Machine learning-based event recognition in SiFi Compton camera imaging for proton therapy monitoring

Abstract

Objective. Online monitoring of dose distribution in proton therapy is currently being investigated with the detection of prompt gamma (PG) radiation emitted from a patient during irradiation. The SiPM and scintillation Fiber based Compton Camera (SiFi-CC) setup is being developed for this aim. Approach. A machine learning approach to recognize Compton events is proposed, reconstructing the PG emission profile during proton therapy. The proposed method was verified on pseudo-data generated by a Geant4 simulation for a single proton beam impinging on a polymethyl methacrylate (PMMA) phantom. Three different models including the boosted decision tree (BDT), multilayer perceptron (MLP) neural network, and k-nearest neighbour (k-NN) were trained using 10-fold cross-validation and then their performances were assessed using the receiver operating characteristic (ROC) curves. Subsequently, after event selection by the most robust model, a software based on the List-Mode Maximum Likelihood Estimation Maximization (LM-MLEM) algorithm was applied for the reconstruction of the PG emission distribution profile. Main results. It was demonstrated that the BDT model excels in signal/background separation compared to the other two. Furthermore, the reconstructed PG vertex distribution after event selection showed a significant improvement in distal falloff position determination. Significance. A highly satisfactory agreement between the reconstructed distal edge position and that of the simulated Compton events was achieved. It was also shown that a position resolution of 3.5 mm full width at half maximum (FWHM) in distal edge position determination is feasible with the proposed setup.

Influence of the background in Compton camera images for proton therapy treatment monitoring

“…In addition to the background rejection methods mentioned in section 1, the emerging use of neural networks without requiring additional instrumentation, is also being explored by this (Muñoz et al 2021) and other groups (Zoglauer and Boggs 2007, Polf et al 2021, Kozani and Magiera 2022. Future work will focus on the improvement of the timing capabilities of the MACACO experimental prototype and other strategies to reduce the background in this system, such as the detection of secondary charged particles or the use of neutron absorbers before the system.…”

Hybrid PET/Compton-camera imaging: an imager for the next generation

“…Within the frame of particle therapy, event selection instead of compensation during the reconstruction is often attempted to reduce the impact of accidental coincidences and fortuitous events [69], and/or to compensate for the wrong estimation of the unknown initial energy [126]. Machine learning, in particular deep neural networks, has also shown some potential in this regard [127][128][129][130].…”