利用深度学习和脚本优化为前列腺放疗患者自动生成计划

IF 3.4 Q2 ONCOLOGY
Cody Church , Michelle Yap , Mohamed Bessrour , Michael Lamey , Dal Granville
{"title":"利用深度学习和脚本优化为前列腺放疗患者自动生成计划","authors":"Cody Church ,&nbsp;Michelle Yap ,&nbsp;Mohamed Bessrour ,&nbsp;Michael Lamey ,&nbsp;Dal Granville","doi":"10.1016/j.phro.2024.100641","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and Purpose</h3><p>Treatment planning is a time-intensive task that could be automated. We aimed to develop a “single-click” workflow, fully deployed within a commercial treatment planning system (TPS), for autoplanning prostate radiotherapy treatment plans using predictions from a deep learning model (DLM).</p></div><div><h3>Materials and Methods</h3><p>Automatically generated treatment plans were created with a single script, executed from within a commercial TPS scripting environment, that performed two stages sequentially. Initially, a 3D dose distribution was predicted with a ResUNet DLM. The DLM was trained and validated using previously treated datasets (n = 120) which used 3D contours as inputs. Following this, dose predictions were converted into treatment plans by extracting dose-volume metrics from the predictions to use as objectives for the inverse optimizer within the TPS. An independent test dataset (n = 20) was used to evaluate the similarity between automated and clinical plans.</p></div><div><h3>Results</h3><p>For planning target volumes, the median percentage difference and interquartile range between the automatically generated plans and clinical plans were 0.4% [0.2-1.1%] for the V<sub>100%</sub>, −0.5% [(−1.0)-(−0.2)%] for D<sub>99%</sub> and −0.5% [(−1.0)-(−0.2)%] for D<sub>95%</sub>. Bladder and rectum volume-at-dose objectives agreed within −6.1% [(−12.5)-0.9%]. The conversion of the DLM prediction into a treatment plan took 15 min [13-16 min].</p></div><div><h3>Conclusions</h3><p>An automatic plan generation workflow that uses a DL model with scripted optimization was fully deployed in a commercial TPS. Autoplans were compared to previously treated clinical plans and were found to be non-inferior.</p></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405631624001118/pdfft?md5=6fcbb63bca1c9fd02b6fc82ecbe8a942&pid=1-s2.0-S2405631624001118-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Automated plan generation for prostate radiotherapy patients using deep learning and scripted optimization\",\"authors\":\"Cody Church ,&nbsp;Michelle Yap ,&nbsp;Mohamed Bessrour ,&nbsp;Michael Lamey ,&nbsp;Dal Granville\",\"doi\":\"10.1016/j.phro.2024.100641\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background and Purpose</h3><p>Treatment planning is a time-intensive task that could be automated. We aimed to develop a “single-click” workflow, fully deployed within a commercial treatment planning system (TPS), for autoplanning prostate radiotherapy treatment plans using predictions from a deep learning model (DLM).</p></div><div><h3>Materials and Methods</h3><p>Automatically generated treatment plans were created with a single script, executed from within a commercial TPS scripting environment, that performed two stages sequentially. Initially, a 3D dose distribution was predicted with a ResUNet DLM. The DLM was trained and validated using previously treated datasets (n = 120) which used 3D contours as inputs. Following this, dose predictions were converted into treatment plans by extracting dose-volume metrics from the predictions to use as objectives for the inverse optimizer within the TPS. An independent test dataset (n = 20) was used to evaluate the similarity between automated and clinical plans.</p></div><div><h3>Results</h3><p>For planning target volumes, the median percentage difference and interquartile range between the automatically generated plans and clinical plans were 0.4% [0.2-1.1%] for the V<sub>100%</sub>, −0.5% [(−1.0)-(−0.2)%] for D<sub>99%</sub> and −0.5% [(−1.0)-(−0.2)%] for D<sub>95%</sub>. Bladder and rectum volume-at-dose objectives agreed within −6.1% [(−12.5)-0.9%]. The conversion of the DLM prediction into a treatment plan took 15 min [13-16 min].</p></div><div><h3>Conclusions</h3><p>An automatic plan generation workflow that uses a DL model with scripted optimization was fully deployed in a commercial TPS. Autoplans were compared to previously treated clinical plans and were found to be non-inferior.</p></div>\",\"PeriodicalId\":36850,\"journal\":{\"name\":\"Physics and Imaging in Radiation Oncology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-09-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2405631624001118/pdfft?md5=6fcbb63bca1c9fd02b6fc82ecbe8a942&pid=1-s2.0-S2405631624001118-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Physics and Imaging in Radiation Oncology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2405631624001118\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Physics and Imaging in Radiation Oncology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2405631624001118","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

背景和目的治疗计划是一项时间密集型任务,可以实现自动化。我们的目标是开发一种 "单击 "工作流程,在商用治疗计划系统(TPS)中全面部署,利用深度学习模型(DLM)的预测结果自动规划前列腺放疗治疗计划。材料与方法自动生成的治疗计划是通过一个脚本创建的,该脚本在商用 TPS 脚本环境中执行,依次执行两个阶段。首先,使用 ResUNet DLM 预测三维剂量分布。DLM 使用以前处理过的数据集(n = 120)进行训练和验证,这些数据集使用三维轮廓作为输入。之后,通过从预测中提取剂量-体积指标,将剂量预测转换为治疗计划,作为 TPS 中反优化器的目标。结果对于规划目标体积,自动生成的计划与临床计划之间的中位百分比差异和四分位数范围分别为:V100%为 0.4% [0.2-1.1%],D99%为-0.5% [(-1.0)-(-0.2)%],D95%为-0.5% [(-1.0)-(-0.2)%]。膀胱和直肠剂量容积目标的一致性在-6.1%[(-12.5)-0.9%]以内。将 DLM 预测转换为治疗计划耗时 15 分钟[13-16 分钟]。结论在商用 TPS 中全面部署了使用带脚本优化的 DL 模型的自动计划生成工作流程。将自动计划与之前的临床治疗计划进行了比较,发现两者并无差别。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automated plan generation for prostate radiotherapy patients using deep learning and scripted optimization

Background and Purpose

Treatment planning is a time-intensive task that could be automated. We aimed to develop a “single-click” workflow, fully deployed within a commercial treatment planning system (TPS), for autoplanning prostate radiotherapy treatment plans using predictions from a deep learning model (DLM).

Materials and Methods

Automatically generated treatment plans were created with a single script, executed from within a commercial TPS scripting environment, that performed two stages sequentially. Initially, a 3D dose distribution was predicted with a ResUNet DLM. The DLM was trained and validated using previously treated datasets (n = 120) which used 3D contours as inputs. Following this, dose predictions were converted into treatment plans by extracting dose-volume metrics from the predictions to use as objectives for the inverse optimizer within the TPS. An independent test dataset (n = 20) was used to evaluate the similarity between automated and clinical plans.

Results

For planning target volumes, the median percentage difference and interquartile range between the automatically generated plans and clinical plans were 0.4% [0.2-1.1%] for the V100%, −0.5% [(−1.0)-(−0.2)%] for D99% and −0.5% [(−1.0)-(−0.2)%] for D95%. Bladder and rectum volume-at-dose objectives agreed within −6.1% [(−12.5)-0.9%]. The conversion of the DLM prediction into a treatment plan took 15 min [13-16 min].

Conclusions

An automatic plan generation workflow that uses a DL model with scripted optimization was fully deployed in a commercial TPS. Autoplans were compared to previously treated clinical plans and were found to be non-inferior.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Physics and Imaging in Radiation Oncology
Physics and Imaging in Radiation Oncology Physics and Astronomy-Radiation
CiteScore
5.30
自引率
18.90%
发文量
93
审稿时长
6 weeks
×
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