{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T11:33:29Z","timestamp":1791804809738,"version":"4.3.4"},"reference-count":37,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Formulating a clinically acceptable plan within the time\u2010constrained clinical setting of brachytherapy poses challenges to clinicians. Deep learning based dose prediction methods have shown favorable solutions for enhancing efficiency, but development has primarily been on external beam radiation therapy. Thus, there is a need for translation to brachytherapy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>This study proposes a dose prediction model utilizing an attention\u2010gating mechanism and a 3D UNET for cervical cancer high\u2010dose\u2010rate intracavitary brachytherapy treatment planning with tandem\u2010and\u2010ovoid\/ring applicators.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A multi\u2010institutional data set consisting of 77 retrospective clinical brachytherapy plans was utilized in this study. The data were preprocessed and augmented to increase the number of plans to 252. A 3D UNET architecture with attention gates was constructed and trained for mapping the contour information to dose distribution. The trained model was evaluated on a testing data set using various metrics, including dose statistics and dose\u2010volume indices. We also trained a baseline UNET model for a fair comparison.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The attention\u2010gated 3D UNET model exhibited competitive accuracy in predicting dose distributions similar to the ground truth. The average values of the mean absolute errors were 0.46\u00a0\u00b1\u00a011.71\u00a0Gy (vs. 0.47\u00a0\u00b1\u00a09.16\u00a0Gy for a baseline UNET) in CTV<jats:sub>HR<\/jats:sub>, 0.55\u00a0\u00b1\u00a00.67\u00a0Gy (vs. 0.70\u00a0\u00b1\u00a01.54\u00a0Gy for a baseline UNET) in bladder, 0.42\u00a0\u00b1\u00a00.46\u00a0Gy (vs. 0.49\u00a0\u00b1\u00a01.34\u00a0Gy for a baseline UNET) in rectum, and 0.31\u00a0\u00b1\u00a00.65\u00a0Gy (vs. 0.20\u00a0\u00b1\u00a03.76\u00a0Gy for a baseline UNET) in sigmoid. Our results showed that the mean individual differences in \u0394D<jats:sub>2cc<\/jats:sub> for bladder, rectum, and sigmoid were 0.38\u00a0\u00b1\u00a01.19 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.50), 0.43\u00a0\u00b1\u00a00.71 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.41), and \u22120.47\u00a0\u00b1\u00a00.79 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.30) Gy, respectively. Similarly, the mean individual differences in \u0394D<jats:sub>1cc<\/jats:sub> for bladder, rectum, and sigmoid were 0.09\u00a0\u00b1\u00a01.21 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.36), 0.20\u00a0\u00b1\u00a00.95 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.24), and \u22120.21\u00a0\u00b1\u00a00.59 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.30) Gy. The mean individual differences for \u0394D<jats:sub>90<\/jats:sub>, \u0394V<jats:sub>100%<\/jats:sub>, \u0394V<jats:sub>150%<\/jats:sub>, and \u0394V<jats:sub>200%<\/jats:sub> of the CTV<jats:sub>HR<\/jats:sub> were \u22120.45\u00a0\u00b1\u00a02.42 (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.26) Gy, 0.55\u00a0\u00b1\u00a09.42% (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.78), 0.82\u00a0\u00b1\u00a04.21% (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.81), and \u22120.80\u00a0\u00b1\u00a010.48% (<jats:italic>p<\/jats:italic>\u00a0=\u00a00.36), respectively. The model requires less than 5 s to predict a full 3D dose distribution for a new patient plan.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Attention\u2010gated 3D UNET revealed a promising capability in predicting voxel\u2010wise dose distributions compared to 3D UNET. This model could be deployed for clinical use to predict 3D dose distributions for near real\u2010time decision\u2010making before planning, quality assurance, and guiding future automated planning, making the current workflow more efficient.<\/jats:p><\/jats:sec>","DOI":"10.1002\/acm2.14568","type":"journal-article","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T14:39:36Z","timestamp":1731681576000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Attention 3D UNET for dose distribution prediction of high\u2010dose\u2010rate brachytherapy of cervical cancer: Intracavitary applicators"],"prefix":"10.1002","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7160-7107","authenticated-orcid":false,"given":"Suman","family":"Gautam","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1286-475X","authenticated-orcid":false,"given":"Alexander F. I.","family":"Osman","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan","family":"Richeson","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Inova Schar Cancer Institute  Fairfax Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Somayeh","family":"Gholami","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Utah  Salt Lake City Utah USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binod","family":"Manandhar","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sharmin","family":"Alam","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Baylor Scott and White Health  Temple Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3196-2368","authenticated-orcid":false,"given":"William Y.","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,11,15]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21708"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.14316\/pmp.2021.32.2.25"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2016.03.020"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20220500"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.09.041"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8140(88)90167-3"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.2818738"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.03.013"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4906183"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4938583"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010018\u201037741\u2010x"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2023.06.120"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2017.04.011"},{"key":"e_1_2_9_15_1","unstructured":"RonnebergerO FischerP BroxT.U\u2010Net: Convolutional Networks for Biomedical Image Segmentation.2015.http:\/\/arxiv.org\/abs\/1505.04597"},{"key":"e_1_2_9_16_1","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek\u00d6 AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010Net: learning dense volumetric segmentation from sparse annotation.In: Medical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2016: 19th International Conference Athens Greece October 17\u201321 2016 Proceedings Part II 19.Springer;2016. pp.424\u2010432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3086020"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-021-01864-9"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17238"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14015"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2023.06.136"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2021.3098507"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.580919"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2023.06.1810"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2023.06.096"},{"key":"e_1_2_9_27_1","unstructured":"YangS XiaoW ZhangM GuoS ZhaoJ ShenF.Image data augmentation for deep learning: a survey.2023.https:\/\/arxiv.org\/abs\/2204.08610"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2021.765525"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.brachy.2021.10.003"},{"key":"e_1_2_9_30_1","volume-title":"Deep Learning with Python: Develop Deep Learning Models on Theano and TensorFlow Using Keras","author":"Brownlee J","year":"2016"},{"key":"e_1_2_9_31_1","unstructured":"NairV HintonGE.Rectified Linear Units Improve Restricted Boltzmann Machines.Proceedings of the 27th International Conference on International Conference on Machine Learning.Madison WI USA:Omnipress;2010. pp.807\u2010814."},{"key":"e_1_2_9_32_1","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","journal-title":"J Mach Learn Res"},{"key":"e_1_2_9_33_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Delving Deep into Rectifiers: Surpassing Human\u2010Level Performance on ImageNet Classification.2015 IEEE International Conference on Computer Vision (ICCV).2015:1026\u20101034. doi:10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_9_34_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization.2014.https:\/\/api.semanticscholar.org\/CorpusID:6628106"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104755"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13630"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acecd2"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ac344d"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.14568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T04:50:15Z","timestamp":1744433415000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.14568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,15]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10.1002\/acm2.14568"],"URL":"https:\/\/doi.org\/10.1002\/acm2.14568","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,15]]},"assertion":[{"value":"2024-04-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e14568"}}