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, Xuying Shang, Nan Li, Zishen Wang, Chunfeng Fang, Yue Zou, Xiaoyun Le, Gaolong Zhang, 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 16 16 voxels, 3 mm resolution) and energy (a float value) as inputs and outputs the spot dose distribution (256 16 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.
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.