Methods and systems related to image reconstruction based on energy-resolved x-ray data

A system for image reconstruction based on energy-resolved x-ray data comprising:

• an input for receiving at least one representation of energy-resolved x-ray data;
• a basis material decomposition system configured to perform at least two basis material decompositions based on said at least one representation of energy-resolved x-ray data to generate at least two sets of basis image representations;
• a trained machine learning system having a configuration determined based on input-output-paired training data and adapted to receive at least two basis image representations from said at least two of said sets of basis image representation and process said received at least two basis image representations by machine learning-based data processing to generate at least one representation of output image data, wherein said trained machine learning system is configured to map said received at least two basis image representations, originating from said at least two basis material decompositions, into said at least one representation of output image data, and wherein said trained machine learning system is trained to reduce bias and noise in the at least one representation of output image data and to generate a basis image representation set with a greater number of basis function than any of said at least two sets of basis image representations;
• and
• an output for outputting said at least one representation of output image data.