<ul><li>Spiking neural networks (SNN) are investigated for detecting photon coincidences in positron emission tomography (PET) data.</li><li>PETNet interprets detector hits as a binary-valued spike train and learns to identify photon coincidence pairs.</li><li>PETNet outperforms the state-of-the-art classical algorithm with a maximal coincidence detection F1 of 95.2%.</li><li>PETNet predicts photon coincidences up to 36 times faster than the classical approach, demonstrating the potential of SNNs in particle physics applications.</li></ul>

PETNet -- Coincident Particle Event Detection using Spiking Neural Networks

Discover more