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: A reference sample for calibrating and/or adjusting a microscope and to uses of the reference sample. The latter has at least one carrier structure made of a carrier material which, at least in regions of its extent, is excitable to emit luminescence light, and at least one two-dimensional and/or three-dimensional structure consisting of a number of substructures. The carrier material is diamond or silicon carbide and is doped in or around the regions of the two-dimensional and/or three-dimensional structure in order to be excitable to emit the luminescence light.

Abstract: A prediction algorithm determines synthetic fluorescence images on the basis of measurement images. A validation of the synthetic fluorescence images can be effected on the basis of reference images which are captured after the measurement images or are captured for a separate sample. Alternatively or additionally, a training of the prediction algorithm can be effected on the basis of training images which are captured after the measurement images or are captured for a separate sample.

Abstract: A prediction algorithm determines synthetic fluorescence images on the basis of measurement images. A validation of the synthetic fluorescence images can be effected on the basis of reference images which are captured after the measurement images or are captured for a separate sample. Alternatively or additionally, a training of the prediction algorithm can be effected on the basis of training images which are captured after the measurement images or are captured for a separate sample.

Abstract: A method and a microscope determine flow properties in a sample chamber through which a medium flows. The method includes detecting detection radiation from a confocal volume generated in the sample chamber with a plurality of detector elements of a detector in the form of a detector array at a plurality of points in time. The detector is arranged in a plane conjugate to the rear-side image plane of an objective. The measurement values from the detector elements can be analyzed individually. Cross correlations of the acquired measurement values from the detector elements of at least one pair are generated in two directions and analyzed. The confocal volume is generated at at least two mutually different locations of the sample chamber. At each location, a speed and optionally a movement direction of the medium are determined to create a flow profile over at least one region of the sample chamber.

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: A reference sample for calibrating and/or adjusting a microscope and to uses of the reference sample. The latter has at least one carrier structure made of a carrier material which, at least in regions of its extent, is excitable to emit luminescence light, and at least one two-dimensional and/or three-dimensional structure consisting of a number of substructures. The carrier material is diamond or silicon carbide and is doped in or around the regions of the two-dimensional and/or three-dimensional structure in order to be excitable to emit the luminescence light.

Abstract: A prediction algorithm determines synthetic fluorescence images on the basis of measurement images. A validation of the synthetic fluorescence images can be effected on the basis of reference images which are captured after the measurement images or are captured for a separate sample. Alternatively or additionally, a training of the prediction algorithm can be effected on the basis of training images which are captured after the measurement images or are captured for a separate sample.