An External, Independent Validation of an O-(2-[18F]Fluoroethyl)-l-Tyrosine PET Automatic Segmentation Network on a Single-Center, Prospective Dataset of Patients with Glioblastoma

Nathaniel Barry, Jake Kendrick, Pejman Rowshanfarzad, Ghulam Mubashar Hassan, Roslyn J. Francis, Nicholas Bucknell, Eng-Siew Koh, Andrew M. Scott, Martin A. Ebert, Robin Gutsche, Keith George Ciantar, Norbert Galldiks, Karl-Josef Langen, Philipp Lohmann
{"title":"An External, Independent Validation of an O-(2-[18F]Fluoroethyl)-l-Tyrosine PET Automatic Segmentation Network on a Single-Center, Prospective Dataset of Patients with Glioblastoma","authors":"Nathaniel Barry, Jake Kendrick, Pejman Rowshanfarzad, Ghulam Mubashar Hassan, Roslyn J. Francis, Nicholas Bucknell, Eng-Siew Koh, Andrew M. Scott, Martin A. Ebert, Robin Gutsche, Keith George Ciantar, Norbert Galldiks, Karl-Josef Langen, Philipp Lohmann","doi":"10.2967/jnumed.124.268925","DOIUrl":null,"url":null,"abstract":"<p>The goal of this study was to conduct an external, independent validation of an <em>O</em>-(2-[<sup>18</sup>F]fluoroethyl)-<span>l</span>-tyrosine ([<sup>18</sup>F]FET) PET automatic segmentation network on a cohort of patients with glioblastoma. <strong>Methods:</strong> Twenty-four patients with glioblastoma were included in this study who underwent a total of 52 [<sup>18</sup>F]FET PET scans (preradiotherapy, <em>n</em> = 23; preradiotherapy retest, <em>n</em> = 9; follow-up, <em>n</em> = 20). Biologic tumor volume (BTV) delineation was performed by an expert nuclear medicine physician and an automatic segmentation network. Physician and automated quantitative metrics (BTV, mean tumor-to-background ratio [TBR<sub>mean</sub>], lesion SUV<sub>mean</sub>, and background SUV<sub>mean</sub>) were assessed with Pearson correlation and Bland–Altman analysis (bias, limits of agreement [LoA]). Automated and physician segmentation overlap was assessed with spatial and distance-based metrics. <strong>Results:</strong> BTV and TBR<sub>mean</sub> Pearson correlation was excellent for all time points (range, 0.92–0.98). In 2 patients with frontal lobe lesions, the network segmented the transverse sinus. Bland–Altman analysis showed network underestimation of physician-derived BTVs (absolute bias, 2.7 cm<sup>3</sup>, LoA, −13.1–18.5 cm<sup>3</sup>; relative bias, 27.9%, LoA, −95.3%–151.2%) and deviations for TBR<sub>mean</sub> were small (absolute bias, 0.03, LoA, −0.25–0.30; relative bias, 0.83%, LoA −14.27%–15.93%). Median Dice similarity coefficient, surface Dice similarity coefficient, Hausdorff distance, 95th percentile Hausdorff distance, and mean absolute surface distance were 0.83, 0.95, 10.94 mm, 3.62 mm, and 0.88 mm, respectively. <strong>Conclusion:</strong> Automated quantitative analysis was highly correlated with physician assessment; however, volume underestimation and erroneous segmentations may impact radiotherapy treatment planning and response assessment. Further training on a representative local dataset would likely be required for multicenter implementation.</p>","PeriodicalId":22820,"journal":{"name":"The Journal of Nuclear Medicine","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Journal of Nuclear Medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2967/jnumed.124.268925","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The goal of this study was to conduct an external, independent validation of an O-(2-[18F]fluoroethyl)-l-tyrosine ([18F]FET) PET automatic segmentation network on a cohort of patients with glioblastoma. Methods: Twenty-four patients with glioblastoma were included in this study who underwent a total of 52 [18F]FET PET scans (preradiotherapy, n = 23; preradiotherapy retest, n = 9; follow-up, n = 20). Biologic tumor volume (BTV) delineation was performed by an expert nuclear medicine physician and an automatic segmentation network. Physician and automated quantitative metrics (BTV, mean tumor-to-background ratio [TBRmean], lesion SUVmean, and background SUVmean) were assessed with Pearson correlation and Bland–Altman analysis (bias, limits of agreement [LoA]). Automated and physician segmentation overlap was assessed with spatial and distance-based metrics. Results: BTV and TBRmean Pearson correlation was excellent for all time points (range, 0.92–0.98). In 2 patients with frontal lobe lesions, the network segmented the transverse sinus. Bland–Altman analysis showed network underestimation of physician-derived BTVs (absolute bias, 2.7 cm3, LoA, −13.1–18.5 cm3; relative bias, 27.9%, LoA, −95.3%–151.2%) and deviations for TBRmean were small (absolute bias, 0.03, LoA, −0.25–0.30; relative bias, 0.83%, LoA −14.27%–15.93%). Median Dice similarity coefficient, surface Dice similarity coefficient, Hausdorff distance, 95th percentile Hausdorff distance, and mean absolute surface distance were 0.83, 0.95, 10.94 mm, 3.62 mm, and 0.88 mm, respectively. Conclusion: Automated quantitative analysis was highly correlated with physician assessment; however, volume underestimation and erroneous segmentations may impact radiotherapy treatment planning and response assessment. Further training on a representative local dataset would likely be required for multicenter implementation.

O-(2-[18F]氟乙基)-l-酪氨酸PET自动分割网络在胶质母细胞瘤患者单中心前瞻性数据集上的外部独立验证
本研究的目的是对一组胶质母细胞瘤患者的O-(2-[18F]氟乙基)-l-酪氨酸([18F]FET) PET自动分割网络进行外部独立验证。方法:本研究纳入24例胶质母细胞瘤患者,共接受52次[18F]FET PET扫描(放疗前,n = 23;放疗前复测,n = 9;随访,n = 20)。生物肿瘤体积(BTV)划分由核医学专家和自动分割网络完成。采用Pearson相关性和Bland-Altman分析(偏倚、一致限[LoA])评估医师和自动定量指标(BTV、平均肿瘤与背景比[TBRmean]、病变SUVmean和背景SUVmean)。使用基于空间和距离的度量来评估自动分割和医生分割的重叠。结果:BTV与TBRmean Pearson相关性在各时间点均极好(范围0.92 ~ 0.98)。在2例额叶病变患者中,神经网络分割横窦。Bland-Altman分析显示,网络低估了医生来源的btv(绝对偏差,2.7 cm3, LoA,−13.1-18.5 cm3;相对偏倚,27.9%,LoA, - 95.3%-151.2%), TBRmean的偏差较小(绝对偏倚,0.03,LoA, - 0.25-0.30;相对偏倚0.83%,LoA为- 14.27% ~ 15.93%)。Dice相似系数中位数为0.83 mm,表面相似系数为0.95 mm, Hausdorff距离为10.94 mm,第95百分位Hausdorff距离为3.62 mm,平均绝对表面距离为0.88 mm。结论:自动化定量分析与医师评价高度相关;然而,体积低估和错误的分割可能会影响放射治疗计划和反应评估。对于多中心实现,可能需要对具有代表性的本地数据集进行进一步的训练。
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
自引率
0.00%
发文量
0
×
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