Incorporating patient-specific information for the development of rectal tumor auto-segmentation models for online adaptive magnetic resonance Image-guided radiotherapy

Chavelli M. Kensen , Rita Simões , Anja Betgen , Lisa Wiersema , Doenja M.J. Lambregts , Femke P. Peters , Corrie A.M. Marijnen , Uulke A. van der Heide , Tomas M. Janssen
{"title":"Incorporating patient-specific information for the development of rectal tumor auto-segmentation models for online adaptive magnetic resonance Image-guided radiotherapy","authors":"Chavelli M. Kensen ,&nbsp;Rita Simões ,&nbsp;Anja Betgen ,&nbsp;Lisa Wiersema ,&nbsp;Doenja M.J. Lambregts ,&nbsp;Femke P. Peters ,&nbsp;Corrie A.M. Marijnen ,&nbsp;Uulke A. van der Heide ,&nbsp;Tomas M. Janssen","doi":"10.1016/j.phro.2024.100648","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and purpose</h3><p>In online adaptive magnetic resonance image (MRI)-guided radiotherapy (MRIgRT), manual contouring of rectal tumors on daily images is labor-intensive and time-consuming. Automation of this task is complex due to substantial variation in tumor shape and location between patients. The aim of this work was to investigate different approaches of propagating patient-specific prior information to the online adaptive treatment fractions to improve deep-learning based auto-segmentation of rectal tumors.</p></div><div><h3>Materials and methods</h3><p>243 T2-weighted MRI scans of 49 rectal cancer patients treated on the 1.5T MR-Linear accelerator (MR-Linac) were utilized to train models to segment rectal tumors. As benchmark, an MRI_only auto-segmentation model was trained. Three approaches of including a patient-specific prior were studied: 1. include the segmentations of fraction 1 as extra input channel for the auto-segmentation of subsequent fractions, 2. fine-tuning of the MRI_only model to fraction 1 (PSF_1) and 3. fine-tuning of the MRI_only model on all earlier fractions (PSF_cumulative). Auto-segmentations were compared to the manual segmentation using geometric similarity metrics. Clinical impact was assessed by evaluating post-treatment target coverage.</p></div><div><h3>Results</h3><p>All patient-specific methods outperformed the MRI_only segmentation approach. Median 95th percentile Hausdorff (95HD) were 22.0 (range: 6.1–76.6) mm for MRI_only segmentation, 9.9 (range: 2.5–38.2) mm for MRI+prior segmentation, 6.4 (range: 2.4–17.8) mm for PSF_1 and 4.8 (range: 1.7–26.9) mm for PSF_cumulative. PSF_cumulative was found to be superior to PSF_1 from fraction 4 onward (p = 0.014).</p></div><div><h3>Conclusion</h3><p>Patient-specific fine-tuning of automatically segmented rectal tumors, using images and segmentations from all previous fractions, yields superior quality compared to other auto-segmentation approaches.</p></div>","PeriodicalId":36850,"journal":{"name":"Physics and Imaging in Radiation Oncology","volume":"32 ","pages":"Article 100648"},"PeriodicalIF":3.4000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405631624001180/pdfft?md5=bf30e0e5baddbf3b8635126444c1301f&pid=1-s2.0-S2405631624001180-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/S2405631624001180","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

In online adaptive magnetic resonance image (MRI)-guided radiotherapy (MRIgRT), manual contouring of rectal tumors on daily images is labor-intensive and time-consuming. Automation of this task is complex due to substantial variation in tumor shape and location between patients. The aim of this work was to investigate different approaches of propagating patient-specific prior information to the online adaptive treatment fractions to improve deep-learning based auto-segmentation of rectal tumors.

Materials and methods

243 T2-weighted MRI scans of 49 rectal cancer patients treated on the 1.5T MR-Linear accelerator (MR-Linac) were utilized to train models to segment rectal tumors. As benchmark, an MRI_only auto-segmentation model was trained. Three approaches of including a patient-specific prior were studied: 1. include the segmentations of fraction 1 as extra input channel for the auto-segmentation of subsequent fractions, 2. fine-tuning of the MRI_only model to fraction 1 (PSF_1) and 3. fine-tuning of the MRI_only model on all earlier fractions (PSF_cumulative). Auto-segmentations were compared to the manual segmentation using geometric similarity metrics. Clinical impact was assessed by evaluating post-treatment target coverage.

Results

All patient-specific methods outperformed the MRI_only segmentation approach. Median 95th percentile Hausdorff (95HD) were 22.0 (range: 6.1–76.6) mm for MRI_only segmentation, 9.9 (range: 2.5–38.2) mm for MRI+prior segmentation, 6.4 (range: 2.4–17.8) mm for PSF_1 and 4.8 (range: 1.7–26.9) mm for PSF_cumulative. PSF_cumulative was found to be superior to PSF_1 from fraction 4 onward (p = 0.014).

Conclusion

Patient-specific fine-tuning of automatically segmented rectal tumors, using images and segmentations from all previous fractions, yields superior quality compared to other auto-segmentation approaches.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
为在线自适应磁共振图像引导放射治疗开发直肠肿瘤自动分割模型时纳入患者特异性信息
背景和目的在在线自适应磁共振成像(MRI)引导放疗(MRIgRT)中,在日常图像上手动绘制直肠肿瘤轮廓是一项劳动密集型且耗时的工作。由于不同患者的肿瘤形状和位置存在很大差异,这项任务的自动化非常复杂。这项工作的目的是研究向在线自适应治疗分数传播患者特定先验信息的不同方法,以改进基于深度学习的直肠肿瘤自动分割。作为基准,训练了一个仅使用 MRI 的自动分割模型。研究了包含患者特异性先验的三种方法:1.将第 1 部分的分割作为后续部分自动分割的额外输入通道;2.对第 1 部分的纯 MRI 模型进行微调(PSF_1);3.对所有早期部分的纯 MRI 模型进行微调(PSF_cumulative)。使用几何相似度指标将自动分割与手动分割进行比较。通过评估治疗后的目标覆盖范围来评估临床效果。仅核磁共振成像分割的第 95 百分位数 Hausdorff (95HD) 中值为 22.0(范围:6.1-76.6)毫米,核磁共振成像+先前分割为 9.9(范围:2.5-38.2)毫米,PSF_1 为 6.4(范围:2.4-17.8)毫米,PSF_cumulative 为 4.8(范围:1.7-26.9)毫米。PSF_cumulative从第4分段开始就优于PSF_1(p = 0.014)。结论与其他自动分段方法相比,使用之前所有分段的图像和分段对患者特定的直肠肿瘤自动分段进行微调可获得更高的质量。
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 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
期刊最新文献
Results of 2023 survey on the use of synthetic computed tomography for magnetic resonance Imaging-only radiotherapy: Current status and future steps Head and neck automatic multi-organ segmentation on Dual-Energy Computed Tomography Automatic segmentation for magnetic resonance imaging guided individual elective lymph node irradiation in head and neck cancer patients Development of a novel 3D-printed dynamic anthropomorphic thorax phantom for evaluation of four-dimensional computed tomography Technical feasibility of delivering a simultaneous integrated boost in partial breast irradiation
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1