{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T18:08:15Z","timestamp":1791310095282,"version":"4.3.1"},"reference-count":49,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:00:00Z","timestamp":1778716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:00:00Z","timestamp":1778716800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100006703","name":"Universit\u00e9 de Bretagne Occidentale","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006703","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100011697","name":"Brittany Region","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100011697","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"crossref","award":["ANR-20-CE45-0025"],"award-info":[{"award-number":["ANR-20-CE45-0025"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["J. Radiol. Prot."],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Interventional procedures expose physicians to scattered radiation, particularly to their upper extremities, posing occupational health risks. Existing extremity dosimeters such as thermoluminescents, optically stimulated luminescence rings and active personal dosimeters provide limited spatial information, exhibit angular and energy dependence and offer little or no real-time feedback. This study develops machine learning (ML) models to estimate radiation dose values at discrete upper-limb locations using Monte Carlo (MC)-derived data and procedure-specific parameters. A dataset of 10\u2009000 MC dose maps was generated under varied clinical and geometric conditions. After log-transformation and normalisation, several ML models, including deep neural networks and tree-based regressor, were trained and assessed using five-fold cross-validation. Mean absolute error and relative error (RE) were evaluated on the original dose scale, and an ensemble of the three best-performing models was constructed to improve robustness. The ensemble consistently outperformed individual models, achieving an average RE of 3.69% and demonstrating stable performance across anatomical regions and dose levels. Highest accuracy was obtained for standard beam geometries, whereas larger discrepancies occurred in extreme configurations with steep dose gradients. Predicted dose patterns were consistent with the expected distributions across the upper-limb regions. The findings demonstrate the feasibility of ML-based extremity dose estimation in interventional environments. The proposed ensemble provides a rapid (around 10\u2009ms), scalable alternative to full MC simulations, enabling near real-time predictions of upper-limb occupational dose and supporting optimisation of radiation protection practices in image-guided procedures.<\/jats:p>","DOI":"10.1088\/1361-6498\/ae63da","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T22:48:43Z","timestamp":1776984523000},"page":"021516","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Fast occupational upper-limb radiation dose prediction using machine learning and Monte Carlo simulation"],"prefix":"10.1088","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9615-6831","authenticated-orcid":true,"given":"Hussein","family":"Harb","sequence":"first","affiliation":[{"name":"University of Brest, INSERM UMR1101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamilia","family":"Taguelmimt","sequence":"additional","affiliation":[{"name":"University of Brest, INSERM UMR1101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Didier","family":"Benoit","sequence":"additional","affiliation":[{"name":"University of Brest, INSERM UMR1101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Hieu","family":"Pham","sequence":"additional","affiliation":[{"name":"University of Brest, INSERM UMR1101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6672-9764","authenticated-orcid":false,"given":"Bahaa","family":"Nasr","sequence":"additional","affiliation":[{"name":"University of Brest, INSERM UMR1101"},{"name":"Brest University Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2756-942X","authenticated-orcid":true,"given":"Julien","family":"Bert","sequence":"additional","affiliation":[{"name":"University of Brest, INSERM UMR1101"},{"name":"Brest University Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"jrpae63dabib1","article-title":"13th EURADOS winter school on eye lens dosimetry","author":"Ainsbury","year":"2012","type":"conference-proceedings"},{"key":"jrpae63dabib2","doi-asserted-by":"publisher","first-page":"S78","DOI":"10.1016\/j.radmeas.2007.01.004","type":"journal-article","article-title":"Optically stimulated luminescence and its use in medical dosimetry","volume":"41","author":"Akselrod","year":"2006","journal-title":"Radiat. Meas."},{"key":"jrpae63dabib3","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1093\/rpd\/ncab045","type":"journal-article","article-title":"Personal dosimetry using Monte-Carlo simulations for occupational dose monitoring in interventional radiology: the results of a proof of concept in a clinical setting","volume":"195","author":"Alm\u00e9n","year":"2021","journal-title":"Radiat. Prot. Dosim."},{"key":"jrpae63dabib4","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","type":"journal-article","article-title":"Permutation importance: a corrected feature importance measure","volume":"26","author":"Altmann","year":"2010","journal-title":"Bioinformatics"},{"key":"jrpae63dabib5","first-page":"pp 6679","type":"conference-proceedings","article-title":"Tabnet: attentive interpretable tabular learning","author":"Arik","year":"2021"},{"key":"jrpae63dabib6","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.ejmp.2021.05.012","type":"journal-article","article-title":"Fast Monte Carlo codes for occupational dosimetry in interventional radiology","volume":"85","author":"Balcaza","year":"2021","journal-title":"Phys. Medica"},{"key":"jrpae63dabib7","first-page":"pp 1","type":"book","article-title":"Pearson correlation coefficient","author":"Benesty","year":"2009"},{"key":"jrpae63dabib8","doi-asserted-by":"publisher","first-page":"5593","DOI":"10.1088\/0031-9155\/58\/16\/5593","type":"journal-article","article-title":"Geant4-based Monte Carlo simulations on GPU for medical applications","volume":"58","author":"Bert","year":"2013","journal-title":"Phys. Med. Biol."},{"key":"jrpae63dabib9","doi-asserted-by":"publisher","first-page":"1648","DOI":"10.21037\/jtd.2019.12.86","type":"journal-article","article-title":"Radiation protection in the cardiac catheterization laboratory","volume":"12","author":"Biso","year":"2020","journal-title":"J. Thoracic Dis."},{"key":"jrpae63dabib10","article-title":"Blender\u2013a 3D modelling and rendering package","author":"Blender Online Community","year":"2023","type":"other"},{"key":"jrpae63dabib11","first-page":"pp 785","type":"conference-proceedings","article-title":"Xgboost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"jrpae63dabib12","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1269\/jrr.09112","type":"journal-article","article-title":"Radiation dose and radiation protection for patients and physicians during interventional procedure","volume":"51","author":"Chida","year":"2010","journal-title":"J. Radiat. Res."},{"key":"jrpae63dabib13","doi-asserted-by":"publisher","first-page":"1252","DOI":"10.1016\/j.radmeas.2011.07.008","type":"journal-article","article-title":"Use of active personal dosemeters in interventional radiology and cardiology: tests in laboratory conditions and recommendations-oramed project","volume":"46","author":"Clairand","year":"2011","journal-title":"Radiat. Meas."},{"key":"jrpae63dabib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrras.2024.101252","type":"journal-article","article-title":"Machine learning and neural network approaches for enhanced measuring and prediction of radiation doses","volume":"18","author":"Elhaie","year":"2025","journal-title":"J. Radiat. Res. Appl. Sci."},{"key":"jrpae63dabib15","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":"jrpae63dabib16","doi-asserted-by":"publisher","first-page":"1","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":"jrpae63dabib17","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ae2cdf","type":"journal-article","article-title":"Machine learning-based modeling of the anode heel effect in x-ray beam Monte Carlo simulations","volume":"71","author":"Harb","year":"2025","journal-title":"Phys. Med. Biol."},{"key":"jrpae63dabib18","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":"jrpae63dabib19","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":"jrpae63dabib20","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","type":"journal-article","article-title":"Accurate predictions on small data with a tabular foundation model","volume":"637","author":"Hollmann","year":"2025","journal-title":"Nature"},{"key":"jrpae63dabib21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2023.102543","type":"journal-article","article-title":"Effectiveness of staff radiation protection devices for interventional cardiology procedures","volume":"107","author":"Huet","year":"2023","journal-title":"Phys. Medica"},{"key":"jrpae63dabib22","doi-asserted-by":"publisher","DOI":"10.1038\/srep42077","type":"journal-article","article-title":"Operator radiation and the efficacy of ceiling-suspended lead screen shielding during coronary angiography: an anthropomorphic phantom study using real-time dosimeters","volume":"7","author":"Jia","year":"2017","journal-title":"Sci. Rep."},{"key":"jrpae63dabib23","article-title":"Lightgbm: a highly efficient gradient boosting decision tree","author":"Ke","year":"2017","type":"conference-proceedings"},{"key":"jrpae63dabib24","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1177\/0146645319893605","type":"journal-article","article-title":"ICRP publication 145: adult mesh-type reference computational phantoms","volume":"49","author":"Kim","year":"2020","journal-title":"Ann. ICRP"},{"key":"jrpae63dabib25","doi-asserted-by":"publisher","first-page":"178","DOI":"10.14716\/ijtech.v4i2.107","type":"journal-article","article-title":"A study on performance of low-dose medical radiation shielding fiber (RSF) in CT scans","volume":"4","author":"Kim","year":"2013","journal-title":"Int. J. Technol."},{"key":"jrpae63dabib26","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ae237c","type":"journal-article","article-title":"Gate 10 Monte Carlo particle transport simulation -Part ii: architecture and innovations","volume":"71","author":"Krah","year":"2025","journal-title":"Phys. Med. Biol."},{"key":"jrpae63dabib27","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1002\/mp.15555","type":"journal-article","article-title":"Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks","volume":"49","author":"Mentzel","year":"2022","journal-title":"Med. Phys."},{"key":"jrpae63dabib28","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.avsg.2023.07.104","type":"journal-article","article-title":"Monte Carlo dosimetry validation for x-ray guided endovascular procedures","volume":"99","author":"Nasr","year":"2024","journal-title":"Ann. Vascular Surg."},{"key":"jrpae63dabib29","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1002\/mp.13955","type":"journal-article","article-title":"Incorporating human and learned domain knowledge into training deep neural networks: a differentiable dose-volume histogram and adversarial inspired framework for generating pareto optimal dose distributions in radiation therapy","volume":"47","author":"Nguyen","year":"2020","journal-title":"Med. Phys."},{"key":"jrpae63dabib30","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.ejmp.2021.05.015","type":"journal-article","article-title":"Recommendations for the use of active personal dosemeters (APDs) in interventional workplaces in hospitals","volume":"87","author":"O\u2019Connor","year":"2021","journal-title":"Phys. Medica"},{"key":"jrpae63dabib31","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6498\/ac9394","type":"journal-article","article-title":"Feasibility study of computational occupational dosimetry: evaluating a proof-of-concept in an endovascular and interventional cardiology setting","volume":"42","author":"O\u2019Connor","year":"2022","journal-title":"J. Radiol. Prot."},{"key":"jrpae63dabib32","doi-asserted-by":"publisher","first-page":"209","DOI":"10.23042\/radin.2024.18.3.209","type":"journal-article","article-title":"Development of a real-time active safety management platform and data collection device for the safety of radiation workers","volume":"18","author":"Park","year":"2024","journal-title":"J. Radiat. Ind."},{"key":"jrpae63dabib33","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","type":"conference-proceedings"},{"key":"jrpae63dabib34","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1093\/oxfordjournals.rpd.a079971","type":"journal-article","article-title":"Thermoluminescence dosimetry and its applications","volume":"1","author":"Pradhan","year":"1981","journal-title":"Radiat. Prot. Dosim."},{"key":"jrpae63dabib35","doi-asserted-by":"publisher","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","type":"journal-article","article-title":"Random forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J. Insur. Med."},{"key":"jrpae63dabib36","doi-asserted-by":"publisher","first-page":"4654","DOI":"10.1002\/mp.13758","type":"journal-article","article-title":"Physics-driven learning of x-ray skin dose distribution in interventional procedures","volume":"46","author":"Roser","year":"2019","journal-title":"Med. Phys."},{"key":"jrpae63dabib37","doi-asserted-by":"publisher","first-page":"9411","DOI":"10.1007\/s00330-023-09839-y","type":"journal-article","article-title":"Real-time, acquisition parameter-free voxel-wise patient-specific Monte Carlo dose reconstruction in whole-body CT scanning using deep neural networks","volume":"33","author":"Salimi","year":"2023","journal-title":"Eur. Radiol."},{"key":"jrpae63dabib38","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ae237b","type":"journal-article","article-title":"Gate 10 Monte Carlo particle transport simulation -Part i: development and new features","volume":"71","author":"Sarrut","year":"2025","journal-title":"Phys. Med. Biol."},{"key":"jrpae63dabib39","first-page":"pp 35","type":"conference-proceedings","article-title":"Evaluating tree explanation methods for anomaly reasoning: a case study of SHAP treeexplainer and treeinterpreter","author":"Sharma","year":"2020"},{"key":"jrpae63dabib40","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1259\/bjr\/26692771","type":"journal-article","article-title":"Monte Carlo simulations of occupational radiation doses in interventional radiology","volume":"80","author":"Siiskonen","year":"2007","journal-title":"Brit. J. Radiol."},{"key":"jrpae63dabib41","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1186\/1471-2105-9-307","type":"journal-article","article-title":"Conditional variable importance for random forests","volume":"9","author":"Strobl","year":"2008","journal-title":"BMC Bioinform."},{"key":"jrpae63dabib42","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1007\/s00330-024-11002-0","type":"journal-article","article-title":"A machine learning-based pipeline for multi-organ\/tissue patient-specific radiation dosimetry in CT","volume":"35","author":"Tzanis","year":"2025","journal-title":"Eur. Radiol."},{"key":"jrpae63dabib43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2023.103195","type":"journal-article","article-title":"A fully automated machine learning-based methodology for personalized radiation dose assessment in thoracic and abdomen CT","volume":"117","author":"Tzanis","year":"2024","journal-title":"Phys. Medica"},{"key":"jrpae63dabib44","article-title":"Cluster","author":"University of Western Brittany","year":"2024","type":"other"},{"key":"jrpae63dabib45","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1148\/radiol.2482071800","type":"journal-article","article-title":"Eye lens exposure to radiation in interventional suites: caution is warranted","volume":"248","author":"Vano","year":"2008","journal-title":"Radiology"},{"key":"jrpae63dabib46","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1259\/bjr.71.849.10195011","type":"journal-article","article-title":"Radiation exposure to medical staff in interventional and cardiac radiology","volume":"71","author":"Vano","year":"1998","journal-title":"Brit. J. Radiol."},{"key":"jrpae63dabib47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/0146645317717209","type":"journal-article","article-title":"Diagnostic reference levels in medical imaging. ICRP Publication 135","volume":"46","author":"Va\u00f1\u00f3","year":"2017","journal-title":"Ann. ICRP"},{"key":"jrpae63dabib48","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ace678","type":"journal-article","article-title":"Fast dose calculation in x-ray guided interventions by using deep learning","volume":"68","author":"Villa","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"jrpae63dabib49","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1002\/mp.13953","type":"journal-article","article-title":"A feasibility study on deep learning-based radiotherapy dose calculation","volume":"47","author":"Xing","year":"2020","journal-title":"Med. Phys."}],"container-title":["Journal of Radiological Protection"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:22:32Z","timestamp":1778779352000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6498\/ae63da"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,14]]},"references-count":49,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,5,14]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6498\/ae63da","relation":{},"ISSN":["0952-4746","1361-6498"],"issn-type":[{"value":"0952-4746","type":"print"},{"value":"1361-6498","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,14]]},"assertion":[{"value":"Fast occupational upper-limb radiation dose prediction using machine learning and Monte Carlo simulation","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 Society for Radiological Protection. Published on behalf of SRP by IOP Publishing Limited. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-12-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-04-23","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}