Explicitly encoding the cyclic nature of breathing signal allows for accurate breathing motion prediction in radiotherapy with minimal training data

IF 3.4 Q2 ONCOLOGY
Andreas Renner , Ingo Gulyas , Martin Buschmann , Gerd Heilemann , Barbara Knäusl , Martin Heilmann , Joachim Widder , Dietmar Georg , Petra Trnková
{"title":"Explicitly encoding the cyclic nature of breathing signal allows for accurate breathing motion prediction in radiotherapy with minimal training data","authors":"Andreas Renner ,&nbsp;Ingo Gulyas ,&nbsp;Martin Buschmann ,&nbsp;Gerd Heilemann ,&nbsp;Barbara Knäusl ,&nbsp;Martin Heilmann ,&nbsp;Joachim Widder ,&nbsp;Dietmar Georg ,&nbsp;Petra Trnková","doi":"10.1016/j.phro.2024.100594","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and purpose</h3><p>Active breathing motion management in radiotherapy consists of motion monitoring, quantification and mitigation. It is impacted by associated latencies of a few 100 ms. Artificial neural networks can successfully predict breathing motion and eliminate latencies. However, they require usually a large dataset for training. The objective of this work was to demonstrate that explicitly encoding the cyclic nature of the breathing signal into the training data enables significant reduction of training datasets which can be obtained from healthy volunteers.</p></div><div><h3>Material and methods</h3><p>Seventy surface scanner breathing signals from 25 healthy volunteers in anterior-posterior direction were used for training and validation (ratio 4:1) of long short-term memory models. The model performance was compared to a model using decomposition into phase, amplitude and a time-dependent baseline. Testing of the models was performed on 55 independent breathing signals in anterior-posterior direction from surface scanner (35 lung, 20 liver) of 30 patients with a mean breathing amplitude of (5.9 ± 6.7)<!--> <!-->mm.</p></div><div><h3>Results</h3><p>Using the decomposed breathing signal allowed for a reduction of the absolute root-mean square error (RMSE) from 0.34 mm to 0.12 mm during validation. Testing using patient data yielded an average absolute RMSE of the breathing signal of (0.16 ± 0.11)<!--> <!-->mm with a prediction horizon of 500 ms.</p></div><div><h3>Conclusion</h3><p>It was demonstrated that a motion prediction model can be trained with less than 100 datasets of healthy volunteers if breathing cycle parameters are considered. Applied to 55 patients, the model predicted breathing motion with a high accuracy.</p></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"30 ","pages":"Article 100594"},"PeriodicalIF":3.4000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405631624000642/pdfft?md5=11454d87d05403c0a30c0d3df553dcde&pid=1-s2.0-S2405631624000642-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/S2405631624000642","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

Abstract

Background and purpose

Active breathing motion management in radiotherapy consists of motion monitoring, quantification and mitigation. It is impacted by associated latencies of a few 100 ms. Artificial neural networks can successfully predict breathing motion and eliminate latencies. However, they require usually a large dataset for training. The objective of this work was to demonstrate that explicitly encoding the cyclic nature of the breathing signal into the training data enables significant reduction of training datasets which can be obtained from healthy volunteers.

Material and methods

Seventy surface scanner breathing signals from 25 healthy volunteers in anterior-posterior direction were used for training and validation (ratio 4:1) of long short-term memory models. The model performance was compared to a model using decomposition into phase, amplitude and a time-dependent baseline. Testing of the models was performed on 55 independent breathing signals in anterior-posterior direction from surface scanner (35 lung, 20 liver) of 30 patients with a mean breathing amplitude of (5.9 ± 6.7) mm.

Results

Using the decomposed breathing signal allowed for a reduction of the absolute root-mean square error (RMSE) from 0.34 mm to 0.12 mm during validation. Testing using patient data yielded an average absolute RMSE of the breathing signal of (0.16 ± 0.11) mm with a prediction horizon of 500 ms.

Conclusion

It was demonstrated that a motion prediction model can be trained with less than 100 datasets of healthy volunteers if breathing cycle parameters are considered. Applied to 55 patients, the model predicted breathing motion with a high accuracy.

对呼吸信号的周期性进行明确编码,只需最少的训练数据就能在放疗中准确预测呼吸运动
背景和目的放疗中的主动呼吸运动管理包括运动监测、量化和缓解。它受到几百毫秒相关延迟的影响。人工神经网络可以成功预测呼吸运动并消除延迟。不过,它们通常需要大量数据集进行训练。这项工作的目的是证明,将呼吸信号的周期性明确编码到训练数据中能显著减少训练数据集,而训练数据集可从健康志愿者处获得。材料和方法来自 25 名健康志愿者的 70 个前后方向的表面扫描呼吸信号被用于训练和验证(比例为 4:1)长短期记忆模型。将模型性能与分解为相位、振幅和随时间变化的基线的模型进行了比较。结果在验证过程中,使用分解的呼吸信号可将均方根绝对误差(RMSE)从 0.34 毫米减少到 0.12 毫米。结论研究表明,如果考虑到呼吸周期参数,运动预测模型可以用少于 100 个健康志愿者数据集进行训练。该模型应用于 55 名患者,预测呼吸运动的准确率很高。
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
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