{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T22:04:20Z","timestamp":1791583460688,"version":"4.3.4"},"reference-count":36,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T00:00:00Z","timestamp":1743206400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Conventional proton dose calculation methods are either time\u2010 and resource\u2010intensive, like Monte Carlo (MC) simulations, or they sacrifice accuracy, as seen with analytical methods. This trade\u2010off between computational efficiency and accuracy highlights the need for improved dose calculation approaches in clinical settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>\n                      This study aims to develop a deep\u2010learning\u2010based model that calculates dose\u2010to\u2010water (\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>W<\/jats:sub>\n                      ) and dose\u2010to\u2010medium (\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>M<\/jats:sub>\n                      ) using patient anatomy and proton spot map (PSM), achieving approaching MC\u2010level accuracy with significantly reduced computation time. Additionally, the study seeks to generalize the model to different treatment sites using transfer learning.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A SwinUNetr model was developed using 259 four\u2010field prostate proton stereotactic body radiation therapy (SBRT) plans to calculate patient\u2010specific\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>W<\/jats:sub>\n                      and\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>M<\/jats:sub>\n                      distributions from CT and projected PSM (PPSM). The PPSM was created by projecting PSM into the CT scans using spot coordinates, stopping power ratio, beam divergence, and water\u2010equivalent thickness. Fine\u2010tuning was then performed for the central nervous system (CNS) site using 84 CNS plans. The model's accuracy was evaluated against MC simulation benchmarks using mean absolute error (MAE), gamma analysis (2% local dose difference, 2\u2010mm distance\u2010to\u2010agreement, 10% low dose threshold), and relevant clinical indices on the test dataset.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The trained model achieved a single\u2010field dose calculation time of 0.07\u00a0s on a Nvidia\u2010A100 GPU, over 100 times faster than MC simulators. For the prostate site, the best\u2010performing model showed an average MAE of 0.26\u00a0\u00b1\u00a00.17\u00a0Gy and a gamma index of 92.2%\u00a0\u00b1\u00a03.1% in dose regions above 10% of the maximum dose for\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>W<\/jats:sub>\n                      calculations, and an MAE of 0.30\u00a0\u00b1\u00a00.19\u00a0Gy with a gamma index of 89.7%\u00a0\u00b1\u00a03.9% for\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>M<\/jats:sub>\n                      calculations. After transfer learning for CNS plans, the model achieved an MAE of 0.49\u00a0\u00b1\u00a00.24\u00a0Gy and a gamma index of 90.1%\u00a0\u00b1\u00a02.7% for\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>W<\/jats:sub>\n                      computations, and an MAE of 0.47\u00a0\u00b1\u00a00.25\u00a0Gy with a gamma index of 85.4%\u00a0\u00b1\u00a07.1% for\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>M<\/jats:sub>\n                      computations.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      The SwinUNetr model provides an efficient and accurate method for computing dose distributions in proton therapy. It also opens the possibility of reverse\u2010engineering PSM from\n                      <jats:italic>D<\/jats:italic>\n                      <jats:sub>W<\/jats:sub>\n                      , potentially speeding up treatment planning while maintaining accuracy.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17794","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T04:13:24Z","timestamp":1743394404000},"page":"4941-4952","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Proton dose calculation with transformer: Transforming spot map to dose"],"prefix":"10.1002","volume":"52","author":[{"given":"Xueyan","family":"Tang","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hok Wan Chan","family":"Tseung","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark D.","family":"Pepin","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jed E.","family":"Johnson","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doug J.","family":"Moseley","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David M.","family":"Routman","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Rochester Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-29999-8_27"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addr.2016.11.006"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2006.10.0131"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/59\/15\/4427"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20120288"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac344f"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190594"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20150195"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/56\/5\/006"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.12497"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/57\/23\/7783"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4921046"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13182"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/60\/12\/4777"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.06.003"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/56\/10\/012"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/60\/21\/8601"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab7630"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14658"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aba164"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.07.022"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abb6d5"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac692e"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"CaoH WangY ChenJ et\u00a0al.Swin\u2010Unet: Unet\u2010Like Pure Transformer for Medical Image Segmentation.Springer;2022:205\u2010218.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2016.03.001"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13496"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpt.2024.03.001"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"LiuZ LinY CaoY et\u00a0al.Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows;2021:10012\u201010022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: Convolutional Networks for Biomedical Image Segmentation.Springer;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep Residual Learning for Image Recognition.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703"},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"ZhaiJ ZhangS ChenJ HeQ.Autoencoder and Its Various Variants.IEEE;2018:415\u2010419.","DOI":"10.1109\/SMC.2018.00080"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12810"},{"key":"e_1_2_8_35_1","volume-title":"Applied Statistics and Probability for Engineers","author":"Montgomery DC","year":"2010"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/53\/17\/023"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad4844"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T08:08:34Z","timestamp":1762934914000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,29]]},"references-count":36,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1002\/mp.17794"],"URL":"https:\/\/doi.org\/10.1002\/mp.17794","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,29]]},"assertion":[{"value":"2024-08-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}