{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T20:34:07Z","timestamp":1792010047378,"version":"4.4.0"},"reference-count":32,"publisher":"IOP Publishing","issue":"11","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"crossref","award":["202207720085"],"award-info":[{"award-number":["202207720085"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2025,6,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    This study investigates key factors influencing deep learning-based dose prediction models for head and neck cancer radiation therapy. The goal is to evaluate model accuracy, robustness, and computational efficiency, and to identify key components necessary for optimal performance.\n                    <jats:italic>Approach.<\/jats:italic>\n                    We systematically analyze the impact of input and dose grid resolution, input type, loss function, model architecture, and noise on model performance. Two datasets are used: a public dataset (OpenKBP) and an in-house clinical dataset. Model performance is primarily evaluated using two metrics: dose score and dose\u2013volume histogram (DVH) score.\n                    <jats:italic>Main results.<\/jats:italic>\n                    High-resolution inputs improve prediction accuracy (dose score and DVH score) by 8.6%\u201313.5% compared to low resolution. Using a combination of CT, planning target volumes, and organs-at-risk as input significantly enhances accuracy, with improvements of 57.4%\u201386.8% over using CT alone. Integrating mean absolute error (MAE) loss with value-based and criteria-based DVH loss functions further boosts DVH score by 7.2%\u20137.5% compared to MAE loss alone. In the robustness analysis, most models show minimal degradation under Poisson noise (0\u20130.3 Gy) but are more susceptible to adversarial noise (0.2\u20137.8 Gy). Notably, certain models, such as SwinUNETR, demonstrate superior robustness against adversarial perturbations.\n                    <jats:italic>Significance.<\/jats:italic>\n                    These findings highlight the importance of optimizing deep learning models and provide valuable guidance for achieving more accurate and reliable radiotherapy dose prediction.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/adcfeb","type":"journal-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T18:53:51Z","timestamp":1745434431000},"page":"115006","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["On factors that influence deep learning-based dose prediction of head and neck tumors"],"prefix":"10.1088","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9411-3369","authenticated-orcid":true,"given":"Ruochen","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9697-2258","authenticated-orcid":false,"given":"Prerak","family":"Mody","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2472-2409","authenticated-orcid":false,"given":"Chinmay","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1354-3723","authenticated-orcid":true,"given":"Frank","family":"Dankers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2885-5812","authenticated-orcid":false,"given":"Marius","family":"Staring","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"key":"pmbadcfebbib1","doi-asserted-by":"publisher","first-page":"2875","DOI":"10.1002\/mp.12930","article-title":"Knowledge-based automated planning for oropharyngeal cancer","volume":"45","author":"Babier","year":"2018","journal-title":"Med. Phys."},{"key":"pmbadcfebbib2","doi-asserted-by":"publisher","first-page":"5549","DOI":"10.1002\/mp.14845","article-title":"Openkbp: the open-access knowledge-based planning grand challenge and dataset","volume":"48","author":"Babier","year":"2021","journal-title":"Med. Phys."},{"key":"pmbadcfebbib3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13014-020-01626-z","article-title":"A knowledge-based intensity-modulated radiation therapy treatment planning technique for locally advanced nasopharyngeal carcinoma radiotherapy","volume":"15","author":"Bai","year":"2020","journal-title":"Radiat. Oncol."},{"key":"pmbadcfebbib4","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.phro.2021.01.006","article-title":"Development and evaluation of radiotherapy deep learning dose prediction models for breast cancer","volume":"17","author":"Bakx","year":"2021","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"pmbadcfebbib5","first-page":"pp 205","article-title":"Swin-UNet: UNet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"pmbadcfebbib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104940","article-title":"MemU-Net: a new volumetric dose prediction model using deep learning techniques in radiation treatment planning","volume":"85","author":"Chandran","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbadcfebbib7","first-page":"pp 9185","article-title":"Boosting adversarial attacks with momentum","author":"Dong","year":"2018"},{"key":"pmbadcfebbib8","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1126\/science.aaw4399","article-title":"Adversarial attacks on medical machine learning","volume":"363","author":"Finlayson","year":"2019","journal-title":"Science"},{"key":"pmbadcfebbib9","first-page":"pp 715","article-title":"Flexible-CM gan: towards precise 3D dose prediction in radiotherapy","author":"Gao","year":"2023"},{"key":"pmbadcfebbib10","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad209a","article-title":"A cascade transformer-based model for 3D dose distribution prediction in head and neck cancer radiotherapy","volume":"69","author":"Gheshlaghi","year":"2024","journal-title":"Phys. Med. Biol."},{"key":"pmbadcfebbib11","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015"},{"key":"pmbadcfebbib12","doi-asserted-by":"publisher","first-page":"5567","DOI":"10.1002\/mp.14827","article-title":"Dose prediction for head and neck radiotherapy using a three-dimensional dense dilated U-Net architecture","volume":"48","author":"Gronberg","year":"2021","journal-title":"Med. Phys."},{"key":"pmbadcfebbib13","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1251132","article-title":"Dose distribution prediction for head-and-neck cancer radiotherapy using a generative adversarial network: influence of input data","volume":"13","author":"Gu","year":"2023","journal-title":"Front. Oncol."},{"key":"pmbadcfebbib14","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1016\/j.ijrobp.2022.11.021","article-title":"Assessing interobserver variability in the delineation of structures in radiation oncology: a systematic review","volume":"115","author":"Guzene","year":"2023","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"pmbadcfebbib15","first-page":"pp 272","author":"Hatamizadeh","year":"2021"},{"key":"pmbadcfebbib16","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13942","article-title":"TrDosePred: A deep learning dose prediction algorithm based on transformers for head and neck cancer radiotherapy","volume":"24","author":"Hu","year":"2023","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbadcfebbib17","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnUNet: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"pmbadcfebbib18","doi-asserted-by":"publisher","first-page":"23NT04","DOI":"10.1088\/1361-6560\/ab50eb","article-title":"Prediction of dose-volume histograms in nasopharyngeal cancer IMRT using geometric and dosimetric information","volume":"64","author":"Jiao","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"pmbadcfebbib19","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaef74","article-title":"DoseNet: a volumetric dose prediction algorithm using 3D fully-convolutional neural networks","volume":"63","author":"Kearney","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"pmbadcfebbib20","first-page":"pp 195","author":"Kurakin","year":"2018"},{"key":"pmbadcfebbib21","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","article-title":"H-DenseUNet: hybrid densely connected unet for liver and tumor segmentation from CT volumes","volume":"37","author":"Li","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbadcfebbib22","doi-asserted-by":"publisher","first-page":"5795","DOI":"10.1109\/TCYB.2024.3390769","article-title":"LENAS: learning-based neural architecture search and ensemble for 3-D radiotherapy dose prediction","volume":"54","author":"Lin","year":"2024"},{"key":"pmbadcfebbib23","doi-asserted-by":"publisher","first-page":"5574","DOI":"10.1002\/mp.15034","article-title":"A cascade 3D U-Net for dose prediction in radiotherapy","volume":"48","author":"Liu","year":"2021","journal-title":"Med. Phys."},{"key":"pmbadcfebbib24","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2018"},{"key":"pmbadcfebbib25","first-page":"pp 565","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"pmbadcfebbib26","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1002\/acm2.13337","article-title":"Knowledge-based radiation treatment planning: a data-driven method survey","volume":"22","author":"Momin","year":"2021","journal-title":"J. Appl. Clin. Med. phys."},{"key":"pmbadcfebbib27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41199-019-0046-z","article-title":"Adaptive radiotherapy for head and neck cancer","volume":"5","author":"Morgan","year":"2020","journal-title":"Cancers Head Neck"},{"key":"pmbadcfebbib28","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.prro.2011.11.012","article-title":"Variation in external beam treatment plan quality: an inter-institutional study of planners and planning systems","volume":"2","author":"Nelms","year":"2012","journal-title":"Pract. Radiat. Oncol."},{"key":"pmbadcfebbib29","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab039b","article-title":"3D radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected U-Net deep learning architecture","volume":"64","author":"Nguyen","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"pmbadcfebbib30","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1002\/mp.13955","article-title":"Incorporating human and learned domain knowledge into training deep neural networks: a differentiable dose-volume histogram and adversarial inspired framework for generating Pareto optimal dose distributions in radiation therapy","volume":"47","author":"Nguyen","year":"2020","journal-title":"Med. Phys."},{"key":"pmbadcfebbib31","doi-asserted-by":"publisher","first-page":"2","DOI":"10.31449\/inf.v43i2.2179","article-title":"A review on CT and x-ray images denoising methods","volume":"43","author":"Thanh","year":"2019","journal-title":"Informatica"},{"key":"pmbadcfebbib32","first-page":"pp 575","article-title":"Deep learning-based head and neck radiotherapy planning dose prediction via beam-wise dose decomposition","author":"Wang","year":"2022"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T08:24:38Z","timestamp":1747902278000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/adcfeb"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":32,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,5,22]]},"published-print":{"date-parts":[[2025,6,8]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/adcfeb","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,22]]},"assertion":[{"value":"On factors that influence deep learning-based dose prediction of head and neck tumors","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-01-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-04-23","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-05-22","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}