SYSTEM AND METHOD FOR ESTIMATING A RELATIVE SUBSTANCE COMPOSITION OF A PORTION OF A BODY OF A PATIENT

The invention relates to a method and a system (100 for estimating a relative substance composition, RSC, of a portion of a body of a patient in a field of view for a medical image to be taken from the patient in a magnetic resonance imaging scan, comprising:an input interface (10) for receiving at least one piece of patient information data, PPID (71), and for receiving at least one piece of field-of-view information data, PFID (72);a computing device (50) configured to implement a trained machine learning algorithm, MLA, (55) wherein the trained MLA (55) is configured and trained to receive the at least one PPID (71) and the at least one PFID (72) received by the input interface (10) as its input and to generate as its output at least one output signal (74) indicating an RSC of a portion of the body of the patient for the medical image based on the at least one PPID (71) and the at least one PFID (72); andan output interface (90) for outputting at least the at least one output signal (74).The output signal may used in a method for determining a water resonance setting frequency for an magnetic resonance imaging, MRI, scan and/or is used in a shimming method for an MRI device.