Improving Compton camera imaging of multi-energy radioactive sources by using machine learning algorithms for event selection

Event selection and background reduction for Compton camera imaging of multi-energy radioactive sources has been performed by employing neural networks. A Compton camera prototype with detectors made of LaBr 3 crystals coupled to silicon photomultiplier arrays was used to acquire experimental data from a circular array of 22 Na sources. The prototype and two arrays of 22 Na sources were simulated with GATE v8.2 Monte Carlo code, to obtain data for neural network training. Neural network models were trained on simulated data for event classification. The optimum models were found by using Weights & Biases platform tools. The trained models were used to classify simulated and real data for selecting signal events and rejecting background prior to image reconstruction. The models performed well on simulated data. The image obtained with experimental data showed an improvement with respect to event selection with energy cuts. The method is promising for Compton camera imaging of multi-energy radioactive sources. • Compton camera imaging of multi-energy radioactive sources. • Processing of Compton camera experimental data with neural networks. • Neural network models employed for event selection on experimental data prior to image reconstruction. • Comparison between the performance of the neural network models and an energy-cut-based method. • Improved results with neural network with both simulated and experimental data.