{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T02:50:50Z","timestamp":1791946250002,"version":"4.3.4"},"reference-count":44,"publisher":"IOP Publishing","issue":"24","license":[{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2022,12,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . One critical task for adaptive proton therapy is how to perform spot weight re-tuning and reoptimize plan, both of which are time-consuming and labor intensive. We proposed a deep learning framework (SWFT-Net) to speed up such a task, a starting point for us to move towards online adaptive proton therapy.\n                    <jats:italic>Approach<\/jats:italic>\n                    . For a H&amp;N patient case, a reference intensity modulated proton therapy plan was generated. For data augmentation, spot weights were modified to generate three datasets (DS10, DS30, DS50), corresponding to different levels of weight adjustment. For each dataset, the samples were split into the training and testing groups at a ratio of 8:2 (6400 for training, 1706 for testing). To ease the difficulty of machine learning, the residuals of dose maps and spot weights (i.e. difference relative to a reference) were used as inputs and outputs, respectively. Quantitative analyses were performed in terms of normalized root mean square error (NRMSE) of spot weights, Gamma passing rate and dose difference within the PTV.\n                    <jats:italic>Main results<\/jats:italic>\n                    . The SWFT-Net is able to generate an adapted plan in less than a second with a NVIDIA GeForce RTX 3090 GPU. For the 1706 samples in the testing dataset, the NRMSE is 0.41% (DS10), 1.05% (DS30) and 2.04% (DS50), respectively. Cold\/hot spots in the dose maps after adaptation are observed. The mean relative dose difference is 0.64% (DS10), 0.92% (DS30) and 0.88% (DS50), respectively. For all three datasets, the mean Gamma passing rate is consistently over 95% for both 1 mm\/1% and 3 mm\/3% settings.\n                    <jats:italic>Significance<\/jats:italic>\n                    . The proposed SWFT-Net is a promising tool to help realize adaptive proton therapy. It can be used as an alternative tool to other spot fine-tuning optimization algorithms, likely demonstrating superior performance in terms of speed, accuracy, robustness and minimum human interaction. This study lays down a foundation for us to move further incorporating other factors such as daily anatomical changes and propagated PTVs, and develop a truly online adaptive workflow in proton therapy.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/aca517","type":"journal-article","created":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T17:44:36Z","timestamp":1669139076000},"page":"245010","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["SWFT-Net: a deep learning framework for efficient fine-tuning spot weights towards adaptive proton therapy"],"prefix":"10.1088","volume":"67","author":[{"given":"Guoliang","family":"Zhang","sequence":"first","affiliation":[{"name":"Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University School of Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeng","family":"Han","sequence":"additional","affiliation":[{"name":"Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5320-3117","authenticated-orcid":true,"given":"Hao","family":"Peng","sequence":"additional","affiliation":[{"name":"Wuhan University"},{"name":"University of Texas Southwestern Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2022,12,9]]},"reference":[{"key":"pmbaca517bib1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190594","type":"journal-article","article-title":"Online daily adaptive proton therapy","volume":"93","author":"Albertini","year":"2019","journal-title":"Br. J. Radiol."},{"key":"pmbaca517bib2","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1016\/j.radonc.2017.09.037","type":"journal-article","article-title":"Treatment log files as a tool to identify treatment plan sensitivity to inaccuracies in scanned proton beam delivery","volume":"125","author":"Be Losi","year":"2017","journal-title":"Radiother. Oncol."},{"key":"pmbaca517bib3","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaba8c","type":"journal-article","article-title":"Feasibility of online IMPT adaptation using fast, automatic and robust dose restoration","volume":"63","author":"Bernatowicz","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib4","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaf30b","type":"journal-article","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":"2019","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib5","doi-asserted-by":"publisher","first-page":"e43","DOI":"10.1002\/mp.12256","type":"journal-article","article-title":"Use of image registration and fusion algorithms and techniques in radiotherapy: report of the AAPM radiation therapy committee task group no. 132","volume":"44","author":"Brock","year":"2017","journal-title":"Med. Phys."},{"key":"pmbaca517bib6","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1016\/j.ijrobp.2014.07.045","type":"journal-article","article-title":"Clinical implementation of intensity modulated proton therapy for thoracic malignancies","volume":"90","author":"Chang","year":"2014","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"pmbaca517bib7","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.radonc.2018.12.008","type":"journal-article","article-title":"Including anatomical variations in robust optimization for head and neck proton therapy can reduce the need of adaptation","volume":"131","author":"Cubillos-Mes\u00edas","year":"2019","journal-title":"Radiother. Oncol."},{"key":"pmbaca517bib8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1088\/0031-9155\/42\/1\/008","type":"journal-article","article-title":"Adaptive radiation therapy","volume":"42","author":"Di Yan","year":"1997","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib9","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1109\/TMI.2018.2823768","type":"journal-article","article-title":"Framing U-Net via deep convolutional framelets: application to sparse-view CT","volume":"37","author":"Han","year":"2018","journal-title":"IEEE Trans. Med. Imag"},{"key":"pmbaca517bib10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.03385","type":"journal-article","author":"He","year":"2016","journal-title":"Deep Residual Learning for Image Recognition."},{"key":"pmbaca517bib11","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.radonc.2016.12.018","type":"journal-article","article-title":"Adaptation is mandatory for intensity modulated proton therapy of advanced lung cancer to ensure target coverage","volume":"122","author":"Hoffmann","year":"2016","journal-title":"Radiother. Oncol."},{"key":"pmbaca517bib12","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab9707","type":"journal-article","article-title":"A machine learning framework with anatomical prior for online dose verification using positron emitters and PET in proton therapy","volume":"65","author":"Hu","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib13","doi-asserted-by":"publisher","first-page":"S135","DOI":"10.1016\/j.ijrobp.2009.06.093","type":"journal-article","article-title":"Accurate accumulation of dose for improved understanding of radiation effects in normal Tissue","volume":"76","author":"Jaffray","year":"2010","journal-title":"Int. J. Radiat. Oncol., Biol., Phys."},{"key":"pmbaca517bib14","doi-asserted-by":"publisher","first-page":"4254","DOI":"10.1088\/1361-6560\/aa5c12","type":"journal-article","article-title":"Near real-time automated dose restoration in IMPT to compensate for daily tissue density variations in prostate cancer","volume":"62","author":"Jagt","year":"2017","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib15","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","type":"journal-article","article-title":"Deep convolutional neural network for inverse problems in imaging","volume":"26","author":"Jin","year":"2017","journal-title":"IEEE Trans. Image Proc"},{"key":"pmbaca517bib16","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.zemedi.2018.10.003","type":"journal-article","article-title":"Dose-guided patient positioning in proton radiotherapy using multicriteria-optimization","volume":"29","author":"Kurz","year":"2019","journal-title":"Z. Med. Phys."},{"key":"pmbaca517bib17","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1016\/j.radonc.2014.10.009","type":"journal-article","article-title":"Intra thoracic anatomical changes in lung cancer patients during the course of radiotherapy","volume":"113","author":"Kwint","year":"2014","journal-title":"Radiother. Oncol. J. Eur. Soc. Ther. Radiol. Oncol."},{"key":"pmbaca517bib18","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/j.radonc.2015.01.017","type":"journal-article","article-title":"Robust optimization in intensity-modulated proton therapy to account for anatomy changes in lung cancer patients","volume":"114","author":"Li","year":"2015","journal-title":"Radiother. Oncol."},{"key":"pmbaca517bib19","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab3564","type":"journal-article","article-title":"Range and dose verification in proton therapy using proton-induced positron emitters and recurrent neural networks (RNNs)","volume":"64","author":"Liu","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib20","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1118\/1.3679340","type":"journal-article","article-title":"Robust optimization of intensity modulated proton therapy","volume":"39","author":"Liu","year":"2012","journal-title":"Med. Phys."},{"key":"pmbaca517bib21","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1118\/1.598248","type":"journal-article","article-title":"A technique for the quantitative evaluation of dose distributions","volume":"25","author":"Low","year":"1998","journal-title":"Med. Phys."},{"key":"pmbaca517bib22","doi-asserted-by":"publisher","first-page":"4045","DOI":"10.1002\/mp.13096","type":"journal-article","article-title":"A robust intensity modulated proton therapy optimizer based on monte carlo dose calculation","volume":"45","author":"Ma","year":"2018","journal-title":"Med. Phys."},{"key":"pmbaca517bib23","doi-asserted-by":"publisher","first-page":"5194","DOI":"10.1002\/mp.14443","type":"journal-article","article-title":"Feasibility study of patient\u2010specific dose verification in proton therapy utilizing positron emission tomography (PET) and generative adversarial network (GAN)","author":"Ma","year":"2020","journal-title":"Med. Phys."},{"key":"pmbaca517bib24","doi-asserted-by":"publisher","first-page":"1832","DOI":"10.1002\/mp.12858","type":"journal-article","article-title":"Positioning accuracy and daily dose assessment for prostate cancer treatment using in\u2010room CT image guidance at a proton therapy facility","volume":"45","author":"Maeda","year":"2018","journal-title":"Med. Phys."},{"key":"pmbaca517bib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/0284186X.2019.1630753","type":"journal-article","article-title":"Intensity modulated proton therapy plan generation in under ten seconds","volume":"58","author":"Matter","year":"2019","journal-title":"Acta Oncol."},{"key":"pmbaca517bib26","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aae2f4","type":"journal-article","article-title":"Alternatives to patient specific verification measurements in proton therapy: a comparative experimental study with intentional errors","volume":"63","author":"Matter","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib27","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1016\/j.ijrobp.2010.11.030","type":"journal-article","article-title":"Experience-based quality control of clinical intensity-modulated radiotherapy planning \u2013 science direct","volume":"81","author":"Moore","year":"2011","journal-title":"Int. J. Radiat. Oncol.*Biol.*Phys."},{"key":"pmbaca517bib28","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1016\/j.ejmp.2015.02.007","type":"journal-article","article-title":"Impact of interfractional changes in head and neck cancer patients on the delivered dose in intensity modulated radiotherapy with protons and photons","volume":"31","author":"M\u00fcller","year":"2015","journal-title":"Physica Med."},{"key":"pmbaca517bib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/0284186X.2019.1641217","type":"journal-article","article-title":"Daily adaptive proton therapy\u2014the key to innovative planning approaches for paranasal cancer treatments","volume":"58","author":"Nenoff","year":"2019","journal-title":"Acta Oncol."},{"key":"pmbaca517bib30","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/S0958-3947(01)00057-7","type":"journal-article","article-title":"Inverse planning for photon and proton beams","volume":"26","author":"Oelfke","year":"2001","journal-title":"Med. Dosim. : Official J. Am. Assoc. Med. Dosim."},{"key":"pmbaca517bib31","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1088\/0031-9155\/61\/3\/1171","type":"journal-article","article-title":"Assessing the quality of proton PBS treatment delivery using machine log files: comprehensive analysis of clinical treatments delivered at PSI gantry 2","volume":"61","author":"Scandurra","year":"2016","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib32","doi-asserted-by":"publisher","first-page":"1799","DOI":"10.1109\/TBME.2020.3020741","type":"journal-article","article-title":"Do CNNs Solve the CT inverse problem ?","volume":"68","author":"Sidky","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmbaca517bib33","doi-asserted-by":"publisher","first-page":"4777","DOI":"10.1088\/0031-9155\/60\/12\/4777","type":"journal-article","article-title":"Sub-second pencil beam dose calculation on GPU for adaptive proton therapy","volume":"60","author":"Silva","year":"2015","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib34","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.radonc.2016.04.002","type":"journal-article","article-title":"Effects of anatomical changes on pencil beam scanning proton plans in locally advanced NSCLC patients","volume":"120","author":"Szeto","year":"2016","journal-title":"Radiother. Oncol. J. Eur. Soc. Ther. Radiol. Oncology"},{"key":"pmbaca517bib35","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aacaa7","type":"journal-article","article-title":"An automated planning strategy for near real-time adaptive proton therapy in prostate cancer","volume":"63","author":"Thyrza","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib36","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab120c","type":"journal-article","article-title":"Impact of machine log-files uncertainties on the quality assurance of proton pencil beam scanning treatment delivery","volume":"64","author":"Toscano","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib37","doi-asserted-by":"publisher","first-page":"892","DOI":"10.3109\/0284186X.2016.1139179","type":"journal-article","article-title":"Dosimetric advantages of proton therapy compared with photon therapy using an adaptive strategy in cervical cancer","volume":"55","author":"van de Schoot","year":"2016","journal-title":"Acta Oncol."},{"key":"pmbaca517bib38","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s10107-004-0559-y","type":"journal-article","article-title":"On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming","volume":"106","author":"Wachter","year":"2006","journal-title":"Math. Program."},{"key":"pmbaca517bib39","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.radonc.2017.09.032","type":"journal-article","article-title":"Multiple-CT optimization of intensity-modulated proton therapy\u2014Is it possible to eliminate adaptive planning ?","volume":"128","author":"Wang","year":"2018","journal-title":"Radiother. Oncol.: J. Eur. Soc. Ther. Radiol. Oncol."},{"key":"pmbaca517bib40","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaf82d","type":"journal-article","article-title":"Log file based Monte Carlo calculations for proton pencil beam scanning therapy","volume":"64","author":"Winterhalter","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"pmbaca517bib41","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1118\/1.598932","type":"journal-article","article-title":"Algorithms and functionality of an intensity modulated radiotherapy optimization system","volume":"27","author":"Wu","year":"2000","journal-title":"Med. Phys."},{"key":"pmbaca517bib42","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1118\/1.1688214","type":"journal-article","article-title":"Speed and convergence properties of gradient algorithms for optimization of IMRT","volume":"31","author":"Zhang","year":"2004","journal-title":"Med. Phys."},{"key":"pmbaca517bib43","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1038\/nature25988","type":"journal-article","article-title":"Image reconstruction by domain-transform manifold learning","volume":"555","author":"Zhu","year":"2018","journal-title":"Nature"},{"key":"pmbaca517bib44","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1118\/1.3539749","type":"journal-article","article-title":"A planning quality evaluation tool for prostate adaptive IMRT based on machine learning","volume":"38","author":"Zhu","year":"2011","journal-title":"Med. Phys."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:53:17Z","timestamp":1778777597000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aca517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,9]]},"references-count":44,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2022,12,9]]},"published-print":{"date-parts":[[2022,12,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/aca517","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,9]]},"assertion":[{"value":"SWFT-Net: a deep learning framework for efficient fine-tuning spot weights towards adaptive proton therapy","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2022-07-03","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-11-22","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-12-09","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}