OptiGAN for Crystal Arrays: Physics-Informed Generative Modeling of Optical Photon Transport in PET Detector Arrays
Preprint
Abstract
Monte Carlo simulations of optical photon transport are computationally prohibitive for large-scale optical systems including detector arrays and PET systems, restricting practical use to single-crystal studies. This work presents an enhanced conditional generative adversarial network (optiGAN) replacing optical simulations at the crystal array level, extending our single-crystal approach to a 3x3 BGO array. We enhance the Wasserstein-GAN framework with Fourier feature encoding, a learnable latent mapping network, and a physics-informed loss enforcing momentum conservation. Training data is reduced eight-fold by exploiting symmetry. Evaluation employs three studies: a full array evaluation testing generalization from the fundamental domain to the complete geometry, a high-resolution study probing out-of-distribution generalization to untrained positions, and a pencil beam $γ$-photon study assessing practical applicability for experimental detector characterization. Performance is benchmarked against GATE10/Geant4 ground truth, using intrinsic fluctuations between independent Monte Carlo runs as baseline. OptiGAN achieves sliced Wasserstein similarity within 3$σ$-agreement of the baseline across all conditions, demonstrating successful generalization to the full array. The model transitions from electron-emission training data to realistic $γ$-photon interactions, producing flood maps that reproduce characteristic patterns including photopeak clusters and inter-crystal scatter lines. This proof-of-concept demonstrates that physics-informed generative models can accurately simulate optical photon transport in segmented scintillator arrays. The reproduction of experimentally relevant flood map features validates optiGAN for PET detector development and establishes a foundation for models generalizing across diverse array configurations.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- optiGAN: a deep learning-based alternative to optical photon tracking in Python-based GATE (10+)Physics in Medicine & Biology, 2025
- Towards large nuclear imaging system optical simulations with optiGAN, a generative adversarial networkPhysics in Medicine & Biology, 2025
- Integration of polarization in the LUTDavis model for optical Monte Carlo simulation in radiation detectorsPhysics in Medicine & Biology, 2021
- Advanced Monte Carlo simulations of emission tomography imaging systems with GATEPhysics in Medicine & Biology, 2021
- Modeling complex particles phase space with GAN for Monte Carlo SPECT simulations: a proof of conceptPhysics in Medicine & Biology, 2021
- Generative adversarial networks (GAN) for compact beam source modelling in Monte Carlo simulationsPhysics in Medicine & Biology, 2019
- Innovations in Instrumentation for Positron Emission TomographySeminars in Nuclear Medicine, 2018
- Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics SynthesisComputing and Software for Big Science, 2017
- Simulation of light transport in scintillators based on 3D characterization of crystal surfacesPhysics in Medicine & Biology, 2013
- Positron Emission Tomography2005