I wonder whether Pytomography supports HKEM（ Hybrid kernelized expectation maximization） now? From the description of the KEM API: "support_objects (Sequence[torch.tensor])- Objects used for support when building each basis function. These may correspond to PET/CT/MRI images, for example. "
Does this mean that only prior information from known images can be input (judging from the description and parameters, multiple prior images can be input), and the images in the iteration cannot be utilized? Looking forward to your answer!