A multi-modal diffusion model for noise reduction of particle number limited Monte Carlo dose calculation for carbon ion radiotherapy

IF 3.2 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Medical physics Pub Date : 2025-09-24 DOI:10.1002/mp.70021

Jueye Zhang, Youfang Lai, Haonan Feng, Xiangde Luo, Kai-Wen Li, Tenghui Wang, Cheng Chang, Gen Yang, Chen Lin, Tian Li, Chao Yang, Yibao Zhang

{"title":"A multi-modal diffusion model for noise reduction of particle number limited Monte Carlo dose calculation for carbon ion radiotherapy","authors":"Jueye Zhang, Youfang Lai, Haonan Feng, Xiangde Luo, Kai-Wen Li, Tenghui Wang, Cheng Chang, Gen Yang, Chen Lin, Tian Li, Chao Yang, Yibao Zhang","doi":"10.1002/mp.70021","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>The low computation efficiency impeded the broad application of Monte Carlo (MC) simulation to particle therapy. The existing deep learning (DL) methods for fast dose calculation lacked physics-based interpretability, hence, may introduce additional risks, especially for the more complex carbon ion radiotherapy.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>To develop and validate a multi-modal diffusion model, Diff-MC, for noise reduction of particle number limited MC dose calculation, potentially supporting better optimization and faster online adaptation for carbon ion radiotherapy.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>By using multi-modal data such as CT images, dose maps using a low number of primary particles and beam parameters, and so forth, Diff-MC was developed to generate a dose map adaptively based on the beam state. To enable effective inter-modal interactions, a hybrid-fusion strategy was applied to integrate the data-level, feature-level, and decision-level fusion. The model was evaluated on a highly heterogeneous dataset, including 15 000 paired beamlet data cropped from 20 CTs for training and validating, 500 paired beamlet data cropped from other 5 CTs for testing, and 500 paired beamlet data cropped from another 100 CTs for generalizability test. All datasets encompassed various geometry and beamlet physics parameters such as energy distribution and number of primary particles, and so forth.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Using the MC simulation based on high number of primary particles as ground-truth, the Diff-MC achieved nearly linear acceleration and high accuracy of gamma passing rate up to 99.25% under the criteria of 3 mm, 3%, 10% cutoff. The performance was significantly higher (all <span></span><math>\n <semantics>\n <mrow>\n <mi>p</mi>\n <mo><</mo>\n <mn>0.01</mn>\n </mrow>\n <annotation>$p<0.01$</annotation>\n </semantics></math>) than the UNet-based models (96.17%) and transformer-based models (97.81%). The accuracy achieved by Diff-MC in the generalizability test was 99.22%. The lateral dose, integral depth dose (IDD), and percentage depth dose (PDD) of Diff-MC were also more consistent with the ground-truth than that of conventional AI models.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>The proposed Diff-MC method displayed high efficiency and robustness in carbon ion dose calculation. By maintaining the physics features of MC, the results of Diff-MC were more interpretable and generalizable than the conventional AI models.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 10","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://aapm.onlinelibrary.wiley.com/doi/10.1002/mp.70021","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Background

The low computation efficiency impeded the broad application of Monte Carlo (MC) simulation to particle therapy. The existing deep learning (DL) methods for fast dose calculation lacked physics-based interpretability, hence, may introduce additional risks, especially for the more complex carbon ion radiotherapy.

Purpose

To develop and validate a multi-modal diffusion model, Diff-MC, for noise reduction of particle number limited MC dose calculation, potentially supporting better optimization and faster online adaptation for carbon ion radiotherapy.

Methods

By using multi-modal data such as CT images, dose maps using a low number of primary particles and beam parameters, and so forth, Diff-MC was developed to generate a dose map adaptively based on the beam state. To enable effective inter-modal interactions, a hybrid-fusion strategy was applied to integrate the data-level, feature-level, and decision-level fusion. The model was evaluated on a highly heterogeneous dataset, including 15 000 paired beamlet data cropped from 20 CTs for training and validating, 500 paired beamlet data cropped from other 5 CTs for testing, and 500 paired beamlet data cropped from another 100 CTs for generalizability test. All datasets encompassed various geometry and beamlet physics parameters such as energy distribution and number of primary particles, and so forth.

Results

Using the MC simulation based on high number of primary particles as ground-truth, the Diff-MC achieved nearly linear acceleration and high accuracy of gamma passing rate up to 99.25% under the criteria of 3 mm, 3%, 10% cutoff. The performance was significantly higher (all $p < 0.01$ ) than the UNet-based models (96.17%) and transformer-based models (97.81%). The accuracy achieved by Diff-MC in the generalizability test was 99.22%. The lateral dose, integral depth dose (IDD), and percentage depth dose (PDD) of Diff-MC were also more consistent with the ground-truth than that of conventional AI models.

Conclusions

The proposed Diff-MC method displayed high efficiency and robustness in carbon ion dose calculation. By maintaining the physics features of MC, the results of Diff-MC were more interpretable and generalizable than the conventional AI models.

Abstract Image

查看原文本刊更多论文

碳离子放射治疗中粒子数限制蒙特卡罗剂量计算的多模态扩散降噪模型。

背景：计算效率低阻碍了蒙特卡罗模拟在粒子治疗中的广泛应用。现有的用于快速剂量计算的深度学习（DL）方法缺乏基于物理的可解释性，因此可能会带来额外的风险，特别是对于更复杂的碳离子放疗。目的：开发并验证一种多模态扩散模型Diff-MC，用于粒子数限制MC剂量计算的降噪，可能支持碳离子放疗更好的优化和更快的在线适应。方法：利用CT图像、低初级粒子数剂量图、光束参数等多模态数据，开发基于光束状态自适应生成剂量图的difff - mc。为了实现有效的多模式交互，采用混合融合策略集成数据级、特征级和决策级融合。该模型在一个高度异构的数据集上进行评估，包括从20个ct中裁剪的15000对光束数据用于训练和验证，从其他5个ct中裁剪的500对光束数据用于测试，以及从另外100个ct中裁剪的500对光束数据用于泛化测试。所有数据集包含各种几何和光束物理参数，如能量分布和主要粒子的数量，等等。结果：在3 mm、3%、10%截止条件下，采用以高初级粒子数为基础的MC模拟，Diff-MC获得了接近线性加速度和99.25%的伽马通过率精度。性能显著高于基于unet的模型（96.17%）和基于变压器的模型（97.81%）（p均为0.01 $p）。Diff-MC在归纳性检验中的准确率为99.22%。Diff-MC的侧位剂量、积分深度剂量（IDD）和百分比深度剂量（PDD）也比常规AI模型更符合基本事实。结论：Diff-MC法计算碳离子剂量具有较高的效率和稳健性。通过保持人工智能的物理特征，Diff-MC的结果比传统的人工智能模型更具可解释性和可泛化性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Medical physics 医学-核医学

CiteScore

6.80

自引率

15.80%

发文量

660

审稿时长

1.7 months

期刊介绍： Medical Physics publishes original, high impact physics, imaging science, and engineering research that advances patient diagnosis and therapy through contributions in 1) Basic science developments with high potential for clinical translation 2) Clinical applications of cutting edge engineering and physics innovations 3) Broadly applicable and innovative clinical physics developments Medical Physics is a journal of global scope and reach. By publishing in Medical Physics your research will reach an international, multidisciplinary audience including practicing medical physicists as well as physics- and engineering based translational scientists. We work closely with authors of promising articles to improve their quality.