{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:01:01Z","timestamp":1792785661922,"version":"4.5.0"},"reference-count":46,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"German Federal Ministry for Economic Affairs and Energy","award":["KK5252103AJ2"],"award-info":[{"award-number":["KK5252103AJ2"]}],"id":[{"id":"https:\/\/ror.org\/02vgg2808","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["J. Radiol. Prot."],"published-print":{"date-parts":[[2026,12,1]]},"abstract":"Abstract<\/jats:title>\n \n Fluoroscopy-guided interventions expose clinical staff to x-ray scatter radiation, motivating accurate three-dimensional scatter-field predictions for radiation protection planning. Monte Carlo (MC) simulations provide reference accuracy but require minutes to hours of computation, while analytical models are faster but often lack spatial fidelity in complex geometries. We present a transformer-based model for scatter dosimetry in a single simulated interventional suite with fixed room geometry and object inventory, supporting near real-time inference on localised subvolumes and interactive runtimes for whole-room evaluation. We train a separate transformer-based model for each target quantity: air kerma per source photon, transported energy, and energy fluence per source photon. Each predictor encodes spectrum and technique parameters and represents room objects and their poses as a set of scene tokens. Predictions are obtained by coordinate-conditioned regression at queried voxel locations, so inference can be restricted to selected subvolumes and runtime scales with the number of queried voxels. The training set comprises\n \n \n \n <\/jats:tex-math>\n \n \n 715<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n simulated configurations with varied C-arm poses, spectra, patient-table and patient phantom positions. On an independent test set of\n \n \n \n <\/jats:tex-math>\n \n \n 48<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n configurations, the model achieves median\n \n \n \n <\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n 2<\/mml:mn>\n <\/mml:msup>\n ><\/mml:mo>\n 0.996<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n for log-transformed targets and structural similarity around\n \n \n \n <\/jats:tex-math>\n \n \n 0.83<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n . In linear units, median\n \n \n \n <\/jats:tex-math>\n \n \n \n R<\/mml:mi>\n 2<\/mml:mn>\n <\/mml:msup>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n values are\n \n \n \n <\/jats:tex-math>\n \n \n 0.885<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n for air kerma per source photon,\n \n \n \n <\/jats:tex-math>\n \n \n 0.97<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n for transported energy, and\n \n \n \n <\/jats:tex-math>\n \n \n 0.96<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n for energy fluence. Full-room inference, reconstructing the effective grid of about\n \n \n \n <\/jats:tex-math>\n \n \n 12.2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n million voxels, takes\n \n \n \n <\/jats:tex-math>\n \n \n \n \u223c<\/mml:mo>\n <\/mml:mrow>\n 13<\/mml:mn>\n \n s<\/mml:mtext>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n on an NVIDIA L40S GPU compared to\n \n \n \n <\/jats:tex-math>\n \n \n 17<\/mml:mn>\n \n min<\/mml:mtext>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n for MC simulation, yielding\n a<\/jats:italic>\n \n \n \n <\/jats:tex-math>\n \n \n \n \u223c<\/mml:mo>\n <\/mml:mrow>\n 77<\/mml:mn>\n \u00d7<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n speed-up. These results represent a step toward interactive, room-scale radiation protection planning, enabling rapid what-if analyses of staff positioning and procedure planning.\n <\/jats:p>","DOI":"10.1088\/1361-6498\/ae9ecf","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T05:57:40Z","timestamp":1791266260000},"page":"041501","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Query-based prediction of 3D x-ray scatter fields in an interventional suite using a transformer model"],"prefix":"10.1088","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7814-877X","authenticated-orcid":true,"given":"Niklas","family":"Rettig","sequence":"first","affiliation":[{"name":"Technical University of Applied Sciences Mannheim"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9792-0038","authenticated-orcid":true,"given":"Patrick","family":"Sch\u00fclein","sequence":"additional","affiliation":[{"name":"Technical University of Applied Sciences Mannheim"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3784-9297","authenticated-orcid":true,"given":"Yannick","family":"Bukschat","sequence":"additional","affiliation":[{"name":"Technical University of Applied Sciences Mannheim"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0244-6638","authenticated-orcid":false,"given":"Marcus","family":"Vetter","sequence":"additional","affiliation":[{"name":"Technical University of Applied Sciences Mannheim"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"key":"jrpae9ecfbib1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-75257-5","type":"journal-article","article-title":"Characterisation and mapping of scattered radiation fields in interventional radiology theatres","volume":"10","author":"Nowak","year":"2020","journal-title":"Sci. Rep."},{"key":"jrpae9ecfbib2","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1093\/rpd\/ncad275","type":"journal-article","article-title":"x-ray scatter in projection radiography","volume":"200","author":"Ylimaula","year":"2024","journal-title":"Radiat. Prot. Dosim."},{"key":"jrpae9ecfbib3","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1007\/s13246-024-01479-w","type":"journal-article","article-title":"Visualization of spatial dose distribution for effective radiation protection education in interventional radiology: obtaining high-accuracy spatial doses","volume":"47","author":"Mori","year":"2024","journal-title":"Phys. Eng. Sci. Med."},{"key":"jrpae9ecfbib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/0146645318777667","type":"journal-article","article-title":"Occupational radiological protection in interventional procedures","volume":"47","author":"International Commission on Radiological Protection","year":"2018","journal-title":"Ann. ICRP"},{"key":"jrpae9ecfbib5","article-title":"Radiation dose management for fluoroscopically-guided interventional medical procedures","author":"National Council on Radiation Protection and Measurements","year":"2010","type":"other"},{"key":"jrpae9ecfbib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.icrp.2012.06.001","type":"journal-article","article-title":"Radiological protection in cardiology","volume":"42","author":"Cousins","year":"2013","journal-title":"Ann. ICRP"},{"key":"jrpae9ecfbib7","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/S0168-90020301368-8","type":"journal-article","article-title":"Geant4\u2014a simulation toolkit","volume":"506","author":"Agostinelli","year":"2003","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"jrpae9ecfbib8","doi-asserted-by":"publisher","first-page":"4543","DOI":"10.1088\/0031-9155\/49\/19\/007","type":"journal-article","article-title":"GATE: a simulation toolkit for PET and SPECT","volume":"49","author":"S\u00e9bastien Jan","year":"2004","journal-title":"Phys. Med. Biol."},{"key":"jrpae9ecfbib9","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ae237b","type":"journal-article","article-title":"GATE 10 Monte Carlo particle transport simulation: I. development and new features","volume":"71","author":"Sarrut","year":"2026","journal-title":"Phys. Med. Biol."},{"key":"jrpae9ecfbib10","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ae237c","type":"journal-article","article-title":"GATE 10 Monte Carlo particle transport simulation: II","volume":"71","author":"Krah","year":"2026","journal-title":"Archit. Innov. Phys. Med. Biol."},{"key":"jrpae9ecfbib11","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1002\/acm2.12036","type":"journal-article","article-title":"Real-time, ray casting-based scatter dose estimation for C-arm x-ray system","volume":"18","author":"Alnewaini","year":"2017","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"jrpae9ecfbib12","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1088\/1361-6498\/aac392","type":"journal-article","article-title":"A fast simulation method for radiation maps using interpolation in a virtual environment","volume":"38","author":"Meng-Kun","year":"2018","journal-title":"J. Radiol. Prot."},{"key":"jrpae9ecfbib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.nucengdes.2021.111228","type":"journal-article","article-title":"BP neural network based reconstruction method for radiation field applications","volume":"380","author":"Zhou","year":"2021","journal-title":"Nucl. Eng. Des."},{"key":"jrpae9ecfbib14","doi-asserted-by":"publisher","DOI":"10.3389\/fenrg.2023.1151364","type":"journal-article","article-title":"Validation of the neural network for 3D photon radiation field reconstruction under various source distributions","volume":"11","author":"Hao","year":"2023","journal-title":"Front. Energy Res."},{"key":"jrpae9ecfbib15","doi-asserted-by":"publisher","first-page":"517","DOI":"10.7538\/yzk.2025.youxian.0184","type":"journal-article","article-title":"3D radiation field reconstruction method based on U-Net","volume":"59","author":"Jin","year":"2025","journal-title":"At. Energy Sci. Technol."},{"key":"jrpae9ecfbib16","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1117\/12.2580733","type":"journal-article","article-title":"Estimating Compton scatter distributions with a regressional neural network for use in a real-time staff dose management system for fluoroscopic procedures","volume":"11595","author":"Troville","year":"2021","journal-title":"Proc. SPIE"},{"key":"jrpae9ecfbib17","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac58dc","type":"journal-article","article-title":"Learning-based occupational x-ray scatter estimation","volume":"67","author":"Maul","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"jrpae9ecfbib18","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1093\/rpd\/ncaf064","type":"journal-article","article-title":"Machine learning-based estimation of occupational radiation dose in interventional cardiology","volume":"201","author":"H\u0131\u015f\u0131ro\u011flu","year":"2025","journal-title":"Radiat. Prot. Dosim."},{"key":"jrpae9ecfbib19","doi-asserted-by":"publisher","first-page":"179","DOI":"10.15748\/jasse.12.179","type":"journal-article","article-title":"Prediction of spatial x-ray dose distribution using pix2pix-based model","volume":"12","author":"Sato","year":"2025","journal-title":"J. Adv. Simul. Sci. Eng."},{"key":"jrpae9ecfbib20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762","type":"conference-proceedings","article-title":"Attention is all you need","volume":"vol 30","author":"Vaswani","year":"2017"},{"key":"jrpae9ecfbib21","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","type":"conference-proceedings"},{"key":"jrpae9ecfbib22","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.ejmp.2021.01.065","type":"journal-article","article-title":"Monte Carlo study of patient and medical staff radiation exposures during interventional cardiology","volume":"82","author":"Bhar","year":"2021","journal-title":"Phys. Med."},{"key":"jrpae9ecfbib23","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6498\/add53d","type":"journal-article","article-title":"RadField3D: a data generator and data format for deep learning in radiation-protection dosimetry for medical applications","volume":"45","author":"Lehner","year":"2025","journal-title":"J. Radiol. Prot."},{"key":"jrpae9ecfbib24","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6498\/ae268e","type":"journal-article","article-title":"Fast operating room scattered radiation calculation in x-ray guided interventions by using deep learning","volume":"45","author":"Harb","year":"2025","journal-title":"J. Radiol. Prot."},{"key":"jrpae9ecfbib25","doi-asserted-by":"publisher","first-page":"623","DOI":"10.4103\/jmp.jmp-99-24","type":"journal-article","article-title":"Artificial neural network-based model for predicting cardiologists\u2019 over-apron dose in CATHLABs","volume":"49","author":"Fardid","year":"2024","journal-title":"J. Med. Phys."},{"key":"jrpae9ecfbib26","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6498\/ae63da","type":"journal-article","article-title":"Fast occupational upper-limb radiation dose prediction using machine learning and Monte Carlo simulation","volume":"46","author":"Harb","year":"2026","journal-title":"J. Radiol. Prot."},{"key":"jrpae9ecfbib27","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1007\/s12194-026-01043-z","type":"journal-article","article-title":"Fast 3D whole-body occupational dose estimation in interventional radiology using physics-informed deep learning","volume":"19","author":"Harb","year":"2026","journal-title":"Radiol. Phys. Technol."},{"key":"jrpae9ecfbib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102902","type":"journal-article","article-title":"TransDose: transformer-based radiotherapy dose prediction from CT images guided by super-pixel-level GCN classification","volume":"89","author":"Jiao","year":"2023","journal-title":"Med. Image Anal."},{"key":"jrpae9ecfbib29","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13942","type":"journal-article","article-title":"TrDosePred: a deep learning dose prediction algorithm based on transformers for head and neck cancer radiotherapy","volume":"24","author":"Chenchen","year":"2023","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"jrpae9ecfbib30","doi-asserted-by":"publisher","first-page":"3159","DOI":"10.1002\/mp.16231","type":"journal-article","article-title":"Sub-second photon dose prediction via transformer neural networks","volume":"50","author":"Pastor-Serrano","year":"2023","journal-title":"Med. Phys."},{"key":"jrpae9ecfbib31","author":"Community","year":"2025","type":"book"},{"key":"jrpae9ecfbib32","doi-asserted-by":"publisher","first-page":"3630","DOI":"10.1002\/mp.14945","type":"journal-article","article-title":"Technical note: spekpy v2.0\u2014a software toolkit for modeling x-ray tube spectra","volume":"48","author":"Poludniowski","year":"2021","journal-title":"Med. Phys."},{"key":"jrpae9ecfbib33","doi-asserted-by":"publisher","first-page":"3","DOI":"10.2312\/egtp.19871000)","type":"other","article-title":"A fast voxel traversal algorithm for ray tracing","author":"Amanatides","year":"1987"},{"key":"jrpae9ecfbib34","author":"Lux","year":"1991","type":"book"},{"key":"jrpae9ecfbib35","author":"Lewis","year":"1993","type":"book"},{"key":"jrpae9ecfbib36","type":"other","article-title":"X-ray mass attenuation coefficients","volume":"vol 126","author":"Hubbell","year":"2004"},{"key":"jrpae9ecfbib37","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","type":"journal-article","article-title":"SciPy1.0: fundamental algorithms for scientific computing in python","volume":"vol 17","author":"SciPy 1.0 Contributors.","year":"2020","journal-title":"Nat. Methods"},{"key":"jrpae9ecfbib38","article-title":"Radiation quantities and units","author":"International Commission on Radiation Units and Measurements","year":"1980","type":"other"},{"key":"jrpae9ecfbib39","author":"Attix","year":"2004","type":"book"},{"key":"jrpae9ecfbib40","doi-asserted-by":"crossref","DOI":"10.6028\/NIST.IR.4812","type":"book","article-title":"Mass energy-transfer and mass energy-absorption coefficients, including in-flight positron annihilation for photon energies 1 keV to 100 MeV","author":"Higgins","year":"1992"},{"key":"jrpae9ecfbib41","author":"Santal\u00f3","year":"2004","edition":"2nd edn","type":"book"},{"key":"jrpae9ecfbib42","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1016\/S0306-4549(02)00107-X","type":"journal-article","article-title":"On the average chord length in reactor physics","volume":"30","author":"de Kruijf","year":"2003","journal-title":"Ann. Nucl. Energy"},{"key":"jrpae9ecfbib43","first-page":"pp 7537","type":"conference-proceedings","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"vol 33","author":"Tancik","year":"2020"},{"key":"jrpae9ecfbib44","first-page":"pp 5745","type":"conference-proceedings","article-title":"On the continuity of rotation representations in neural networks","author":"Zhou","year":"2019"},{"key":"jrpae9ecfbib45","doi-asserted-by":"crossref","DOI":"10.1145\/3620665.3640366","type":"conference-proceedings","article-title":"PyTorch 2: faster machine learning through dynamic Python bytecode transformation and graph compilation","author":"Ansel","year":"2024"},{"key":"jrpae9ecfbib46","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.1002\/mp.12702","type":"journal-article","article-title":"RECORDS: improved reporting of Monte Carlo radiation transport studies: report of the AAPM research committee task group 268","volume":"45","author":"Ioannis Sechopoulos","year":"2018","journal-title":"Med. Phys."}],"container-title":["Journal of Radiological Protection"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae9ecf","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae9ecf\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae9ecf\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae9ecf\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T05:57:44Z","timestamp":1791266264000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae9ecf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,6]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,10,6]]},"published-print":{"date-parts":[[2026,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6498\/ae9ecf","relation":{},"ISSN":["0952-4746","1361-6498"],"issn-type":[{"value":"0952-4746","type":"print"},{"value":"1361-6498","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,6]]},"assertion":[{"value":"Query-based prediction of 3D x-ray scatter fields in an interventional suite using a transformer model","name":"article_title","label":"Article Title"},{"value":"Journal of Radiological Protection","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published on behalf of the Society for Radiological Protection by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2026-04-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-26","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-06","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}