{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T20:34:08Z","timestamp":1792010048755,"version":"4.4.0"},"reference-count":33,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Institute of Health","award":["R01CA301555"],"award-info":[{"award-number":["R01CA301555"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Treatment planning is a multi-disciplinary effort that requires medical decision-making, specialized training, and access to specialized software. Recently, deep learning has arisen as a powerful method for predicting patient-specific dose distributions. This work presents the radiotherapy dose inference and analysis toolkit (RADIANT), an open-source, fully configurable framework for 3D radiotherapy dose prediction. Built upon the Medical Imaging Segmentation Toolkit, RADIANT supports diverse network architectures, loss functions, and training strategies.\n                    <jats:italic>Approach.<\/jats:italic>\n                    We demonstrate its capabilities on cervical and prostate treatment plans generated with the radiation planning assistant, and on head and neck cancer plans from the American Association of Physicists in Medicine OpenKBP challenge data. For cervical cancer, we trained and compared nnU-Net, FMG-Net, W-Net, ddU-Net, and Swin UNETR using clinical metrics such as dose score, homogeneity index, and percent errors in\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mrow>\n                            <mml:msub>\n                              <mml:mi>D<\/mml:mi>\n                              <mml:mrow>\n                                <mml:mn>95<\/mml:mn>\n                              <\/mml:mrow>\n                            <\/mml:msub>\n                          <\/mml:mrow>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    ,\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mrow>\n                            <mml:msub>\n                              <mml:mi>D<\/mml:mi>\n                              <mml:mrow>\n                                <mml:mn>98<\/mml:mn>\n                              <\/mml:mrow>\n                            <\/mml:msub>\n                          <\/mml:mrow>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    , and\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mrow>\n                            <mml:msub>\n                              <mml:mi>D<\/mml:mi>\n                              <mml:mrow>\n                                <mml:mn>99<\/mml:mn>\n                              <\/mml:mrow>\n                            <\/mml:msub>\n                          <\/mml:mrow>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    . Benchmarking was also performed on the OpenKBP dataset using dose score and dose-volume histogram (DVH) score for comparison with top challenge submissions.\n                    <jats:italic>Results.<\/jats:italic>\n                    Our results indicate that RADIANT provides a scalable platform for the rapid development and benchmarking of dose prediction models for selected cancer sites (cervix, prostate, head and neck). For cervical cancer, the best configuration (nnU-Net architecture, mean absolute error loss, cosine learning rate scheduler) achieved a dose score of 1.31 and sub-\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mn>1<\/mml:mn>\n                          <mml:mi mathvariant=\"normal\">%<\/mml:mi>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    errors in\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mrow>\n                            <mml:msub>\n                              <mml:mi>D<\/mml:mi>\n                              <mml:mrow>\n                                <mml:mn>95<\/mml:mn>\n                              <\/mml:mrow>\n                            <\/mml:msub>\n                          <\/mml:mrow>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    and\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mrow>\n                            <mml:msub>\n                              <mml:mi>D<\/mml:mi>\n                              <mml:mrow>\n                                <mml:mn>98<\/mml:mn>\n                              <\/mml:mrow>\n                            <\/mml:msub>\n                          <\/mml:mrow>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    on the training set, and a dose score of 1.20 on the test set. The same configuration performed best on prostate data with a dose score of 1.96 on a test set. On the head and neck OpenKBP data, RADIANT achieved a dose score of 2.702 and a DVH score of 1.495, competitive with top challenge results.\n                    <jats:italic>Significance.<\/jats:italic>\n                    This work provides an open-source, fully configurable framework for deep learning\u2013based dose prediction. RADIANT facilitates reproducible experimentation across data preprocessing, model configuration, training, and evaluation for multiple cancer sites and anatomical structures.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae7090","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T22:48:16Z","timestamp":1779317296000},"page":"035046","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["RADIANT: A fully configurable radiotherapy dose prediction framework"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5281-5541","authenticated-orcid":true,"given":"Josiane","family":"Pafeng","sequence":"first","affiliation":[{"name":"Radiation Physics, The University of Texas MD Anderson Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0041-7239","authenticated-orcid":false,"given":"Adrian","family":"Celaya","sequence":"additional","affiliation":[{"name":"Department of Computational Applied Mathematics and Operations Research, Rice University"},{"name":"Google LLC,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4659-0766","authenticated-orcid":true,"given":"Skylar","family":"Gay","sequence":"additional","affiliation":[{"name":"Radiation Physics, The University of Texas MD Anderson Cancer Center"},{"name":"Graduate School of Biomedical Sciences, The University of Texas MD Anderson Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Fuentes","sequence":"additional","affiliation":[{"name":"Imaging Physics, The University of Texas MD Anderson Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mary","family":"Martel","sequence":"additional","affiliation":[{"name":"Radiation Physics, The University of Texas MD Anderson Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3241-6145","authenticated-orcid":false,"given":"Laurence","family":"Court","sequence":"additional","affiliation":[{"name":"Radiation Physics, The University of Texas MD Anderson Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1583-7121","authenticated-orcid":true,"given":"Tucker","family":"Netherton","sequence":"additional","affiliation":[{"name":"Radiation Physics, The University of Texas MD Anderson Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"bpexae7090bib1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2023-077253","type":"journal-article","article-title":"ARCHERY: a prospective observational study of artificial intelligence-based radiotherapy treatment planning for cervical, head and neck and prostate cancer\u2014study protocol","volume":"13","author":"Aggarwal","year":"2023","journal-title":"BMJ Open."},{"key":"bpexae7090bib2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac8044","type":"journal-article","article-title":"OpenKBP-Opt: an international and reproducible evaluation of 76 knowledge-based planning pipelines","volume":"67","author":"Babier","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"bpexae7090bib3","doi-asserted-by":"publisher","first-page":"5549","DOI":"10.1002\/mp.14845","type":"journal-article","article-title":"OpenKBP: the open-access knowledge-based planning grand challenge and dataset","volume":"48","author":"Babier","year":"2021","journal-title":"Med. Phys."},{"key":"bpexae7090bib4","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.ijrobp.2016.09.015","type":"journal-article","article-title":"Does peer review of radiation plans affect clinical care? A systematic review of the literature","volume":"97","author":"Brunskill","year":"2017","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"bpexae7090bib5","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-031-25066-8_9","type":"book","article-title":"Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation","volume":"3","author":"Cao","year":"2023"},{"key":"bpexae7090bib6","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1109\/TMI.2022.3224873","type":"journal-article","article-title":"PocketNet: a smaller neural network for medical image analysis","volume":"42","author":"Celaya","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae7090bib7","article-title":"MIST: a simple and scalable end-to-end 3d medical imaging segmentation framework","author":"Celaya","year":"2024","type":"preprint"},{"key":"bpexae7090bib8","doi-asserted-by":"crossref","DOI":"10.52591\/lxai202312104","type":"conference-proceedings","article-title":"FMG-net and W-net: multigrid inspired deep learning architectures for medical imaging segmentation","author":"Celaya","year":"2023"},{"key":"bpexae7090bib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.111237","type":"journal-article","article-title":"nnDoseNet: intuitive and flexible deep learning framework to train and evaluate radiotherapy dose prediction models","volume":"198","author":"Chang","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"bpexae7090bib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110609","type":"journal-article","article-title":"Knowledge-based planning for fully automated radiation therapy treatment planning of 10 different cancer sites","volume":"202","author":"Chung","year":"2025","journal-title":"Radiother. Oncol."},{"key":"bpexae7090bib11","doi-asserted-by":"publisher","DOI":"10.3791\/57411","type":"journal-article","article-title":"Radiation planning assistant\u2014a streamlined, fully automated radiotherapy treatment planning system","volume":"134","author":"Court","year":"2018","journal-title":"J. Vis. Exp."},{"key":"bpexae7090bib12","doi-asserted-by":"publisher","DOI":"10.3791\/65504","type":"journal-article","article-title":"Radiation planning assistant\u2014A web-based tool to support high-quality radiotherapy in clinics with limited resources","volume":"6","author":"Court","year":"2023b","journal-title":"J. Vis. Exp."},{"key":"bpexae7090bib13","doi-asserted-by":"publisher","DOI":"10.1200\/GO.23.00376","type":"journal-article","article-title":"Artificial intelligence-based radiotherapy contouring and planning to improve global access to cancer care","volume":"10","author":"Court","year":"2024","journal-title":"JCO Glob. Oncol."},{"key":"bpexae7090bib14","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/S1470-2045(24)00084-6","type":"journal-article","article-title":"The radiation planning assistant: addressing the global gap in radiotherapy services","volume":"25","author":"Court","year":"2024","journal-title":"Lancet Oncol."},{"key":"bpexae7090bib15","doi-asserted-by":"publisher","DOI":"10.1200\/GO.22.00431","type":"journal-article","article-title":"Addressing the global expertise gap in radiation oncology: the radiation planning assistant","volume":"9","author":"Court","year":"2023a","journal-title":"JCO Glob. Oncol."},{"key":"bpexae7090bib16","doi-asserted-by":"publisher","first-page":"e236-72","DOI":"10.1002\/mp.14030","type":"journal-article","article-title":"Strategies for effective physics plan and chart review in radiation therapy: report of AAPM task group 275","volume":"47","author":"Ford","year":"2020","journal-title":"Med. Phys."},{"key":"bpexae7090bib17","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1002\/mp.14827","type":"journal-article","article-title":"Technical note: dose prediction for head and neck radiotherapy using a three-dimensional dense dilated U-net architecture","volume":"97","author":"Gronberg","year":"2021","journal-title":"Med. Phys."},{"key":"bpexae7090bib18","doi-asserted-by":"publisher","first-page":"e282","DOI":"10.1016\/j.prro.2022.12.003","type":"journal-article","article-title":"Deep learning-based dose prediction for automated, individualized quality assurance of head and neck radiation therapy plans","volume":"13","author":"Gronberg","year":"2023a","journal-title":"Pract. Radiat. Oncol."},{"key":"bpexae7090bib19","doi-asserted-by":"publisher","first-page":"6639","DOI":"10.1002\/mp.16735","type":"journal-article","article-title":"Deep learning\u2013based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers","volume":"50","author":"Gronberg","year":"2023b","journal-title":"Med. Phys."},{"key":"bpexae7090bib20","doi-asserted-by":"publisher","first-page":"5088","DOI":"10.1002\/mp.16545","type":"journal-article","article-title":"Generating deliverable DICOM RT treatment plans for prostate VMAT by predicting MLC motion sequences with an encoder-decoder network","volume":"50","author":"Heilemann","year":"2023","journal-title":"Med. Phys."},{"key":"bpexae7090bib21","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.prro.2014.04.004","type":"journal-article","article-title":"Practice patterns for peer review in radiation oncology","volume":"5","author":"Hoopes","year":"2015","journal-title":"Pract. Radiat. Oncol."},{"key":"bpexae7090bib22","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","type":"journal-article","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"bpexae7090bib23","article-title":"Automated treatment planning in radiation therapy using generative adversarial networks","author":"Mahmood","year":"2018","type":"other"},{"key":"bpexae7090bib24","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.prro.2012.11.010","type":"journal-article","article-title":"Enhancing the role of case-oriented peer review to improve quality and safety in radiation oncology: executive summary","volume":"3","author":"Marks","year":"2013","journal-title":"Pract. Radiat. Oncol."},{"key":"bpexae7090bib25","doi-asserted-by":"publisher","first-page":"2025-10","DOI":"10.1101\/2025.10.01.25337092","type":"journal-article","article-title":"AI-powered radiotherapy for resource-limited settings: advancing cervical and prostate cancer treatment planning with the radiation planning assistant (RPA)","volume":"1","author":"Netherton","year":"2026","journal-title":"medRxiv"},{"key":"bpexae7090bib26","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1038\/s41598-018-37741-x","type":"journal-article","article-title":"A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning","volume":"9","author":"Nguyen","year":"2019","journal-title":"Sci. Rep."},{"key":"bpexae7090bib27","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":"bpexae7090bib28","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1093\/jnci\/djt001","type":"journal-article","article-title":"Radiotherapy protocol deviations and clinical outcomes: a meta-analysis of cooperative group clinical trials","volume":"105","author":"Ohri","year":"2013","journal-title":"J. Natl Cancer Inst."},{"key":"bpexae7090bib29","doi-asserted-by":"publisher","first-page":"2996","DOI":"10.1200\/JCO.2009.27.4498","type":"journal-article","article-title":"Critical impact of radiotherapy protocol compliance and quality in the treatment of advanced head and neck cancer: results from TROG 02.02","volume":"28","author":"Peters","year":"2010","journal-title":"J. Clin. Oncol."},{"key":"bpexae7090bib30","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13647","type":"journal-article","article-title":"Automatic contouring QA method using a deep learning-based autocontouring system","volume":"23","author":"Rhee","year":"2022a","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"bpexae7090bib31","doi-asserted-by":"publisher","first-page":"5742","DOI":"10.1002\/mp.15868","type":"journal-article","article-title":"Clinical acceptability of fully automated external beam radiotherapy for cervical cancer with three different beam delivery techniques","volume":"49","author":"Rhee","year":"2022b","journal-title":"Med. Phys."},{"key":"bpexae7090bib32","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.prro.2020.05.012","type":"journal-article","article-title":"A blinded, prospective study of error detection during physician chart rounds in radiation oncology","volume":"10","author":"Talcott","year":"2020","journal-title":"Pract. Radiat. Oncol."},{"key":"bpexae7090bib33","doi-asserted-by":"publisher","DOI":"10.7937\/QSTF-ST65","type":"other","article-title":"Stress-testing pelvic autosegmentation algorithms using anatomical edge cases (prostate anatomical edge cases) (version 1) [data set] the cancer imaging archive","author":"Thompson","year":"2023"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T06:31:38Z","timestamp":1780036298000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae7090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":33,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,5,29]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae7090","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"assertion":[{"value":"RADIANT: A fully configurable radiotherapy dose prediction framework","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2026-01-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-20","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}