Functional magnetic resonance imaging artifact removal by means of an artificial neural network

A method of operating a medical imaging system, wherein the method comprises:

• receiving magnetic resonance imaging data, wherein the magnetic resonance imaging data is BOLD functional magnetic resonance imaging data descriptive of a time dependent BOLD signal for each of a set of voxels;
• constructing a set of initial signals by reconstructing the time dependent BOLD signal for each of the set of voxels using the magnetic resonance imaging data;
• wherein the set of initial signals is the time dependent BOLD signal for each voxel and
• receiving a set of modified signals a configured artificial neural network in response to inputting the set of initial signals into the configured artificial neural network, wherein the configured artificial neural network is configured for removing physiological artifacts from the set of initial signals, the set of modified signals is either a pure noise signal from the set of initial signals or the set of modified signals with the pure noise signal removed wherein the configured artificial neural network comprises a recurrent neural network each of the set of voxels.

A computer program product comprising machine executable instructions stored on a non-transitory computer readable medium for execution by a processor an implementation of a configured artificial neural network, wherein execution of the machine executable instructions causes the processor to:

• receive magnetic resonance imaging data, wherein the magnetic resonance imaging data is BOLD functional magnetic resonance imaging data descriptive of a time dependent BOLD signal for each of a set of voxels;
• construct a set of initial signals by reconstructing the time dependent BOLD signal for each of the set of voxels using the magnetic resonance imaging data;
• wherein the set of initial signals is the time dependent BOLD signal for each voxel and
• receive a set of modified signals from the configured artificial neural network in response to inputting the set of initial signals into the configured artificial neural network, wherein the configured artificial neural network is configured for removing physiological artifacts from the set of initial signals, wherein the set of modified signals is either a pure noise signal from the set of initial signals or the set of modified signals with the pure noise signal removed, wherein the configured artificial neural network comprises a recurrent neural network or each of the set of voxels.