{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T23:39:43Z","timestamp":1782776383325,"version":"3.54.5"},"reference-count":40,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T00:00:00Z","timestamp":1617667200000},"content-version":"vor","delay-in-days":36,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T00:00:00Z","timestamp":1617667200000},"content-version":"tdm","delay-in-days":36,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R01CA237269"],"award-info":[{"award-number":["R01CA237269"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Pencil beam (PB) dose calculation is fast but inaccurate due to the approximations when dealing with inhomogeneities. Monte Carlo (MC) dose calculation is the most accurate method but it is time consuming. The aim of this study was to develop a deep learning model that can boost the accuracy of PB dose calculation to the level of MC dose by converting PB dose to MC dose for different tumor sites. The proposed model uses the PB dose and computed tomography image as inputs to generate the MC dose. We used 290 patients (90 head and neck, 93 liver, 75 prostate and 32 lung) to train, validate, and test the model. For each tumor site, we performed four numerical experiments to explore various combinations of training datasets. Training the model on data from all tumor sites together and using the dose distribution of each individual beam as input yielded the best performance for all four tumor sites. The average gamma passing rate (1 mm\/1%) between the converted and the MC dose was 92.8%, 92.7%, 89.7% and 99.6% for head and neck, liver, lung, and prostate test patients, respectively. The average dose conversion time for a single field was less than 4 s. The trained model can be adapted to new datasets through transfer learning. Our deep learning-based approach can quickly boost the accuracy of PB dose to that of MC dose. The developed model can be added to the clinical workflow of proton treatment planning to improve dose calculation accuracy.<\/jats:p>","DOI":"10.1088\/2632-2153\/abb6d5","type":"journal-article","created":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T22:34:07Z","timestamp":1599690847000},"page":"015017","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Improving proton dose calculation accuracy by using deep learning"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4988-6255","authenticated-orcid":false,"given":"Chao","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9590-0655","authenticated-orcid":false,"given":"Dan","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixun","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana Barragan","family":"Montero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7554-8818","authenticated-orcid":false,"given":"Jan","family":"Schuemann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijiao","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuehu","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,4,6]]},"reference":[{"key":"mlstabb6d5bib1","doi-asserted-by":"publisher","first-page":"R99-117","DOI":"10.1088\/0031-9155\/57\/11\/R99","article-title":"Range uncertainties in proton therapy and the role of Monte Carlo simulations","volume":"57","author":"Paganetti","year":"2012","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib2","doi-asserted-by":"publisher","first-page":"7783","DOI":"10.1088\/0031-9155\/57\/23\/7783","article-title":"GPU-based fast Monte Carlo dose calculation for proton therapy","volume":"57","author":"Jia","year":"2012","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib3","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1088\/0031-9155\/41\/8\/005","article-title":"A pencil beam algorithm for proton dose calculations","volume":"41","author":"Hong","year":"1996","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib4","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1088\/0031-9155\/44\/1\/004","article-title":"Dose calculation models for proton treatment planning using a dynamic beam delivery system: an attempt to include density heterogeneity effects in the analytical dose calculation","volume":"44","author":"Schaffner","year":"1999","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib5","doi-asserted-by":"publisher","first-page":"114","DOI":"10.21037\/tlcr.2018.04.04","article-title":"Advanced proton beam dosimetry part II: Monte Carlo vs. pencil beam-based planning for lung cancer","volume":"7","author":"Maes","year":"2018","journal-title":"Transl. Lung Cancer Res."},{"key":"mlstabb6d5bib6","doi-asserted-by":"publisher","first-page":"5631","DOI":"10.1002\/mp.13231","article-title":"Validation and application of a fast Monte Carlo algorithm for assessing the clinical impact of approximations in analytical dose calculations for pencil beam scanning proton therapy","volume":"45","author":"Huang","year":"2018","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib7","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190583","article-title":"Is an analytical dose engine sufficient for intensity modulate proton therapy in lung cancer?","volume":"93","author":"Teoh","year":"2019","journal-title":"Br. J. Radiol."},{"key":"mlstabb6d5bib8","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/j.ijrobp.2015.04.006","article-title":"Assessing the clinical impact of approximations in analytical dose calculations for proton therapy","volume":"92","author":"Schuemann","year":"2015","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"mlstabb6d5bib9","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1002\/acm2.12497","article-title":"A comprehensive dosimetric study of Monte Carlo and pencil\u2010beam algorithms on intensity\u2010modulated proton therapy for breast cancer","volume":"20","author":"Liang","year":"2019","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"mlstabb6d5bib10","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20140293","article-title":"Monte Carlo simulations will change the way we treat patients with proton beams today","volume":"87","author":"Paganetti","year":"2014","journal-title":"Br. J. Radiol."},{"key":"mlstabb6d5bib11","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1016\/j.ijrobp.2017.06.003","article-title":"Pencil beam algorithms are unsuitable for proton dose calculations in lung","volume":"99","author":"Taylor","year":"2017","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"mlstabb6d5bib12","doi-asserted-by":"publisher","DOI":"10.1118\/1.4812682","article-title":"An algorithm to assess the need for clinical Monte Carlo dose calculation for small proton therapy fields based on quantification of tissue heterogeneity","volume":"40","author":"Bueno","year":"2013","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib13","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.ijrobp.2014.02.023","article-title":"Quantification of proton dose calculation accuracy in the lung","volume":"89","author":"Grassberger","year":"2014","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"mlstabb6d5bib14","doi-asserted-by":"publisher","first-page":"7659","DOI":"10.1088\/1361-6560\/aa82a5","article-title":"Dosimetric evaluation of a commercial proton spot scanning Monte\u2010Carlo dose algorithm: comparisons against measurements and simulations","volume":"62","author":"Saini","year":"2017","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib15","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaa845","article-title":"Comparison of Monte Carlo and analytical dose computations for intensity modulated proton therapy","volume":"63","author":"Yepes","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib16","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaf30b","article-title":"Online adaption approaches for intensity modulated proton therapy for head and neck patients based on cone beam CTs and Monte Carlo simulations","volume":"64","author":"Botas","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib17","doi-asserted-by":"publisher","first-page":"3682","DOI":"10.1088\/1361-6560\/aa5d43","article-title":"Initial development of goCMC: a GPU-oriented fast cross-platform Monte Carlo engine for carbon ion therapy","volume":"62","author":"Qin","year":"2017","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib18","doi-asserted-by":"publisher","first-page":"7347","DOI":"10.1088\/0031-9155\/61\/20\/7347","article-title":"Recent developments and comprehensive evaluations of a GPU-based Monte Carlo package for proton therapy","volume":"61","author":"Qin","year":"2016","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib19","doi-asserted-by":"publisher","first-page":"N21","DOI":"10.1088\/0031-9155\/54\/1\/N03","article-title":"Monte Carlo fast dose calculator for proton radiotherapy: application to a voxelized geometry representing a patient with prostate cancer","volume":"54","author":"Yepes","year":"2009","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib20","doi-asserted-by":"publisher","first-page":"R151","DOI":"10.1088\/0031\u20139155\/59\/4\/R151","article-title":"GPU-based high-performance computing for radiation therapy","volume":"59","author":"Jia","year":"2014","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib21","doi-asserted-by":"publisher","DOI":"10.1118\/1.4901522","article-title":"GPU-accelerated and Monte Carlo-based intensity modulated proton therapy optimization system","volume":"41","author":"Ma","year":"2014","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib22","doi-asserted-by":"publisher","first-page":"2967","DOI":"10.1118\/1.4921046","article-title":"A fast GPU-based Monte Carlo simulation of proton transport with detailed modeling of nonelastic interactions","volume":"42","author":"Wan Chan Tseung","year":"2015","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib23","doi-asserted-by":"publisher","first-page":"7419","DOI":"10.1088\/0031-9155\/60\/19\/7419","article-title":"A GPU OpenCL based cross-platform Monte Carlo dose calculation engine (goMC)","volume":"60","author":"Tian","year":"2015","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib24","doi-asserted-by":"publisher","first-page":"1700","DOI":"10.1118\/1.4943377","article-title":"Fast multipurpose Monte Carlo simulation for proton therapy using multi\u2010and many\u2010core CPU architectures","volume":"43","author":"Souris","year":"2016","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib25","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1088\/1361-6560\/62\/2\/415","article-title":"Voxel-based dose prediction with multi-patient atlas selection for automated radiotherapy treatment planning","volume":"62","author":"Mcintosh","year":"2017","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib26","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1038\/s41598-018-37741-x","article-title":"Dose prediction with U-net: a feasibility study for predicting dose distributions from contours using deep learning on prostate IMRT patients","volume":"9","author":"Nguyen","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstabb6d5bib27","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab039b","article-title":"3D radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected U-net deep learning architecture","volume":"64","author":"Nguyen","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib28","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1002\/mp.13262","article-title":"A feasibility study on an automated method to generate patient-specific dose distributions for radiotherapy using deep learning","volume":"46","author":"Chen","year":"2019","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib29","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1002\/mp.13271","article-title":"Automatic treatment planning based on three-dimensional dose distribution predicted from deep learning technique","volume":"46","author":"Fan","year":"2019","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib30","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaef74","article-title":"DoseNet: a volumetric dose prediction algorithm using 3D fully- convolutional neural networks","volume":"63","author":"Kearney","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"mlstabb6d5bib31","doi-asserted-by":"publisher","first-page":"3679","DOI":"10.1002\/mp.13597","article-title":"Three-dimensional dose prediction for lung IMRT patients with deep neural networks: robust learning from heterogeneous beam configurations","volume":"46","author":"Barrag\u00e1n-Montero","year":"2019","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib32","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1002\/mp.13953","article-title":"Technical note: a feasibility study on deep learning-based radiotherapy dose calculation","volume":"47","author":"Xing","year":"2019","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib33","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger","year":"2015","journal-title":"Lect. Notes Comput. Sci."},{"key":"mlstabb6d5bib34","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"mlstabb6d5bib35","doi-asserted-by":"publisher","first-page":"6818","DOI":"10.1118\/1.4758060","article-title":"TOPAS: an innovative proton Monte Carlo platform for research and clinical applications","volume":"39","author":"Perl","year":"2012","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib36","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/S0168-9002(03)01368-8","article-title":"GEANT4 - a simulation toolkit","volume":"506","author":"Agostinelli","year":"2003","journal-title":"Nuclear Instrum. Methods Phys. Res. A"},{"key":"mlstabb6d5bib37","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2015"},{"key":"mlstabb6d5bib38","article-title":"Tensorflow: large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"mlstabb6d5bib39","doi-asserted-by":"publisher","first-page":"1647","DOI":"10.1118\/1.2721657","article-title":"A fast algorithm for gamma evaluation in 3D","volume":"34","author":"Wendling","year":"2007","journal-title":"Med. Phys."},{"key":"mlstabb6d5bib40","doi-asserted-by":"publisher","first-page":"281","DOI":"10.3389\/fonc.2015.00281","article-title":"Fast pencil beam dose calculation for proton therapy using a double-Gaussian beam model","volume":"5","author":"da Silva","year":"2015","journal-title":"Front. Oncol."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T09:03:02Z","timestamp":1714726982000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,1]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,4,6]]},"published-print":{"date-parts":[[2021,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abb6d5","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,1]]},"assertion":[{"value":"Improving proton dose calculation accuracy by using deep learning","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 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-06-10","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-09-09","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-04-06","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}