| CPC G06T 11/005 (2013.01) [G06T 7/0012 (2013.01); G06T 2207/10104 (2013.01); G06T 2207/20081 (2013.01)] | 18 Claims |

|
1. A system for positron emission tomography (PET) image reconstruction, comprising:
at least one storage device including a set of instructions; and
at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to direct the system to perform operations including:
obtaining PET data of a subject, the PET data being associated with a plurality of coincidence events, the plurality of coincidence events including scattering events and true coincident events;
generating, based on the PET data, a preliminary scatter sinogram relating to the scattering events and a true sinogram relating to the true coincident events and the scatter events;
generating, based on the preliminary scatter sinogram and the true sinogram, an input of a scatter sinogram generator, the scatter sinogram generator being a trained machine learning model;
determining a target scatter sinogram relating to the scattering events by inputting the input into the scatter sinogram generator, the target scatter sinogram having a higher image quality than the preliminary scatter sinogram; and
reconstructing, based on the PET data and the target scatter sinogram, a target PET image of the subject.
|