Systems and methods of accelerated dynamic imaging in pet
AssigneeSiemens Medical Solutions USA, Inc.
InventorsDeepak Bharkhada, Maurizio Conti, Vladimir Panin
Life of this patent
Estimating the term…
Abstract
Systems and methods of dynamic PET imaging are disclosed. A system includes a positron emission tomography (PET) imaging modality configured to execute a first scan to acquire a first PET dataset and a processor. The first PET dataset includes dynamic PET data. The processor is configured to back-project the first PET dataset to generate a plurality of histo-image frames, input each of the plurality of histo-image frames to a trained neural network, and receive a dynamic PET output from the trained neural network. Each of the histo-image frames corresponds to a first axial position of the PET imaging modality.
Claims20
A system, comprising:
- a positron emission tomography (PET) imaging modality configured to execute a first scan to acquire a first PET dataset, wherein the first PET dataset includes dynamic PET data;
- and
- a processor configured to:
- back-project the first PET dataset to generate a plurality of histo-image frames, wherein each of the histo-image frames corresponds to a first axial position of the PET imaging modality;
- input each of the plurality of histo-image frames to a trained neural network;
- and
- receive an estimated dynamic PET output from the trained neural network.
A method of dynamic imaging for a positron emission tomography (PET) imaging device, comprising:
- executing a first scan to acquire a first PET dataset, wherein the first PET dataset includes dynamic PET data;
- back-projecting the first PET dataset to generate a plurality of histo-image frames, wherein each of the histo-image frames corresponds to a first axial position of the PET imaging modality;
- inputting each of the plurality of histo-image frames to a trained neural network;
- and
- receiving an estimated dynamic PET output from the trained neural network.
A method of training a neural network for use in dynamic positron emission tomography (PET) imaging, comprising:
- receiving a training dataset comprising a plurality of dynamic PET datasets and a plurality of dynamic PET outputs, wherein each dynamic PET dataset in the plurality of dynamic PET datasets has a corresponding dynamic PET output in the plurality of dynamic PET outputs;
- inputting each of the plurality of dynamic PET datasets to a neural network, wherein the neural network is configured to generate an estimated dynamic PET output for each dynamic PET dataset in the plurality of dynamic PET datasets;
- comparing the estimated dynamic PET output for each dynamic PET dataset to the corresponding dynamic PET output from the plurality of dynamic PET outputs to determine any differences between each estimated dynamic PET output and the dynamic PET output that corresponds to the dynamic PET dataset that was inputted to the neural network;
- and
- modifying the neural network based on the determined differences between the estimated dynamic PET output for each dynamic PET dataset and the corresponding dynamic PET output.
Dependencies are inferred from the claim text.