Abstract: In a computer-implemented method for controlling a microscope, a textual input describing a desired microscope image and an employed sample is received. The textual input and an overview image of the employed sample are input into a large language model, which is trained to process the textual input and the overview image together to calculate microscope settings for capturing a microscope image that corresponds to the desired microscope image. A microscope image is then captured with these calculated microscope settings.

Abstract: A domain-specific machine-learned model is used to generate context information for a generic machine-learned foundation model. Its output may then be used in turn to retrain the domain-specific machine-learned model.

Abstract: A method for classifying a roadway condition on the basis of image data from a camera system includes providing image data which is configured to image at least one portion of the surroundings of the vehicle, at least part of the portion containing the roadway on which the vehicle is driving. The method includes distinguishing diffuse reflection and specular reflection of the roadway by evaluating differences in the appearances of at least one point of the roadway in at least two images. The method also includes determining whether, in at least one image, there are disturbances that have been caused by at least one wheel of a vehicle whirling up a substance covering a roadway as said wheel travels thereover. The method further includes classifying the roadway condition into one of several roadway condition classes, taking account of the results with regard to the reflection type and the disturbance intensity.

Abstract: A method for generating an image of a sample includes radiating a first grid-shaped light sheet of a first wavelength range onto the sample in such a way that the sample is inhomogeneously illuminated by the first light sheet, capturing the light emitted by the sample due to the radiating of the first light sheet of the first wavelength range onto the sample; and reconstructing first areas of the sample, which are not illuminated or are more weakly illuminated using the first light sheet of the first wavelength range, on the basis of the captured light of the second areas of the sample, which are more strongly illuminated using the light sheet of the first wavelength range, by means of a machine learning system.

Abstract: Various examples relate to determining a number and/or a confluency of cells in a microscopy image. To that end, the microscopy image is firstly rescaled and then processed.

Abstract: A method is useful for scanning partial regions of a sample by a scanning microscope, such as a laser scanning microscope or a scanning electron microscope, and for reconstructing an overall image of the sample from data of the scanned partial regions of the sample. The method includes: 1) determining partial regions of the sample, which are scanned by the scanning microscope, by a machine learning system which is trained by supervised learning, unsupervised learning, and/or reinforcement learning for improved determination of the partial regions of the sample which are scanned by the scanning microscope; 2) scanning the determined partial regions of the sample by the scanning microscope; and 3) reconstructing the overall image of the sample from the data of the scanned partial regions of the sample, wherein non-scanned partial regions of the sample are estimated by the data of the scanned partial regions of the sample.

Abstract: A method for providing source data for training and validating a processing model for processing analyte image sequences. An analyte image sequence is generated by labeling analytes with markers in a plurality of coloring rounds and detecting the markers with a camera. The markers are selected, in particular based on a codebook, such that signal sequences of analytes in an image region over the analyte image sequence comprise colored signals and uncolored signals, in particular an order of the colored and uncolored signals is based on the codebook. The camera captures an image of the analyte image sequence in each of the coloring rounds. The method comprises capturing a spot analyte image sequence of a sample, and comprises providing an evaluation of image regions based on image signals of the image regions. Further, the method comprises identifying spot image regions from the evaluation of the image regions.

Abstract: In a computer-implemented method for modifying microscope images, a generative model is trained using a training dataset which comprises a plurality of microscope images. After the training, the generative model is configured to compute a generated microscope image from a feature vector derived from a feature space. It is established which image properties are affected by which feature variables in the feature space. A microscope image to be modified is received and projected into the feature space in order to obtain an associated feature vector. One or more feature variables of the feature vector are modified in order to change one or more image properties, whereby a modified feature vector is generated. The modified feature vector is projected back into an image space by inputting the modified feature vector into the generative model, thereby generating a modified microscope image.

Abstract: In a computer-implemented method for processing a microscope image, the microscope image is converted into a downscaled microscope image and then input into a first image-to-image model. The first image-to-image model calculates a result image which differs in an image property from the downscaled microscope image. The microscope image is input together with the result image into a second image-to-image model, which calculates an output image that has a higher image resolution than the result image and resembles the result image in the image property.

Abstract: A computer-implemented method for generating pairs of registered microscope images includes training a generative model to create generated microscope images from input feature vectors comprising feature variables. The training uses image data sets which respectively contain microscope images of microscopic objects but which differ in an imaging/image property. It is identified which of the feature variables are object feature variables, which define at least object positions of microscopic objects in generated microscope images, and which of the feature variables are imaging-property feature variables, which determine a depiction of the microscopic objects in generated microscope images depending on the imaging/image property.

Abstract: Various examples relate to determining a number and/or a confluency of cells in a microscopy image. To that end, the microscopy image is firstly rescaled and then processed.

Abstract: Various aspects of the disclosure relate to techniques for recognizing cell structures in microscope images. In particular, techniques for recognizing cell walls, i.e. cell edges, in microscope images, e.g. phase contrast images, are described. For this purpose, a machine-learned algorithm, e.g. an artificial neural network, can be used. Techniques of how annotations can be created as a ground truth for the training of the machine-learned algorithm, e.g. based on the fluorescence channel of transfection image data, are described. Further actions can then be performed based on correspondingly localized cell walls, e.g. cell-instance annotations that segment cell instances, for the training of a further machine-learned algorithm.

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.

Abstract: A method for training a machine learning system having a processing model for a sample type, which processes microscope images of samples of the sample type by virtual processing mapping, comprising recording at least one fine stack of a sample of the sample type, wherein the at least one fine stack comprises microscope images of the sample registered with respect to one another, determining at least one target microscope image based on the fine stack and the virtual processing mapping, creating an annotated data set comprising at least the target microscope image and a learning microscope image, wherein the learning microscope image is based on a coarse stack capturing the sample coarser than the fine stack, optimizing the processing model on the basis of the annotated data set.

Abstract: In a method, a device and a computer program product for acquiring images for training data to train a statistical model by machine learning for image processing in microscopy, the training data is made up of pairs of input images and output images from image processing. The method includes acquiring at least one image, analyzing the at least one image according to predetermined criteria, determining acquisition parameters for the acquisition of output images on the basis of the analysis results, and acquiring output images on the basis of the determined acquisition parameters.

Abstract: A method for processing microscope images in order to generate an image processing result comprises: implementing a convolutional neural network, wherein a first convolutional layer calculates an output tensor from an input tensor formed from a microscope image. The output tensor is input into one or more further layers of the convolutional neural network in order to calculate the image processing result. The first convolutional layer comprises a plurality of filter kernels. At least several of the filter kernels are respectively representable by at least one filter matrix with learning parameters and dependent filter matrices with implicit parameters, which are determined by means of the learning parameters and one or more weights to be learned, wherein the filter matrices with learning parameters of different filter kernels are different from one another and different layers of the output tensor are calculated by different filter kernels.

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.

Abstract: A method generates an image processing model to calculate a virtually stained image from a microscope image. The image processing model is trained using training data comprising 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. 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. After a number of training steps, at least one weighting mask is defined using one of the chemically stained images and an associated virtually stained image calculated after the number of training steps. 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.

Abstract: A computer-implemented method for generating an image processing model (M) that calculates a virtually stained image (30) from a microscope image (20) comprises a training (15) of the image processing model (M) using training data (T) comprising at least: microscope images (20) as input data into the image processing model (M); target images (50) formed using captured chemically stained images (60); and predefined segmentation masks (70) that discriminate between image regions (71, 72) to be stained and image regions (72) that are not to be stained. The image processing model (M) is trained to calculate virtually stained images (30) from the input microscope images (20) by optimizing a staining reward/loss function (LSTAIN) that captures a difference between the virtually stained images (30) and the target images (50). The predefined segmentation masks (70) are taken into account in the training (15) of the image processing model (M) to compensate errors in the chemically stained images (60).

Abstract: A number of techniques for assessing simulation models for use in microscopy are provided. In one example technique, a first image (IA) of a sample is recorded with a first image recording type, and storing image values of the first image (IA) are stored. Based on a simulation model (SMA?C) being applied to the first image (IA), a simulated image (IA?C) of a third image recording type of the sample is simulated. A third image (Ic) of the sample is recorded with a third image recording type. The third image (Ic) is compared with the simulated image I(A?c) of the third image recording type for verification of compliance with previously defined quality criteria, and the simulation model (SMA?C) is classified as permissible when the quality criteria are complied with.