Abstract: Embodiments of the disclosure are directed to methods and systems for creating a medical image database, wherein data which comprise partial images of two-dimensional or higher-dimensional initial images of parts of the human body are created, a projection for obtaining feature vectors is created from the partial images, wherein, in order to prepare the execution of the projection, a neural network based on specified learning partial images is created, wherein the data records are used within the scope of a metric learning method to learn the projection and creation of the feature vectors from learning partial images. This is achieved for example by specifying learning partial images that are slightly shifted, rotated, skewed or stretched relative to one another and were created starting from the same initial image as similar.