{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T05:38:26Z","timestamp":1792993106472,"version":"4.5.0"},"reference-count":50,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":14,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA255432"],"award-info":[{"award-number":["R01CA255432"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R44CA183390"],"award-info":[{"award-number":["R44CA183390"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA259008"],"award-info":[{"award-number":["R01CA259008"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop and benchmark 3D dose prediction algorithms for volumetric modulated arc therapy for head\u2010and\u2010neck (HN) and pancreatic cancer treatments, and to demonstrate the clinical feasibility of converting the predicted doses into deliverable plans.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and materials<\/jats:title>\n                    <jats:p>Three deep learning models were pretrained on 3232 public plans and fine\u2010tuned on institutional cohorts (256 HN and 72 pancreas patients). The accuracy of the fine\u2010tuning strategy was compared with the baseline trained from scratch using only institutional data. In a prospective setting, the predicted dose was used as the planning goal for fully automated plan generation. Automated plans were benchmarked against clinical plans using Plan Quality Metrics. The deliverability of the fully automated plans was verified by Mobius ion\u2010chamber patient\u2010specific quality assurance (PSQA).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Relative to training from scratch, transfer learning significantly accelerated convergence and minimized prediction error in scenarios with limited site\u2010specific data. For HN cases, fine\u2010tuning yielded a prediction error of 1.76\u00a0Gy. Notably, models fine\u2010tuned on just 5% (\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a012) of the dataset achieved accuracy comparable to models trained from scratch using 50% (\n                      <jats:italic>n<\/jats:italic>\n                      \u00a0=\u00a0116) of the training data. In the pancreas cohort, fine\u2010tuning resulted in a mean absolute error of 1.35\u00a0Gy, representing a 14.6% reduction compared to the baseline trained solely on institutional data. When used for automated planning, these predicted 3D doses improved planning target volume homogeneity and organs at risk sparing (esophagus and trachea) in HN plans, while pancreas plans aimed to meet clinical goals with reduced dose to the spinal cord and right kidney. All automated plans were confirmed as clinically deliverable via PSQA.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Compared with models trained from scratch on institutional data, transfer learning significantly reduced prediction error and improved robustness. The feasibility of converting predicted doses into clinical plans while maintaining plan quality through a fully automated process was demonstrated.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70704","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T10:00:52Z","timestamp":1792058452000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End\u2010to\u2010end automated radiotherapy planning using transfer learning to overcome data scarcity"],"prefix":"10.1002","volume":"53","author":[{"given":"Lu","family":"Jiang","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Hirata","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evan","family":"Porter","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wensha","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihui","family":"Lyu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsong","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Sheng","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology UCSF  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/ijc.29210"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.21324"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/0360\u20103016(92)90768\u2010D"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2018.10.026"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2009.27.4498"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.05.026"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2014.11.014"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13526"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010021\u201001820\u20107"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.06.028"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/aaef74"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15034"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab039b"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14827"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108324"},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","unstructured":"GaoR LouB XuZ ComaniciuD KamenA Flexible\u2010Cm GAN: Towards Precise 3D Dose Prediction in Radiotherapy. In.2023. p.715\u2010725.","DOI":"10.1109\/CVPR52729.2023.00076"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3383423"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13942"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13955"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103045"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110662"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.70346"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.70012"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.10.027"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109606"},{"key":"e_1_2_11_28_1","unstructured":"GaoR DialloM LiuH et\u00a0al.Automating RT Planning at Scale: High Quality Data For AI Training[Internet]. arXiv; 2025 [cited 2025 Oct 30]. Available from: doi:10.48550\/arXiv.2501.11803"},{"key":"e_1_2_11_29_1","doi-asserted-by":"crossref","unstructured":"OarA LeeM LeH et\u00a0al.Australasian Gastrointestinal Trials Group (AGITG) and Trans\u2010Tasman Radiation Oncology Group (TROG) Guidelines for Pancreatic Stereotactic Body Radiation Therapy (SBRT). Practical Radiation Oncology.2020;10(3):e136\u2010e146. doi:10.1016\/j.prro.2019.07.018","DOI":"10.1016\/j.prro.2019.07.018"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43901-8_39"},{"key":"e_1_2_11_31_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA NathV TangY YangD RothH XuD Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images[Internet]. arXiv; 2022 [cited 2026 Feb 23]. Available from: doi:10.48550\/arXiv.2201.01266","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"e_1_2_11_32_1","unstructured":"LukasB Experiment Tracking with Weights and Biases [Internet].2020. Available from:https:\/\/www.wandb.com\/"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2023.102588"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00066\u2010021\u201001771\u20108"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2017.09.007"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14845"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/adcfeb"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14015"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.00068"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ac0856"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.70384"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.11.030"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4761864"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12625"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.07.107"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14544"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16408"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2024.100641"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2023.102586"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20220707"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2024.101649"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70704","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70704","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T05:26:00Z","timestamp":1792992360000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70704"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/mp.70704"],"URL":"https:\/\/doi.org\/10.1002\/mp.70704","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"2026-03-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70704"}}