Prompt gamma emission prediction using a long short-term memory network

Objective: To present a long short-term memory (LSTM)-based prompt gamma (PG) emissionprediction method for proton therapy.Approach: Computed tomography (CT) scans of 33 patientswith a prostate tumor were included in the dataset. A set of 107histories proton pencil beam (PB)swas generated for Monte Carlo (MC) dose and PG simulation. For training (20 patients) andvalidation (3 patients), over 6000 PBs at 150, 175 and 200MeV were simulated. 3D relativestopping power (RSP), PG and dose cuboids that included the PB were extracted. Three modelswere trained, validated and tested based on an LSTM-based network: (1) input RSP and outputPG, (2) input RSP with dose and output PG (single-energy), and (3) input RSP/dose and outputPG (multi-energy). 540 PBs at each of the four energy levels (150, 175, 200, and 125-210MeV)were simulated across 10 patients to test the three models. The gamma passing rate (2%/2mm)and PG range shift were evaluated and compared among the three models.Results: The model withinput RSP/dose and output PG (multi-energy) showed the best performance in terms of gammapassing rate and range shift metrics. Its mean gamma passing rate of testing PBs of 125-210MeVwas 98.5% and the worst case was 92.8%. Its mean absolute range shift between predicted and MCPGs was 0.15mm, where the maximum shift was 1.1mm. The prediction time of our models waswithin 130ms per PB.Significance: We developed a sub-second LSTM-based PG emissionprediction method. Its accuracy in prostate patients has been confirmed across an extensive rangeof proton energies