a microscope image to be processed; these classification masks are combined into a result image.

Abstract: A computer-implemented method for generating an image processing model that calculates a virtually stained image from a microscope image comprises a training of the image processing model using training data comprising at least: microscope images as input data into the image processing model; target images formed using captured chemically stained images; and predefined segmentation masks that discriminate between image regions to be stained and image regions that are not to be stained. The image processing model is trained to calculate virtually stained images from the input microscope images by optimizing a staining reward/loss function that captures a difference between the virtually stained images and the target images. The predefined segmentation masks are taken into account in the training of the image processing model to compensate errors in the chemically stained images.

Abstract: In a computer-implemented method for automatically focusing a light microscope, an experiment description is received that includes at least one textual description of a planned sample analysis. Based on this experiment description, experiment-specific information is determined in vectorized form and input into a machine-learned model in order to define parameters of a focus strategy that includes a coarse-focus strategy and a fine-focus strategy. Using the focus strategy, a data capture with the light microscope is initiated and monitored.

Abstract: In order to define microscope settings for a planned microscope experiment, an embedding vector is calculated from a textual experiment description by means of an embedding model. Microscope settings are derived from the embedding vector using a database that contains stored embeddings for experiment descriptions with respectively associated predetermined microscope settings. The derived microscope settings can be used to capture at least one microscope image.

Abstract: A computer-implemented method tests a sensitivity of an image processing model trained using training data which includes microscope images. The training data is also used to form a generative model that can produce a generated microscope image from an input parameter set. The generative model is used to produce a series of generated microscope images by varying at least one parameter of the parameter set. An image processing result is calculated from each of the generated microscope images using the image processing model. A sensitivity of the image processing model to the at least one parameter is then ascertained based on differences between the image processing results.

Abstract: Provided is a computer-implemented method for generating a second recording of a sample in a predetermined target contrast type, the method comprising detecting at least one structure using a segmentation algorithm, wherein the structure is contained in a first recording of the sample in a predetermined first input contrast type and should be visible in the second recording of the sample in the target contrast type, and generating the second recording of the sample in the target contrast type, the generation of the second recording in the target contrast type including determining first image intensity values of the first recording of the sample to generate the second recording based on the determined first image intensity values and the at least one structure detected in the first recording, wherein the predetermined target contrast corresponds to a microscopy contrast type.

Abstract: A computer-implemented method for determining a current calibration and/or checking an initial calibration of a camera system of a microscope is provided, the camera system comprising an overview camera arranged and configured to provide an overview image of a sample carrier situated on a sample stage of the microscope, and a system camera arranged and configured to provide a microscope image of the sample carrier situated on the sample stage. The overview image and the microscope image overlap in an overlap region. The method comprises determining the current calibration and/or checking the initial calibration based on a pose of a predetermined structure of the sample carrier in the overview image and a pose of the predetermined structure in the microscope image.

Abstract: A computer-implemented method for the ordinal classification of at least one microscope image calculates a classification into one of a plurality of classes which form an order with respect to an image property. The microscope image is input into a machine-learned model for ordinal classification. The model comprises binary classifiers which calculate estimates regarding whether the microscope image belongs to cumulative auxiliary classes, which combine different numbers of the classes which follow each other in the order. The estimates can be combined so as to form a total score, wherein the classification occurs by comparing the total score with threshold values which can be defined in a variable manner depending on the application, or interval limits of the classes can be defined so that the classes form intervals of different widths. The model for ordinal classification can also comprise further binary classifiers for inverse auxiliary classes.

Abstract: A microscopy system comprises a microscope configured to capture an overview image and a computing device comprising a model trained for image segmentation, which calculates a segmentation mask based on the overview image. The computing device adjusts a pattern described by a parameterized model to the segmentation mask. An updated segmentation mask is generated using the adjusted pattern.

Abstract: Various examples of the disclosure concern a transfection analysis for cells that are imaged in a microscope image. Techniques are disclosed for the purpose of determining a cell-specific transfection level or a scene-global transfection level using a vector field map.

Abstract: A method for preparing data for identifying analytes by coloring one or more analytes with markers in multiple coloring rounds, the markers in each case being specific for a certain set of analytes, detecting multiple markers using a camera, which for each coloring round generates at least one image that includes multiple pixels to which a color value is assigned in each case as color information, and includes colored signals and uncolored signals, wherein a colored signal is a pixel containing color information of a marker, and an uncolored signal is a pixel containing color information that is not based on a marker. A data point in each case includes one or more contiguous pixels in the images of the multiple coloring rounds that are assigned to the same location in a sample.

Abstract: A method for training an image processing system with a machine learning model to perform a virtual multi-angle reconstruction of image stacks recorded with a light-sheet microscope. The method includes: recording at least one light-sheet fine stack comprising multiple image stacks at different illumination angles; determining target outputs from the fine stack, the model, and a classical multi-angle reconstruction; determining learning inputs from a light-sheet coarse stack comprising one or more image stacks at different illumination angles using the model and the classical reconstruction; creating an annotated dataset of the target outputs and learning inputs; and optimizing the model for the virtual multi-angle reconstruction based on the dataset.

Abstract: Processing a microscope image includes forming an input image from a microscope image before the input image is input into an image processing program. The image processing program comprises a learned model for image processing which is trained to calculate image processing results from input training images that show structures with certain image properties. The image processing program calculates an image processing result from the input image. The microscope image is converted into the input image by an image conversion program such that image properties of structures in the microscope image become closer to the image properties of the structures in the input training images.

Abstract: A method generates an overall image of a sample, wherein the method includes providing at least two image recordings of the sample; providing a respective coefficient array for the at least two image recordings; combining the at least two image recordings to form a combined image of the sample, wherein the contributions of the image portions of the respective image recording to the combined image are determined by the respective coefficient array; modifying at least one coefficient array of the coefficient arrays to improve the quality of the combined image; combining the at least two image recordings to form a new combined image of the sample on the basis of the modified coefficient arrays; and outputting the new combined image as overall image or forming the overall image on the basis of the modified coefficient arrays from at least two image recordings of the sample and outputting the overall image.

Abstract: In a method for processing microscope images, at least a first image data set (30) of a microscope (10) is received. At least a first generative model (40) that describes the first image data set (30) is estimated with a first computing device (20) based on the first image data set (30). Either a first generated image data set (50) is generated by the first generative model (40) and transmitted to a data exploitation device (60), or the first generative model (40) is transmitted to a data exploitation device (60) and subsequently a first generated image data set (50) is generated by means of the first generative model (40). Generated image data of the first generated image data set (50) is entirely data generated from the first generative model (40) and does not comprise processed image data of the first image data set (30) captured by the microscope (10). The first generated image data set (50) is then exploited by means of the data exploitation device (60).

Abstract: In a method for checking the rotation of a microscope camera, an overview image is captured with an overview camera of a microscope, wherein a rotational orientation of the overview camera relative to a sample stage of the microscope is known. In addition, a microscope image is captured with a microscope camera of the microscope. A rotational orientation of the microscope camera relative to the sample stage is calculated based on a relative rotation between the microscope image and the overview image, wherein the relative rotation is established by means of image structures in the microscope image and the overview image and using the known rotational orientation of the overview camera relative to the sample stage.

Abstract: A method for preparing data for identifying analytes in a sample, in which in an experiment one or more analytes are colored with markers in multiple coloring rounds, the markers in each case being specific for a certain set of analytes, detecting the multiple markers using a camera, which for each coloring round generates at least one image containing multiple pixels and color values assigned thereto, the image including colored signals and uncolored signals, wherein a colored signal is a pixel having a color value that originates from a marker, and an uncolored signal is a pixel having a color value that is not based on a marker, and storing the color information of the particular coloring rounds for evaluating the color information.

Abstract: A computer-implemented method for instance segmentation of at least one microscope image showing a plurality of objects, comprising: calculating positions of object centers of the objects in the microscope image; determining which image areas of the microscope image are covered by the objects; calculating Voronoi regions using the object centers as Voronoi sites; and determining an instance segmentation mask by separating the image areas covered by the objects into different instances using boundaries of the Voronoi regions.

Abstract: A microscopy system comprises a microscope configured to capture an overview image and a computing device comprising a model trained for image segmentation, which calculates a segmentation mask based on the overview image. The computing device adjusts a pattern described by a parameterized model to the segmentation mask. An updated segmentation mask is generated using the adjusted pattern.

Abstract: A method for preparing data for identifying analytes by coloring one or more analytes with markers in multiple coloring rounds, the markers in each case being specific for a certain set of analytes, detecting multiple markers using a camera, which for each coloring round generates at least one image that includes multiple pixels and that may contain color information of one or more markers, and storing the images of the particular coloring rounds stored for evaluating the color information, wherein the color values determined in the individual coloring rounds are clustered, according to their intensity values, in local or global clusters with similar intensity values, and only the clustered data are stored.