{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:22:06Z","timestamp":1783423326600,"version":"3.54.6"},"reference-count":39,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T00:00:00Z","timestamp":1681257600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"NIH","award":["R01EB027130"],"award-info":[{"award-number":["R01EB027130"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Detailed simulation of optical photon transport and detection in radiation detectors is often used for crystal-based gamma detector optimization. However, the time and memory burden associated with the track-wise approach to particle transport and detection in commonly used Monte Carlo codes makes optical simulation prohibitive at a system level, where hundreds to thousands of scintillators must be modeled. Consequently, current large system simulations do not include detailed detector models to analyze the potential performance gain with new radiation detector technologies. Generative adversarial networks (GANs) are explored as a tool to speed up the optical simulation of crystal-based detectors. These networks learn training datasets made of high-dimensional data distributions. Once trained, the resulting model can produce distributions belonging to the training data probability distribution. In this work, we present the proof of concept of using a GAN to enable high-fidelity optical simulations of nuclear medicine systems, mitigating their computational complexity. The architecture of the first network version and high-fidelity training dataset is discussed. The latter is generated through accurate optical simulation with GATE\/Geant4, and contains the position, direction, and energy distributions of the optical photons emitted by 511 keV gamma rays in bismuth germanate and detected on the photodetector face. We compare the GAN and simulation-generated distributions in terms of similarity using the Jensen\u2013Shannon distance. Excellent agreement was found with similarity values higher than 93.5% for all distributions. Moreover, the GAN speeded the optical photon distribution generation by up to two orders of magnitude. These very promising results have the potential to drastically change the use of nuclear imaging system optical simulations by enabling high-fidelity system-level simulations in reasonable computation times. The ultimate is to integrate the GAN within GATE\/Geant4 since numerous applications (large detectors, bright scintillators, Cerenkov-based timing positron emission tomography) can benefit from these improvements.<\/jats:p>","DOI":"10.1088\/2632-2153\/acc782","type":"journal-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T22:35:51Z","timestamp":1679697351000},"page":"025005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["A generative adversarial network to speed up optical Monte Carlo simulations"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0414-9369","authenticated-orcid":true,"given":"Carlotta","family":"Trigila","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anirudh","family":"Srikanth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2439-1064","authenticated-orcid":true,"given":"Emilie","family":"Roncali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,4,12]]},"reference":[{"key":"mlstacc782bib1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aa9a2b","article-title":"Positioning true coincidences that undergo inter-and intra-crystal scatter for a sub-mm resolution cadmium zinc telluride-based PET system","volume":"63","author":"Abbaszadeh","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abaa24","article-title":"A validated Geant4 model of a whole-body PET scanner with four-layer DOI detectors","volume":"65","author":"Ahmed","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib3","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/trpms.2020.3024032","article-title":"Study of \u010cerenkov light emission in the semiconductors TlBr and TlCl for TOF-PET","volume":"5","author":"Ari\u00f1o-Estrada","year":"2020","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"mlstacc782bib4","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"mlstacc782bib5","doi-asserted-by":"publisher","first-page":"2566","DOI":"10.1109\/TNS.2009.2030411","article-title":"Measurements and ray-tracing simulations of light spread in LSO crystals","volume":"56","author":"Bauer","year":"2009","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"mlstacc782bib6","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aad2a6","article-title":"Sub-3 mm, near-200 ps TOF\/DOI-PET imaging with monolithic scintillator detectors in a 70 cm diameter tomographic setup","volume":"63","author":"Borghi","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41781-017-0004-6","article-title":"Learning particle physics by example: location-aware generative adversarial networks for physics synthesis","volume":"1","author":"de Oliveira","year":"2017","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstacc782bib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41781-018-0019-7","article-title":"Precise simulation of electromagnetic calorimeter showers using a Wasserstein generative adversarial network","volume":"3","author":"Erdmann","year":"2019","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstacc782bib9","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab845a","article-title":"DeepRICH: learning deeply Cherenkov detectors","volume":"1","author":"Fanelli","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstacc782bib10","article-title":"Physics reference manual","author":"","year":"2021"},{"key":"mlstacc782bib11","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.ejmp.2018.05.010","article-title":"A Monte Carlo simulation study of the impact of novel scintillation crystals on performance characteristics of PET scanners","volume":"50","author":"Ghabrial","year":"2018","journal-title":"Phys. Med."},{"key":"mlstacc782bib12","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"mlstacc782bib13","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TNS.2015.2408333","article-title":"A DOI detector with crystal scatter identification capability for high sensitivity and high spatial resolution PET imaging","volume":"62","author":"Gu","year":"2015","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"mlstacc782bib14","article-title":"Improved training of Wasserstein GANs 30","author":"Gulrajani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"mlstacc782bib15","article-title":"PE-GAN: Prior Embedding GAN for PXD images at Belle II","author":"Hashemi","year":"2023"},{"key":"mlstacc782bib16","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1109\/TRPMS.2022.3226950","article-title":"Potential of depth-of-interaction-based detection time correction in Cherenkov emitter crystals for TOF-PET","volume":"7","author":"He","year":"2022","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"mlstacc782bib17","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/TRPMS.2021.3069624","article-title":"Metascintillators for ultrafast gamma detectors: a review of current state and future perspectives","volume":"6","author":"Konstantinou","year":"2021","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"mlstacc782bib18","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab87f9","article-title":"Pushing Cherenkov PET with BGO via coincidence time resolution classification and correction","volume":"65","author":"Kratochwil","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib19","doi-asserted-by":"publisher","first-page":"L38","DOI":"10.1088\/0031-9155\/61\/18\/L38","article-title":"Bismuth germanate coupled to near ultraviolet silicon photomultipliers for time-of-flight PET","volume":"61","author":"Kwon","year":"2016","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib20","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1109\/TRPMS.2017.2756674","article-title":"Pushing the limits in time-of-flight PET imaging","volume":"1","author":"Lecoq","year":"2017","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"mlstacc782bib21","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0016-0032(96)00063-4","article-title":"The Jensen-Shannon divergence","volume":"334","author":"Men\u00e9ndez","year":"1997","journal-title":"J. Franklin Inst."},{"key":"mlstacc782bib22","article-title":"Mixed precision training","author":"Micikevicius","year":"2017"},{"key":"mlstacc782bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.97.014021","article-title":"CaloGAN: simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks","volume":"97","author":"Paganini","year":"2018","journal-title":"Phys. Rev. D"},{"key":"mlstacc782bib24","article-title":"On the regularization of Wasserstein GANs","author":"Petzka","year":"2017"},{"key":"mlstacc782bib25","doi-asserted-by":"publisher","first-page":"398","DOI":"10.3390\/cryst9080398","article-title":"Monte Carlo optical simulations of a small FoV gamma camera. Effect of scintillator thicknesses and septa materials","volume":"9","author":"Ricci","year":"2019","journal-title":"Crystals"},{"key":"mlstacc782bib26","doi-asserted-by":"publisher","first-page":"2185","DOI":"10.1088\/0031-9155\/58\/7\/2185","article-title":"Simulation of light transport in scintillators based on 3D characterization of crystal surfaces","volume":"58","author":"Roncali","year":"2013","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib27","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ab0f93","article-title":"Cerenkov light transport in scintillation crystals explained: realistic simulation with GATE","volume":"5","author":"Roncali","year":"2019","journal-title":"Biomed. Phys. Eng. Express"},{"key":"mlstacc782bib28","doi-asserted-by":"publisher","first-page":"R207","DOI":"10.1088\/1361-6560\/aa8b31","article-title":"Modelling the transport of optical photons in scintillation detectors for diagnostic and radiotherapy imaging","volume":"62","author":"Roncali","year":"2017a","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib29","doi-asserted-by":"publisher","first-page":"4811","DOI":"10.1088\/1361-6560\/aa6ca5","article-title":"An integrated model of scintillator-reflector properties for advanced simulations of optical transport","volume":"62","author":"Roncali","year":"2017b","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib30","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac7fd8","article-title":"Active-PET: a multifunctional PET scanner with dynamic gantry size featuring high-resolution and high-sensitivity imaging: a Monte Carlo simulation study","volume":"67","author":"Sanaat","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib31","doi-asserted-by":"publisher","first-page":"10TR03","DOI":"10.1088\/1361-6560\/abf276","article-title":"Advanced Monte Carlo simulations of emission tomography imaging systems with GATE","volume":"66","author":"Sarrut","year":"2021a","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib32","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac8c83","article-title":"The OpenGATE ecosystem for Monte Carlo simulation in medical physics","volume":"67","author":"Sarrut","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib33","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abde9a","article-title":"Modeling complex particles phase space with GAN for Monte Carlo SPECT simulations: a proof of concept","volume":"66","author":"Sarrut","year":"2021b","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib34","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab3fc1","article-title":"Generative adversarial networks (GAN) for compact beam source modelling in Monte Carlo simulations","volume":"64","author":"Sarrut","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib35","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.1088\/0031-9155\/48\/18\/305","article-title":"Monte Carlo simulations of a scintillation camera using GATE: validation and application modelling","volume":"48","author":"Staelens","year":"2003","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib36","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaad76","article-title":"Impact of event positioning algorithm on performance of a whole-body PET scanner using one-to-one coupled detectors","volume":"63","author":"Surti","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"mlstacc782bib37","doi-asserted-by":"publisher","first-page":"371","DOI":"10.3389\/fphy.2022.891602","article-title":"The accuracy of Cerenkov photons simulation in Geant4\/Gate depends on the parameterization of primary electron propagation","volume":"10","author":"Trigila","year":"2022","journal-title":"Front. Phys."},{"key":"mlstacc782bib38","doi-asserted-by":"crossref","DOI":"10.1088\/978-0-7503-2694-0ch1","article-title":"Monte Carlo techniques in nuclear medicine dosimetry","author":"Zaidi","year":"2022"},{"key":"mlstacc782bib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.105.045310","article-title":"Permutation Jensen-Shannon distance: a versatile and fast symbolic tool for complex time-series analysis","volume":"105","author":"Zunino","year":"2022","journal-title":"Phys. Rev. E"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T11:13:41Z","timestamp":1681298021000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,12]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,4,12]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acc782","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,12]]},"assertion":[{"value":"A generative adversarial network to speed up optical Monte Carlo simulations","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-12-27","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-03-24","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-04-12","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}