{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:11:59Z","timestamp":1753891919182,"version":"3.41.2"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T00:00:00Z","timestamp":1735862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Objectives<\/jats:title><jats:p>Implementing pre-treatment patient-specific quality assurance (prePSQA) for cancer patients is a necessary but time-consuming task, imposing a significant workload on medical physicists. Currently, the prediction methods used for prePSQA fall under the category of supervised learning, limiting their generalization ability and resulting in poor performance on new data. In the context of this work, the limitation of traditional supervised models was broken by proposing a conditional generation method utilizing unsupervised diffusion model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A conditional generation method base on the score-based diffusion model was proposed, which employed diffusion model for the first time to predict the predict patients\u2019 therapeutic doses (TherapDose). The proposed diffusion model TherapDose prediction method (DMTP) learns the data distribution of dose images. The data distribution contains the quantitative relationship between the radiotherapy dose (RTDose) derived from the VMAT plan files of the Treatment Planning System (TPS) and the measured Dose (MDose, i.e., TherapDose) obtained from the Dolphin Compass physical system. By sampling from the learnt distribution, efficient prediction of TherapDose was achieved. The training dataset comprises RTDose, and the MDose. The three-dimensional information of dose slice was utilized to predict TherapDose, aiming to enhance the accuracy and efficiency of TherapDose prediction. Root mean square error (RMSE), mean absolute error (MAE), and structural similarity (SSIM) metrics were leveraged to validate the effectiveness of the proposed method. Meanwhile, CT images were further added to test the impacts of CT images on the prediction effect of MDose.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The DMTP method has demonstrated superior performance in predicting TherapDose within key anatomical regions including the head and neck, chest, and abdomen, outperforming existing state-of-the-art methods by achieving high-quality predictions as measured across different evaluation metrics. It indicates that the proposed method is highly effective and accurate in its dose prediction capabilities.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The proposed method has proven to be highly effective, consistently outperforming state-of-the-art techniques in MDose prediction across multiple anatomical regions and evaluation metrics. This method can serve as a clinical aid to assist medical physicists in diminishing the measurement workload associated with prePSQA.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2024.1473050","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T06:49:20Z","timestamp":1735886960000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Therapeutic dose prediction using score-based diffusion model for pretreatment patient-specific quality assurance"],"prefix":"10.3389","volume":"14","author":[{"given":"Xiuwen","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiabin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changfei","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minhui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianyu","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiegen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.2018.45.issue-9","article-title":"A deep learning\u2013based prediction model for gamma evaluation in patient\u2013specific quality assurance","volume":"45","author":"Tomori","year":"2018","journal-title":"Med Phys"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.v104:6","article-title":"The role of radiotherapy in cancer treatment: estimating optimal utilization from a review of evidence\u2013based clinical guidelines","volume":"104","author":"Delaney","year":"2005","journal-title":"Cancer: Interdiscip Int J Am Cancer Soc"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.700343","article-title":"Virtual patient\u2013specific quality assurance of IMRT using UNet++: classification, gamma passing rates prediction, and dose difference prediction","volume":"11","author":"Huang","year":"2021","journal-title":"Front Oncol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/S0167-8140(02)00174-3","article-title":"Acceptance tests and quality control (QC) procedures for the clinical implementation of intensity modulated radiotherapy (IMRT) using inverse planning and the sliding window technique: experience from five radiotherapy departments","volume":"65","author":"Van Esch","year":"2002","journal-title":"Radiotherapy Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1118\/1.4953835","article-title":"A mathematical framework for virtual IMRT QA using machine learning","volume":"43","author":"Valdes","year":"2016","journal-title":"Med Phys"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.2017.18.issue-5","article-title":"IMRT QA using machine learning: a multi\u2013institutional validation","volume":"18","author":"Valdes","year":"2017","journal-title":"J Appl Clin Med Phys"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1002\/mp.v46.10","article-title":"Predicting gamma passing rates for portal dosimetry\u2013based IMRT QA using machine learning","volume":"46","author":"Lam","year":"2019","journal-title":"Med Phys"},{"key":"B8","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1016\/j.ijrobp.2019.07.049","article-title":"Machine learning for patient\u2013specific quality assurance of VMAT: prediction and classification accuracy","volume":"105","author":"Li","year":"2019","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B9","doi-asserted-by":"publisher","first-page":"095017","DOI":"10.1088\/1361-6560\/ab142e","article-title":"Predicting VMAT patient\u2013specific QA results using a support vector classifier trained on treatment plan characteristics and linac QC metrics","volume":"64","author":"Granville","year":"2019","journal-title":"Phys Med Biol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.577620","article-title":"Integration of AI and machine learning in radiotherapy QA","volume":"3","author":"Chan","year":"2020","journal-title":"Front Artif Intell"},{"key":"B11","doi-asserted-by":"publisher","first-page":"15330338221104881","DOI":"10.1177\/15330338221104881","article-title":"Deep learning for patient\u2013specific quality assurance: predicting gamma passing rates for IMRT based on delivery fluence informed by log files","volume":"21","author":"Huang","year":"2022","journal-title":"Technol Cancer Res Treat"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1002\/mp.2018.45.issue-6","article-title":"Deep nets vs expert designed features in medical physics: an IMRT QA case study","volume":"45","author":"Interian","year":"2018","journal-title":"Med Phys"},{"key":"B13","doi-asserted-by":"publisher","first-page":"195007","DOI":"10.1088\/1361-6560\/aba165","article-title":"Verification of the machine delivery parameters of a treatment plan via deep learning","volume":"65","author":"Fan","year":"2020","journal-title":"Phys Med Biol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/mp.v49.12","article-title":"Efficient dose\u2013volume histogram\u2013based pretreatment patient\u2013specific quality assurance methodology with combined deep learning and machine learning models for volumetric modulated arc radiotherapy","volume":"49","author":"Gong","year":"2022","journal-title":"Med Phys"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00813","article-title":"Non-local neural network","author":"Wang","year":"2018"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun ACM"},{"key":"B17","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arXiv preprint arXiv:1710.10196"},{"key":"B18","doi-asserted-by":"publisher","first-page":"109014","DOI":"10.1016\/j.patcog.2022.109014","article-title":"Deep autoregressive models with spectral attention","volume":"133","author":"Moreno\u2013Pino","year":"2023","journal-title":"Pattern Recognition"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3116668","article-title":"Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy\u2013based and autoregressive models","volume":"44","author":"Bond\u2013Taylor","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B20","doi-asserted-by":"publisher","first-page":"31","DOI":"10.48550\/arXiv.1807.03039","article-title":"Glow: Generative flow with invertible 1x1 convolutions","author":"Kingma","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"B21","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2016","journal-title":"arXiv preprint arXiv:1606.05908"},{"article-title":"Variational inference with normalizing flows","year":"2015","author":"Rezende","key":"B22"},{"key":"B23","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"B24","article-title":"Score\u2013based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv:2011.13456"},{"article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","year":"2015","author":"Sohl\u2013Dickstein","key":"B25"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.03006","article-title":"Structured denoising diffusion models in discrete state\u2013spaces","volume":"34","author":"Austin","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58580-8_22","article-title":"Learning gradient fields for shape generation","author":"Cai","year":"2020"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.00630","article-title":"Variational diffusion models","volume":"34","author":"Kingma","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"B29","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv:2009.00713"},{"key":"B30","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv preprint arXiv:2009.09761"},{"key":"B31","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"B32","article-title":"Cascaded diffusion models for high fidelity image generation","author":"Ho","year":"2022","journal-title":"J Mach Learn Res"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461","article-title":"Image super\u2013resolution via iterative refinement","volume":"45","author":"Saharia","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B34","first-page":"1","article-title":"Metal inpainting in CBCT projections using score\u2013based generative model","volume-title":"2023 IEEE 20th international symposium on biomedical imaging (ISBI), Cartagena Colombia.","author":"Mei","year":"2023"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/0550-3213(81)90056-0","article-title":"Correlation functions and computer simulations","volume":"180","author":"Parisi","year":"1981","journal-title":"Nucl Phys B"},{"key":"B36","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.radonc.2020.11.026","article-title":"Deep learning prediction of proton and photon dose distributions for pediatric abdominal tumors","volume":"156","author":"Guerreiro","year":"2021","journal-title":"Radiother Oncol"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1093\/jrr\/rrz051","article-title":"A convolutional neural network approach for IMRT dose distribution prediction in prostate cancer patients","volume":"60","author":"Kajikawa","year":"2019","journal-title":"J Radiat Res"},{"key":"B38","doi-asserted-by":"publisher","first-page":"205010","DOI":"10.1088\/1361-6560\/acfa5e","article-title":"TransQA: deep hybrid transformer network for measurement\u2013guided volumetric dose prediction of pre\u2013treatment patient\u2013specific quality assurance","volume":"68","author":"Zeng","year":"2023","journal-title":"Phys Med Biol"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1002\/mp.v48.11","article-title":"Deep learning\u2013augmented radioluminescence imaging for radiotherapy dose verification","volume":"48","author":"Jia","year":"2021","journal-title":"Med Phys"},{"key":"B40","article-title":"Image restoration with mean\u2013reverting stochastic differential equations","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv:2301.11699"},{"key":"B41","first-page":"32","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"B42","article-title":"Sliced score matching: A scalable approach to density and score estimation","author":"Song","year":"2020","journal-title":"Uncertainty Artif Intelligence PMLR"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2024.1473050\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T06:49:26Z","timestamp":1735886966000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2024.1473050\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,3]]},"references-count":42,"alternative-id":["10.3389\/fonc.2024.1473050"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2024.1473050","relation":{},"ISSN":["2234-943X"],"issn-type":[{"type":"electronic","value":"2234-943X"}],"subject":[],"published":{"date-parts":[[2025,1,3]]},"article-number":"1473050"}}