Automated contouring for breast cancer radiotherapy in the isocentric lateral decubitus position: a neural network-based solution for enhanced precision and efficiency.

IF 2.7 3区 医学 Q3 ONCOLOGY
Strahlentherapie und Onkologie Pub Date : 2025-06-01 Epub Date: 2025-02-03 DOI:10.1007/s00066-024-02364-x
Pierre Loap, Rémi Monteil, Youlia Kirova, Jérémi Vu-Bezin
{"title":"Automated contouring for breast cancer radiotherapy in the isocentric lateral decubitus position: a neural network-based solution for enhanced precision and efficiency.","authors":"Pierre Loap, Rémi Monteil, Youlia Kirova, Jérémi Vu-Bezin","doi":"10.1007/s00066-024-02364-x","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Adjuvant radiotherapy is essential for reducing local recurrence and improving survival in breast cancer patients, but it carries a risk of ischemic cardiac toxicity, which increases with heart exposure. The isocentric lateral decubitus position, where the breast rests flat on a support, reduces heart exposure and leads to delivery of a more uniform dose. This position is particularly beneficial for patients with unique anatomies, such as those with pectus excavatum or larger breast sizes. While artificial intelligence (AI) algorithms for autocontouring have shown promise, they have not been tailored to this specific position. This study aimed to develop and evaluate a neural network-based autocontouring algorithm for patients treated in the isocentric lateral decubitus position.</p><p><strong>Materials and methods: </strong>In this single-center study, 1189 breast cancer patients treated after breast-conserving surgery were included. Their simulation CT scans (1209 scans) were used to train and validate a neural network-based autocontouring algorithm (nnU-Net). Of these, 1087 scans were used for training, and 122 scans were reserved for validation. The algorithm's performance was assessed using the Dice similarity coefficient (DSC) to compare the automatically delineated volumes with manual contours. A clinical evaluation of the algorithm was performed on 30 additional patients, with contours rated by two expert radiation oncologists.</p><p><strong>Results: </strong>The neural network-based algorithm achieved a segmentation time of approximately 4 min, compared to 20 min for manual segmentation. The DSC values for the validation cohort were 0.88 for the treated breast, 0.90 for the heart, 0.98 for the right lung, and 0.97 for the left lung. In the clinical evaluation, 90% of the automatically contoured breast volumes were rated as acceptable without corrections, while the remaining 10% required minor adjustments. All lung contours were accepted without corrections, and heart contours were rated as acceptable in 93.3% of cases, with minor corrections needed in 6.6% of cases.</p><p><strong>Conclusion: </strong>This neural network-based autocontouring algorithm offers a practical, time-saving solution for breast cancer radiotherapy planning in the isocentric lateral decubitus position. Its strong geometric performance, clinical acceptability, and significant time efficiency make it a valuable tool for modern radiotherapy practices, particularly in high-volume centers.</p>","PeriodicalId":21998,"journal":{"name":"Strahlentherapie und Onkologie","volume":" ","pages":"601-605"},"PeriodicalIF":2.7000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Strahlentherapie und Onkologie","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00066-024-02364-x","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/3 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Adjuvant radiotherapy is essential for reducing local recurrence and improving survival in breast cancer patients, but it carries a risk of ischemic cardiac toxicity, which increases with heart exposure. The isocentric lateral decubitus position, where the breast rests flat on a support, reduces heart exposure and leads to delivery of a more uniform dose. This position is particularly beneficial for patients with unique anatomies, such as those with pectus excavatum or larger breast sizes. While artificial intelligence (AI) algorithms for autocontouring have shown promise, they have not been tailored to this specific position. This study aimed to develop and evaluate a neural network-based autocontouring algorithm for patients treated in the isocentric lateral decubitus position.

Materials and methods: In this single-center study, 1189 breast cancer patients treated after breast-conserving surgery were included. Their simulation CT scans (1209 scans) were used to train and validate a neural network-based autocontouring algorithm (nnU-Net). Of these, 1087 scans were used for training, and 122 scans were reserved for validation. The algorithm's performance was assessed using the Dice similarity coefficient (DSC) to compare the automatically delineated volumes with manual contours. A clinical evaluation of the algorithm was performed on 30 additional patients, with contours rated by two expert radiation oncologists.

Results: The neural network-based algorithm achieved a segmentation time of approximately 4 min, compared to 20 min for manual segmentation. The DSC values for the validation cohort were 0.88 for the treated breast, 0.90 for the heart, 0.98 for the right lung, and 0.97 for the left lung. In the clinical evaluation, 90% of the automatically contoured breast volumes were rated as acceptable without corrections, while the remaining 10% required minor adjustments. All lung contours were accepted without corrections, and heart contours were rated as acceptable in 93.3% of cases, with minor corrections needed in 6.6% of cases.

Conclusion: This neural network-based autocontouring algorithm offers a practical, time-saving solution for breast cancer radiotherapy planning in the isocentric lateral decubitus position. Its strong geometric performance, clinical acceptability, and significant time efficiency make it a valuable tool for modern radiotherapy practices, particularly in high-volume centers.

等心侧卧位的乳腺癌放疗自动轮廓:基于神经网络的提高精度和效率的解决方案。
背景:辅助放疗对于减少乳腺癌患者局部复发和提高生存率至关重要,但它有缺血性心脏毒性的风险,心脏暴露会增加缺血性心脏毒性。等心侧卧位,即乳房平躺在支撑物上,减少心脏暴露,使剂量更均匀。这种体位对解剖结构独特的患者尤其有益,如漏斗胸或乳房较大的患者。虽然用于自动轮廓的人工智能(AI)算法已经显示出前景,但它们并没有针对这个特定的位置量身定制。本研究旨在开发和评估一种基于神经网络的自动轮廓算法,用于等心侧卧位患者的治疗。材料与方法:本单中心研究纳入1189例保乳手术后的乳腺癌患者。他们的模拟CT扫描(1209次扫描)用于训练和验证基于神经网络的自动轮廓算法(nnU-Net)。其中,1087次扫描用于训练,122次扫描用于验证。使用Dice相似系数(DSC)对自动绘制的体与手动绘制的体进行比较,评估算法的性能。对另外30名患者进行了该算法的临床评估,由两名放射肿瘤学专家评估轮廓。结果:基于神经网络算法的分割时间约为4 min,而人工分割时间为20 min。验证队列的DSC值为乳腺0.88,心脏0.90,右肺0.98,左肺0.97。在临床评估中,90%的自动轮廓乳房体积被评为可接受的,无需纠正,而剩下的10%需要轻微的调整。所有的肺轮廓均被接受,无需校正,93.3%的病例认为心脏轮廓可接受,6.6%的病例需要轻微校正。结论:基于神经网络的自动轮廓算法为等心侧卧位乳腺癌放疗规划提供了一种实用、省时的解决方案。其强大的几何性能,临床可接受性和显著的时间效率使其成为现代放射治疗实践的宝贵工具,特别是在高容量中心。
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
CiteScore
5.70
自引率
12.90%
发文量
141
审稿时长
3-8 weeks
期刊介绍: Strahlentherapie und Onkologie, published monthly, is a scientific journal that covers all aspects of oncology with focus on radiooncology, radiation biology and radiation physics. The articles are not only of interest to radiooncologists but to all physicians interested in oncology, to radiation biologists and radiation physicists. The journal publishes original articles, review articles and case studies that are peer-reviewed. It includes scientific short communications as well as a literature review with annotated articles that inform the reader on new developments in the various disciplines concerned and hence allow for a sound overview on the latest results in radiooncology research. Founded in 1912, Strahlentherapie und Onkologie is the oldest oncological journal in the world. Today, contributions are published in English and German. All articles have English summaries and legends. The journal is the official publication of several scientific radiooncological societies and publishes the relevant communications of these societies.
×
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:604180095
Book学术官方微信