An AI dose-influence matrix engine for robust pencil beam scanning protons therapy

IF 3.2 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Medical physics Pub Date : 2024-12-23 DOI:10.1002/mp.17602
Yaoying Liu, Xuying Shang, Nan Li, Zishen Wang, Chunfeng Fang, Yue Zou, Xiaoyun Le, Gaolong Zhang, Shouping Xu
{"title":"An AI dose-influence matrix engine for robust pencil beam scanning protons therapy","authors":"Yaoying Liu,&nbsp;Xuying Shang,&nbsp;Nan Li,&nbsp;Zishen Wang,&nbsp;Chunfeng Fang,&nbsp;Yue Zou,&nbsp;Xiaoyun Le,&nbsp;Gaolong Zhang,&nbsp;Shouping Xu","doi":"10.1002/mp.17602","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Rapid planning is of tremendous value in proton pencil beam scanning (PBS) therapy in overcoming range uncertainty. However, the dose calculation of the dose influence matrix (D<sub>ij</sub>) in robust PBS plan optimization is time-consuming and requires substantial acceleration to enhance efficiency.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>To accelerate the D<sub>ij</sub> calculations in PBS therapy, we developed an AI-D<sub>ij</sub> engine integrated into our in-house treatment planning system (TPS).</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>The AI-D<sub>ij</sub> engine calculates spot dose using a transformer-based spot dose calculation model (SDM), which takes CT volumes (CT-bars, 256 <span></span><math>\n <semantics>\n <mo>×</mo>\n <annotation>$ \\times $</annotation>\n </semantics></math> 16 <span></span><math>\n <semantics>\n <mo>×</mo>\n <annotation>$ \\times $</annotation>\n </semantics></math> 16 voxels, 3 mm resolution) and energy (a float value) as inputs and outputs the spot dose distribution (256 <span></span><math>\n <semantics>\n <mo>×</mo>\n <annotation>$ \\times $</annotation>\n </semantics></math> 16 <span></span><math>\n <semantics>\n <mo>×</mo>\n <annotation>$ \\times $</annotation>\n </semantics></math> 16). The SDM was trained on over 200 000 CT-bars and Monte Carlo (MC) spot dose (spanning energy levels from 70 to 225 MeV). Clinical-implemented treatment plans for the head, lung, and liver, initially created on Raystation, were replanned using our AI-D<sub>ij</sub> engine under identical gantry angles and uncertainties settings. After optimizing the spot weight, each in-house plan was recalculated using MCsquare for MC dose evaluation. The dose-volume histogram (DVH) metrics from the in-house TPS and Raystation were compared, evaluating both the optimized and MC doses.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>In optimization, the differences of DVH metrics (%, Value<sub>in-house</sub>—Value<sub>Raystation</sub>) across all uncertainty scenarios between the in-house and Raystation plans were 0.93 ± 2.04% for clinical target volume (CTV) and −5.94 ± 12.19% for organ at risks (OARs). For the MC doses, the differences were 2.48 ± 2.78% for CTV and −5.47 ± 14.16% for OARs. The time cost of a robust AI-D<sub>ij</sub> calculation can be within 2s on an RTX3090 GPU.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>We conducted a feasibility study on AI-D<sub>ij</sub> engine-based robust PBS plan optimization, demonstrating both high planning speed and quality.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1903-1913"},"PeriodicalIF":3.2000,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mp.17602","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

Rapid planning is of tremendous value in proton pencil beam scanning (PBS) therapy in overcoming range uncertainty. However, the dose calculation of the dose influence matrix (Dij) in robust PBS plan optimization is time-consuming and requires substantial acceleration to enhance efficiency.

Purpose

To accelerate the Dij calculations in PBS therapy, we developed an AI-Dij engine integrated into our in-house treatment planning system (TPS).

Methods

The AI-Dij engine calculates spot dose using a transformer-based spot dose calculation model (SDM), which takes CT volumes (CT-bars, 256  × $ \times $  16  × $ \times $  16 voxels, 3 mm resolution) and energy (a float value) as inputs and outputs the spot dose distribution (256  × $ \times $  16  × $ \times $  16). The SDM was trained on over 200 000 CT-bars and Monte Carlo (MC) spot dose (spanning energy levels from 70 to 225 MeV). Clinical-implemented treatment plans for the head, lung, and liver, initially created on Raystation, were replanned using our AI-Dij engine under identical gantry angles and uncertainties settings. After optimizing the spot weight, each in-house plan was recalculated using MCsquare for MC dose evaluation. The dose-volume histogram (DVH) metrics from the in-house TPS and Raystation were compared, evaluating both the optimized and MC doses.

Results

In optimization, the differences of DVH metrics (%, Valuein-house—ValueRaystation) across all uncertainty scenarios between the in-house and Raystation plans were 0.93 ± 2.04% for clinical target volume (CTV) and −5.94 ± 12.19% for organ at risks (OARs). For the MC doses, the differences were 2.48 ± 2.78% for CTV and −5.47 ± 14.16% for OARs. The time cost of a robust AI-Dij calculation can be within 2s on an RTX3090 GPU.

Conclusion

We conducted a feasibility study on AI-Dij engine-based robust PBS plan optimization, demonstrating both high planning speed and quality.

用于强韧铅笔束扫描质子治疗的人工智能剂量影响矩阵引擎。
背景:快速规划在质子束扫描(PBS)治疗中克服范围不确定性具有重要价值。然而,在稳健PBS计划优化中,剂量影响矩阵(Dij)的剂量计算非常耗时,并且需要大幅加速以提高效率。目的:为了加速PBS治疗中的Dij计算,我们开发了一个集成到我们内部治疗计划系统(TPS)中的AI-Dij引擎。方法:AI-Dij引擎采用基于变压器的点剂量计算模型(SDM)计算点剂量,该模型以CT体积(CT条,256 × $ $ × × $ $ × × $ $ × × $ 16体素,3 mm分辨率)和能量(一个浮点值)作为输入,输出点剂量分布(256 × $ $ × × $ $ × × $ $ × × $ 16)。SDM在超过20万个ct棒和蒙特卡罗(MC)点剂量(跨越70至225兆电子伏特的能级)上进行了训练。最初在Raystation上创建的头部、肺部和肝脏的临床治疗计划,使用我们的AI-Dij引擎在相同的龙门角度和不确定设置下重新规划。优化点权重后,使用MCsquare重新计算每个内部计划,进行MC剂量评估。比较内部TPS和Raystation的剂量-体积直方图(DVH)指标,评估优化剂量和MC剂量。结果:在优化中,临床靶体积(CTV)和危险器官(OARs)的DVH指标(%,Valuein-house-ValueRaystation)在所有不确定性情况下的差异为-5.94±12.19%。对于MC剂量,CTV的差异为2.48±2.78%,OARs的差异为-5.47±14.16%。在RTX3090 GPU上,一个健壮的AI-Dij计算的时间成本可以在2s以内。结论:我们对基于AI-Dij引擎的鲁棒PBS计划优化进行了可行性研究,证明了高规划速度和高质量。
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
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.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信