Microscopy system and method for calculating a result image using an ordinal classification model

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.