Computer-implemented method, computer program, systems and x-ray facility for correction of x-ray image data with regard to noise effects

Abstract

A computer-implemented method and system for providing a trained artificial intelligence determination algorithm for correcting x-ray image data with regard to noise effects, for example for scattered radiation correction of the x-ray image data. The determination algorithm, from input data comprising a recorded image dataset, determines a noise effect dataset describing the noise effects to be used for correction of the x-ray image dataset. A statistical physics model parameterized by model parameters is used to describe the noise effects. The model parameters are able to be determined at least in part using the determination algorithm including receiving of training datasets that include x-ray image sub datasets with assigned, known noise effect sub datasets and/or with at least one assigned, noise-free reference image sub dataset, training the determination algorithm using the training datasets, and providing the trained determination algorithm.