Time discrimination techniques using artificial neural networks for positron emission tomography

Abstract

Relevant information in positron emission tomography (PET) is currently being obtained mostly by analog signal processing methods. New digital PET scanner architectures are now becoming available, which offer greater flexibility and easier reconfiguration capability as compared to previous PET designs. Moreover, new strategies can be devised to extract more information with better accuracy from the digitized detector signals. Trained artificial neural networks (ANN) have been investigated to improve coincidence timing resolution with different types of APD-based detectors. The signal at the output of a charge sensitive preamplifier was digitized with an off-the-shelf, free-running 100-MHz, 8-bit ADC and time discrimination was performed with ANNs implemented in field programmable gate arrays (FPGA). Results show that ANNs can be particularly efficient with slow and low light output scintillators like BGO (/spl tau/=300 ns), but less so with faster luminous crystals such as LSO (/spl tau/=40 ns). In reference to a fast PMT-plastic detector, a time resolution of 6.5 ns was achieved with a BGO-APD detector, as compare to 12.7 ns with conventional analog methods using a constant fraction discriminator. With LSO, the ANN was found to be competitive with other digital techniques developed in previous works. In conclusion, ANNs implemented in FPGAs provide a fast and flexible circuit that can be easily reconfigured to accommodate various detectors under different signal/noise conditions.