AI-enabled early-pet acquisition
Data processing systems (DPS) and related methods for nuclear medicine imaging. At an input interface (IN), first projection data (λ), or a first image (V) reconstructable from the first projection data, is received. The first projection data is associated with a first waiting period (ΔT*). The first waiting period indicates the time period from administration of a tracer agent to a start of acquisition by a nuclear medicine imaging apparatus (IA) of the projection date. A trained machine learning module (MLM) estimates, based on the first projection data (λ) or on the first image (V), a second projection data (λ′) or a second image (V′) associable with a second waiting period (ΔT), longer than the first waiting period (ΔT*). Nuclear imaging can thus be conducted quicker. Similar machine learning based data processing systems and related methods are also envisaged to reduce acquisition time periods or the time it takes to reconstruct imagery.
1 . A data processing system (DPS) for nuclear medicine imaging, the data processing system comprising:
an input interface (IN) for receiving first projection data (λ), the first projection data associated with a first waiting period (ΔT*), the first waiting period indicating a time period from administration of a tracer agent to a start of acquisition by a nuclear medicine imaging apparatus (IA) of the first projection data; and
a computing device for running a trained machine learning model, trained based on time-series training input data, the trained machine learning model being configured to estimate, based on the first projection data (λ), second projection data (λ′) associable with a second waiting period (ΔT), longer than the first waiting period (ΔT*).
2 . The data processing system (DPS) of claim 1 , wherein the second waiting period is prescribed by a type of the tracer agent.
3 . A data processing system (DPS) for nuclear medicine imaging, the data processing system comprising:
an input interface (IN) for receiving first projection data (λ), the first projection data associated with a first acquisition time period (Δt*) for acquisition by a nuclear medicine imaging apparatus (IA) of the first projection data in respect of a patient with incorporated tracer agent; and
a computing device for running a trained machine learning model, trained based on time-series training input data, the trained machine learning model being configured to estimate, based on the first projection data (λ), second projection data (λ′) associable with a second acquisition time period (Δt), longer than the first acquisition time period (Δt*).
4 . The data processing system (DPS) of claim 3 , wherein the second acquisition time period is prescribed by a type of the tracer agent.
5 . A data processing method for nuclear imaging, the method comprising:
receiving first projection data (λ), the first projection data associated with a first waiting period (ΔT*), the first waiting period indicating a time period from administration of a tracer agent to a start of acquisition by a nuclear medicine imaging apparatus (IA) of the first projection data;
inputting the first projection data (λ) to a trained machine learning model, trained based on time-series training input data, wherein the trained machine learning model is configured to estimate second projection data (λ′) associable with a second waiting period (ΔT) indicating a prescribed time from the administration of the tracer agent to the start of the acquisition by the nuclear medicine imaging apparatus (IA) of the first projection data, wherein the second waiting period (ΔT) is longer than the first waiting period (ΔT*); and
outputting the second projection data (λ′) from the trained machine learning model.
6 . The data processing method of claim 5 , wherein the prescribed time is based on a type of the tracer agent.
7 . A data processing method for nuclear imaging, the method comprising:
receiving first projection data (λ), the first projection data associated with a first acquisition time period (Δt*) for acquisition by a nuclear medicine imaging apparatus (IA) of the first projection data in respect of a patient with incorporated tracer agent;
inputting the first projection data (λ) to a trained machine learning model, trained based on time-series training input data, wherein the trained machine learning model is configured to estimate second projection data (λ′) associable with a second acquisition time period (Δt) indicating a prescribed time for the acquisition by the nuclear medicine imaging apparatus (IA) of the first projection data, longer than the first acquisition time period (Δt*); and
outputting the second projection data (λ′) from the trained machine learning model.
8 . The data processing method of claim 7 , wherein the prescribed time is based on a type of the tracer agent.