Reproducibility of lung cancer radiomics features extracted from data-driven respiratory gating and free-breathing flow imaging in [18F]-FDG PET/CT.

IF 1.7 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING European Journal of Hybrid Imaging Pub Date : 2022-10-30 DOI:10.1186/s41824-022-00153-2
Daphné Faist, Mario Jreige, Valentin Oreiller, Marie Nicod Lalonde, Niklaus Schaefer, Adrien Depeursinge, John O Prior
{"title":"Reproducibility of lung cancer radiomics features extracted from data-driven respiratory gating and free-breathing flow imaging in [<sup>18</sup>F]-FDG PET/CT.","authors":"Daphné Faist, Mario Jreige, Valentin Oreiller, Marie Nicod Lalonde, Niklaus Schaefer, Adrien Depeursinge, John O Prior","doi":"10.1186/s41824-022-00153-2","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Quality and reproducibility of radiomics studies are essential requirements for the standardisation of radiomics models. As recent data-driven respiratory gating (DDG) [<sup>18</sup>F]-FDG has shown superior diagnostic performance in lung cancer, we evaluated the impact of DDG on the reproducibility of radiomics features derived from [<sup>18</sup>F]-FDG PET/CT in comparison to free-breathing flow (FB) imaging.</p><p><strong>Methods: </strong>Twenty four lung nodules from 20 patients were delineated. Radiomics features were derived on FB flow PET/CT and on the corresponding DDG reconstruction using the QuantImage v2 platform. Lin's concordance factor (C<sub>b</sub>) and the mean difference percentage (DIFF%) were calculated for each radiomics feature using the delineated nodules which were also classified by anatomical localisation and volume. Non-reproducible radiomics features were defined as having a bias correction factor C<sub>b</sub>  < 0.8 and/or a mean difference percentage DIFF% > 10.</p><p><strong>Results: </strong>In total 141 features were computed on each concordance analysis, 10 of which were non-reproducible on all pulmonary lesions. Those were first-order features from Laplacian of Gaussian (LoG)-filtered images (sigma = 1 mm): Energy, Kurtosis, Minimum, Range, Root Mean Squared, Skewness and Variance; Texture features from Gray Level Cooccurence Matrix (GLCM): Cluster Prominence and Difference Variance; First-order Standardised Uptake Value (SUV) feature: Kurtosis. Pulmonary lesions located in the superior lobes had only stable radiomics features, the ones from the lower parts had 25 non-reproducible radiomics features. Pulmonary lesions with a greater size (defined as long axis length > median) showed a higher reproducibility (9 non-reproducible features) than smaller ones (20 non-reproducible features).</p><p><strong>Conclusion: </strong>Calculated on all pulmonary lesions, 131 out of 141 radiomics features can be used interchangeably between DDG and FB PET/CT acquisitions. Radiomics features derived from pulmonary lesions located inferior to the superior lobes are subject to greater variability as well as pulmonary lesions of smaller size.</p>","PeriodicalId":36160,"journal":{"name":"European Journal of Hybrid Imaging","volume":" ","pages":"33"},"PeriodicalIF":1.7000,"publicationDate":"2022-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9617997/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Hybrid Imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s41824-022-00153-2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Quality and reproducibility of radiomics studies are essential requirements for the standardisation of radiomics models. As recent data-driven respiratory gating (DDG) [18F]-FDG has shown superior diagnostic performance in lung cancer, we evaluated the impact of DDG on the reproducibility of radiomics features derived from [18F]-FDG PET/CT in comparison to free-breathing flow (FB) imaging.

Methods: Twenty four lung nodules from 20 patients were delineated. Radiomics features were derived on FB flow PET/CT and on the corresponding DDG reconstruction using the QuantImage v2 platform. Lin's concordance factor (Cb) and the mean difference percentage (DIFF%) were calculated for each radiomics feature using the delineated nodules which were also classified by anatomical localisation and volume. Non-reproducible radiomics features were defined as having a bias correction factor Cb  < 0.8 and/or a mean difference percentage DIFF% > 10.

Results: In total 141 features were computed on each concordance analysis, 10 of which were non-reproducible on all pulmonary lesions. Those were first-order features from Laplacian of Gaussian (LoG)-filtered images (sigma = 1 mm): Energy, Kurtosis, Minimum, Range, Root Mean Squared, Skewness and Variance; Texture features from Gray Level Cooccurence Matrix (GLCM): Cluster Prominence and Difference Variance; First-order Standardised Uptake Value (SUV) feature: Kurtosis. Pulmonary lesions located in the superior lobes had only stable radiomics features, the ones from the lower parts had 25 non-reproducible radiomics features. Pulmonary lesions with a greater size (defined as long axis length > median) showed a higher reproducibility (9 non-reproducible features) than smaller ones (20 non-reproducible features).

Conclusion: Calculated on all pulmonary lesions, 131 out of 141 radiomics features can be used interchangeably between DDG and FB PET/CT acquisitions. Radiomics features derived from pulmonary lesions located inferior to the superior lobes are subject to greater variability as well as pulmonary lesions of smaller size.

Abstract Image

Abstract Image

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
从[18F]-FDG PET/CT 的数据驱动呼吸门控和自由呼吸血流成像中提取的肺癌放射组学特征的再现性。
背景:放射组学研究的质量和可重复性是放射组学模型标准化的基本要求。由于最近数据驱动呼吸门控(DDG)[18F]-FDG 在肺癌中显示出了卓越的诊断性能,我们评估了 DDG 与自由呼吸血流(FB)成像相比对[18F]-FDG PET/CT 得出的放射组学特征可重复性的影响:方法:对 20 名患者的 24 个肺结节进行了划定。方法:对 20 名患者的 24 个肺部结节进行划定,并使用 QuantImage v2 平台在 FB 流式 PET/CT 和相应的 DDG 重建上得出放射组学特征。利用划定的结节计算每个放射组学特征的林氏一致性因子(Cb)和平均差异百分比(DIFF%),并按解剖定位和体积对结节进行分类。结果:每次一致性分析共计算出 141 个特征,其中 10 个特征在所有肺部病变中均不可再现。这些特征来自高斯拉普拉斯(LoG)滤波图像的一阶特征(sigma = 1 mm):能量、峰度、最小值、范围、均方根、偏度和方差;灰度共轭矩阵(GLCM)的纹理特征:簇突出度和差异方差;一阶标准化摄取值(SUV)特征:峰度。位于上叶的肺部病变只有稳定的放射组学特征,而位于下叶的病变有 25 个不可再现的放射组学特征。肺部病变的大小(定义为长轴长度大于中位数)比小病变(20 个不可再现特征)显示出更高的再现性(9 个不可再现特征):根据所有肺部病变计算,141 个放射组学特征中有 131 个可在 DDG 和 FB PET/CT 采集中互换使用。位于上叶下部的肺部病变和体积较小的肺部病变的放射组学特征的可变性较大。
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
European Journal of Hybrid Imaging
European Journal of Hybrid Imaging Computer Science-Computer Science (miscellaneous)
CiteScore
3.40
自引率
0.00%
发文量
29
审稿时长
17 weeks
期刊最新文献
Phosphaturic mesenchymal tumor demonstrated by 68Ga-DOTATATE PET/CT in a patient: a case report Carcinoid crisis in Lutetium-177-Dotatate therapy of neuroendocrine tumors: an overview of pathophysiology, risk factors, recognition, and treatment Four-dimensional computed tomography as first-line imaging in primary hyperparathyroidism, a retrospective comparison to conventional imaging in a predominantly single adenoma population Clinical value of semi-quantitative parameters in 68Ga-DOTANOC PET/CT in treatment and diagnostics of cranial meningioma in a single-center retrospective analysis Cardiac transplant rejection assessment with 18F-FDG PET-CT: initial single-centre experience for diagnosis and management
×
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