{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T20:17:31Z","timestamp":1790626651921,"version":"4.1.0"},"reference-count":39,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"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>\n                      Personalized pretreatment dosimetry planning is crucial for optimizing [\n                      <jats:sup>177<\/jats:sup>\n                      Lu]Lu\u2013prostate\u2010specific membrane antigen\u2010617 (Lu\u2010PSMA) radioligand therapy (RLT) in patients with metastatic castration\u2010resistant prostate cancer (mCRPC).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study addresses two goals. First, we develop a machine learning (ML)\u2010based pretreatment planning model to predict post\u2010therapy absorbed doses (ADs) in metastatic lesions by integrating clinical biomarkers (CBs) with radiomic features (RFs) and dosiomic features (DFs) extracted from [\u2076\u2078Ga]Ga\u2010PSMA\u201011 (Ga\u2010PSMA) positron emission tomography\/computed tomography (PET\/CT), thereby improving predictive accuracy. Second, we develop a transformer\u2010based deep learning (DL) architecture to predict Monte Carlo (MC)\u2010derived dose rate maps (DRMs), minimizing reliance on computationally intensive MC simulations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      For the ML objective, retrospective posttreatment dosimetry data from 20 patients with mCRPC treated with Lu\u2010PSMA RLT were used as ground truth labels. Patient\u2010specific MC dosimetry was employed on Ga\u2010PSMA PET\/CT images using the GATE v9.1 toolkit to generate DRMs. After image preprocessing, RFs and DFs were extracted from Ga\u2010PSMA CT images and DRMs using LIFEx v7.4.0. Multiple feature selection techniques, including recursive feature elimination (RFE), mutual information, Boruta, LASSO, and Elastic Net, were applied and evaluated. The Benjamini\u2010Hochberg correction (\n                      <jats:italic>q<\/jats:italic>\n                      \u00a0&lt;\u00a00.05) was used to control for false discovery rate following each method. Multiple nonlinear regression models were trained using leave\u2010one\u2010out cross\u2010validation (LOOCV), and model interpretability was assessed using SHAP and LIME radar plots. A shifted windows UNET Transformers (Swin UNETR) architecture with self\u2010supervised learning (SSL) pretraining was employed to predict voxel\u2010wise PET\u2010based DRMs for the DL objective. The model was fine\u2010tuned on MC\u2010labelled DRM data from 30 patients (including 10 additional cases) using 5\u2010fold cross\u2010validation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Among multiple feature selection strategies, RFE was ultimately selected for final modelling based on its superior predictive performance. The ensemble tree regressor (ETR) using selected CT RFs, PET DFs, and significant CBs achieved an R\n                      <jats:sup>2<\/jats:sup>\n                      \u00a0=\u00a00.82 and RMSE\u00a0=\u00a00.67\u00a0Gy\/GBq. For DRM prediction, the SSL\u2010pretrained Swin UNETR achieved an R\n                      <jats:sup>2<\/jats:sup>\n                      of 0.97, NRMSE of 0.003\u00a0Gy\/GBq, and a Gamma pass rate of 99.08%, closely matching MC\u2010derived DRMs.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Integrating ML\u2010based radiodosiomics and transformer\u2010based DL enables accurate, efficient lesion AD and DRM prediction from pretherapy PET\/CT, supporting personalized Lu\u2010PSMA RLT planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70030","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T12:55:08Z","timestamp":1758632108000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Transforming [\n                    <sup>177<\/sup>\n                    Lu]Lu\u2010PSMA\u2010617 treatment planning: Machine learning\u2010based radiodosiomics and swin UNETR using pretherapy PSMA positron emission tomography\/computed tomography (PET\/CT)"],"prefix":"10.1002","volume":"52","author":[{"given":"Elmira","family":"Yazdani","sequence":"first","affiliation":[{"name":"Department of Medical Physics School of Medicine Iran University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aryan","family":"Neizehbaz","sequence":"additional","affiliation":[{"name":"Department of Computer and Data Sciences Faculty of Mathematical Sciences Shahid Beheshti University  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Najme","family":"Karamzade\u2010Ziarati","sequence":"additional","affiliation":[{"name":"Research Center for Nuclear Medicine Tehran University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farshad","family":"Emami","sequence":"additional","affiliation":[{"name":"Nuclear Medicine and Molecular Imaging Department Imam Reza International University Razavi Hospital  Mashhad Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Habibeh","family":"Vosoughi","sequence":"additional","affiliation":[{"name":"Research Center for Nuclear Medicine Tehran University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahboobeh","family":"Asadi","sequence":"additional","affiliation":[{"name":"Research Center for Nuclear Medicine Tehran University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atefeh","family":"Mahmoudi","sequence":"additional","affiliation":[{"name":"Department of Medical Physics School of Medicine Iran University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahdi","family":"Sadeghi","sequence":"additional","affiliation":[{"name":"Department of Medical Physics School of Medicine Iran University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saeed Reza","family":"Kheradpisheh","sequence":"additional","affiliation":[{"name":"Department of Computer and Data Sciences Faculty of Mathematical Sciences Shahid Beheshti University  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parham","family":"Geramifar","sequence":"additional","affiliation":[{"name":"Research Center for Nuclear Medicine Tehran University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2107322"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-022-05727-7"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/14736691211060117"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12020205"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1080\/09553002.2024.2404448"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14020181"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-024-06737-3"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-022-05883-w"},{"key":"e_1_2_11_10_1","doi-asserted-by":"crossref","unstructured":"ZhangJ BousseA LiY et\u00a0al.Pre\u2010therapy dose prediction in targeted radionuclide therapy using semi\u2010supervised learning: an in\u2010silico preliminary study.IEEE.2024:1\u20131.","DOI":"10.1109\/NSS\/MIC\/RTSD57108.2024.10655434"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-020-00887-2"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.05.022"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2022.11.036"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-024-01463-4"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.913683"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16746"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.124.268186"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-024-00675-x"},{"issue":"0325","key":"e_1_2_11_19_1","first-page":"00480","article-title":"Machine learning\u2010based dose prediction in [177Lu] Lu\u2010PSMA\u2010617 therapy by integrating biomarkers and radiomic features from [68Ga] Ga\u2010PSMA\u201011 positron emission tomography\/computed tomography","volume":"0360","author":"Yazdani E","year":"2025","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.115.159012"},{"key":"e_1_2_11_21_1","first-page":"1","article-title":"IBSI: an international community radiomics standardization initiative","volume":"59","author":"Hatt M","year":"2018","journal-title":"Soc Nucl Med"},{"key":"e_1_2_11_22_1","unstructured":"ZwanenburgA LegerS Valli\u00e8resM L\u00f6ckS.Image biomarker standardisation initiative. Available online:https:\/\/arxiv.org\/abs\/1612.07003"},{"key":"e_1_2_11_23_1","doi-asserted-by":"crossref","unstructured":"LiuZ LinY CaoY et\u00a0al.Swin transformer: Hierarchical vision transformer using shifted windows. InProceedings of the IEEE\/CVF international conference on computer vision.2021:10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202400304"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1180773"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmir.2025.102023"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1177\/1536012118776068"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05494-5_6"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.118.219352"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLU.0b013e31823926e5"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-012-2124-x"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-023-06252-x"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pdpdt.2025.104528"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab65dc"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3639998"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-022-05891-w"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.121.262748"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apradiso.2024.111378"},{"key":"e_1_2_11_39_1","unstructured":"ZhangJ BousseA ImbertL XueS ShiK BertJ.Semi\u2010Supervised learning for dose prediction in targeted radionuclide: a synthetic data study. arXiv preprint\u00a0arXiv:2503.05367.2025 Mar 7."},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-024-06618-9"}],"updated-by":[{"DOI":"10.1002\/mp.70159","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000}}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70030","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70030","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:48:41Z","timestamp":1772992121000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":39,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1002\/mp.70030"],"URL":"https:\/\/doi.org\/10.1002\/mp.70030","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,23]]},"assertion":[{"value":"2025-05-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70030"}}