{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T04:19:56Z","timestamp":1778905196417,"version":"3.51.4"},"reference-count":35,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":8,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12175312"],"award-info":[{"award-number":["12175312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12375320"],"award-info":[{"award-number":["12375320"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12275357"],"award-info":[{"award-number":["12275357"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12475359"],"award-info":[{"award-number":["12475359"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Monte Carlo (MC)\u2010based estimation of dose\u2010averaged linear energy transfer (LETd) in proton therapy is accurate but computationally intensive. Although deep learning (DL) models offer efficient alternatives, few have been optimized for multi\u2010source inputs or validated on anatomically complex tumors, such as nasopharyngeal carcinoma (NPC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study developed and evaluated a multi\u2010source DL framework for voxel\u2010level LETd prediction in proton therapy for NPC, aiming to identify optimal input configurations and assess both prediction accuracy and clinical reliability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This study analyzed 100 patients with NPC, yielding 500 proton therapy fields. Ground\u2010truth LETd maps were generated using GPU\u2010based Monte Carlo simulations. A deep learning model was trained with different combinations of four input features: dose distribution, CT image, beam mask, and radiological depth, resulting in eight configurations (M\n                      <jats:sub>dose<\/jats:sub>\n                      , M\n                      <jats:sub>dose+ct<\/jats:sub>\n                      , M\n                      <jats:sub>dose+beam<\/jats:sub>\n                      , M\n                      <jats:sub>dose+depth<\/jats:sub>\n                      , M\n                      <jats:sub>dose+beam+depth<\/jats:sub>\n                      , M\n                      <jats:sub>dose+ct+depth<\/jats:sub>\n                      , M\n                      <jats:sub>dose+ct+beam<\/jats:sub>\n                      , and M\n                      <jats:sub>dose+ct+beam+depth<\/jats:sub>\n                      ). The dataset was randomly divided into training (300 fields, 60 patients), validation (100 fields, 20 patients), and testing (100 fields, 20 patients) sets. Model performance was evaluated using mean absolute error (MAE), peak signal\u2010to\u2010noise ratio (PSNR), normalized cross\u2013correlation (NCC), structural similarity index measure (SSIM), and 3D Gamma analysis. A 3D U\u2010Net baseline was retrained under identical conditions for comparison. Model interpretability was examined with Gradient\u2010weighted Class Activation Mapping (Grad\u2010CAM), and prediction confidence was assessed using uncertainty maps.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The M\n                      <jats:sub>dose+ct<\/jats:sub>\n                      model achieved the best performance (MAE 0.21\u00a0\u00b1\u00a00.03\u00a0keV\/\u00b5m, PSNR 28.99\u00a0\u00b1\u00a01.33, NCC 0.98\u00a0\u00b1\u00a00.01, SSIM 0.971\u00a0\u00b1\u00a00.007, Gamma 3%\/3\u00a0mm: 94.69\u00a0\u00b1\u00a03.69%), outperforming the 3D U\u2010Net baseline (MAE 0.38\u00a0\u00b1\u00a00.52\u00a0keV\/\u00b5m). Grad\u2010CAM visualizations confirmed that the model focused on physically relevant regions, while uncertainty maps highlighted high\u2010variability zones at LETd transitions. The model generated voxel\u2010level LETd predictions in approximately 7 s per case, which was substantially faster than GPU\u2010based MC simulations (30 s per case).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed multi\u2010source deep learning framework enables rapid and accurate voxel\u2010level LETd prediction for NPC. Combining dose with CT yielded the most reliable input configuration, and incorporating interpretability and uncertainty analyses enhances confidence in its suitability for biologically guided proton therapy planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70068","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T02:50:16Z","timestamp":1760064616000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A multi\u2010source feature\u2010driven deep learning method to generate linear energy transfer distribution for proton therapy"],"prefix":"10.1002","volume":"52","author":[{"given":"Qian","family":"Liu","sequence":"first","affiliation":[{"name":"National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangyan","family":"Wei","sequence":"additional","affiliation":[{"name":"National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijuan","family":"Peng","sequence":"additional","affiliation":[{"name":"National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaonan","family":"Liu","sequence":"additional","affiliation":[{"name":"National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianrong","family":"Dai","sequence":"additional","affiliation":[{"name":"National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuo","family":"Men","sequence":"additional","affiliation":[{"name":"National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College  Beijing China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2019.4889"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/60\/8\/R155"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2016.11.001"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/59\/22\/R419"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2022.07.1848"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1667\/RR2737.1"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.05.041"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aad9db"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.08.038"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/aae8a5"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/56\/20\/011"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748\u2010717X\u20109\u20102"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apradiso.2008.06.013"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0360\u20103016(02)02754\u20102"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/57\/5\/1159"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/49\/13\/004"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.14338\/IJPT\u201020\u201000049.1"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.01.094"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/61\/2\/740"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4932217"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/61\/4\/1705"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/59\/12\/2863"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13934"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.580919"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16043"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ad154b"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ad4844"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ad64b7"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/279232.279236"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4943377"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/55\/11\/006"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16758"},{"key":"e_1_2_8_34_1","unstructured":"GuA DaoT.Mamba: linear\u2010time sequence modeling with selective state spaces[A]. arXiv.2024."},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.02.024"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3485765"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70068","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70068","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:47:24Z","timestamp":1772992044000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":35,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1002\/mp.70068"],"URL":"https:\/\/doi.org\/10.1002\/mp.70068","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]},"assertion":[{"value":"2025-06-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70068"}}