• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于 MRI 和 18F-FDG-PET 影像组学特征鉴别单发脑转移瘤与胶质母细胞瘤及多模型联合应用。

Differentiating solitary brain metastases from glioblastoma by radiomics features derived from MRI and 18F-FDG-PET and the combined application of multiple models.

机构信息

School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu, China.

College of Computer & Information Science, Southwest University, Chongqing, China.

出版信息

Sci Rep. 2022 Apr 6;12(1):5722. doi: 10.1038/s41598-022-09803-8.

DOI:10.1038/s41598-022-09803-8
PMID:35388124
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8986767/
Abstract

This study aimed to explore the ability of radiomics derived from both MRI and 18F-fluorodeoxyglucose positron emission tomography (18F-FDG-PET) images to differentiate glioblastoma (GBM) from solitary brain metastases (SBM) and to investigate the combined application of multiple models. The imaging data of 100 patients with brain tumours (50 GBMs and 50 SBMs) were retrospectively analysed. Three model sets were built on MRI, 18F-FDG-PET, and MRI combined with 18F-FDG-PET using five feature selection methods and five classification algorithms. The model set with the highest average AUC value was selected, in which some models were selected and divided into Groups A, B, and C. Individual and joint voting predictions were performed in each group for the entire data. The model set based on MRI combined with 18F-FDG-PET had the highest average AUC compared with isolated MRI or 18F-FDG-PET. Joint voting prediction showed better performance than the individual prediction when all models reached an agreement. In conclusion, radiomics derived from MRI and 18F-FDG-PET could help differentiate GBM from SBM preoperatively. The combined application of multiple models can provide greater benefits.

摘要

本研究旨在探索基于 MRI 和 18F-氟脱氧葡萄糖正电子发射断层扫描（18F-FDG-PET）图像的放射组学在鉴别胶质母细胞瘤（GBM）和单发脑转移瘤（SBM）方面的能力，并探讨多种模型的联合应用。回顾性分析了 100 名脑肿瘤患者的影像数据（50 例 GBM 和 50 例 SBM）。使用五种特征选择方法和五种分类算法，在 MRI、18F-FDG-PET 和 MRI 联合 18F-FDG-PET 上分别构建了三个模型集。选择平均 AUC 值最高的模型集，其中一些模型被选入并分为 A、B 和 C 组。对每组的全部数据进行个体和联合投票预测。与单独的 MRI 或 18F-FDG-PET 相比，基于 MRI 联合 18F-FDG-PET 的模型集具有最高的平均 AUC。当所有模型达成一致时，联合投票预测的表现优于个体预测。总之，MRI 和 18F-FDG-PET 衍生的放射组学可帮助术前鉴别 GBM 和 SBM。多模型的联合应用可以带来更大的益处。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/edda5ff81151/41598_2022_9803_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/24d7a88a7ab8/41598_2022_9803_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/19bbc6ebca86/41598_2022_9803_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/d139e1dcc3f6/41598_2022_9803_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/51929491e40a/41598_2022_9803_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/265f2ebf8d52/41598_2022_9803_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/edda5ff81151/41598_2022_9803_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/24d7a88a7ab8/41598_2022_9803_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/19bbc6ebca86/41598_2022_9803_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/d139e1dcc3f6/41598_2022_9803_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/51929491e40a/41598_2022_9803_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/265f2ebf8d52/41598_2022_9803_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8301/8986767/edda5ff81151/41598_2022_9803_Fig6_HTML.jpg

相似文献

1
Differentiating solitary brain metastases from glioblastoma by radiomics features derived from MRI and 18F-FDG-PET and the combined application of multiple models.基于 MRI 和 18F-FDG-PET 影像组学特征鉴别单发脑转移瘤与胶质母细胞瘤及多模型联合应用。
Sci Rep. 2022 Apr 6;12(1):5722. doi: 10.1038/s41598-022-09803-8.
2
An Integrated Radiomics Model Incorporating Diffusion-Weighted Imaging and F-FDG PET Imaging Improves the Performance of Differentiating Glioblastoma From Solitary Brain Metastases.一种整合扩散加权成像和F-FDG PET成像的放射组学模型可提高鉴别胶质母细胞瘤与孤立性脑转移瘤的性能。
Front Oncol. 2021 Aug 30;11:732704. doi: 10.3389/fonc.2021.732704. eCollection 2021.
3
[F]Fludarabine-PET as a promising tool for differentiating CNS lymphoma and glioblastoma: Comparative analysis with [F]FDG in human xenograft models.氟达拉滨-PET 作为区分中枢神经系统淋巴瘤和胶质母细胞瘤的有前途的工具：与 [F]FDG 在人异种移植模型中的比较分析。
Theranostics. 2018 Aug 10;8(16):4563-4573. doi: 10.7150/thno.26754. eCollection 2018.
4
F-FDG-PET-based radiomics features to distinguish primary central nervous system lymphoma from glioblastoma.基于 F-FDG-PET 的影像组学特征可用于区分原发性中枢神经系统淋巴瘤和胶质母细胞瘤。
Neuroimage Clin. 2019;23:101912. doi: 10.1016/j.nicl.2019.101912. Epub 2019 Jun 27.
5
Estimation of Tumor Volumes by 11C-MeAIB and 18F-FDG PET in an Orthotopic Glioblastoma Rat Model.在原位胶质母细胞瘤大鼠模型中通过11C-甲硫氨酸和18F-氟代脱氧葡萄糖PET估计肿瘤体积
J Nucl Med. 2015 Oct;56(10):1562-8. doi: 10.2967/jnumed.115.162511. Epub 2015 Jul 30.
6
Interchangeability of radiomic features between [18F]-FDG PET/CT and [18F]-FDG PET/MR.基于[18F]-FDG 的 PET/CT 与 PET/MR 影像中影像组学特征的可互换性。
Med Phys. 2019 Apr;46(4):1677-1685. doi: 10.1002/mp.13422. Epub 2019 Feb 22.
7
Potential feature exploration and model development based on 18F-FDG PET/CT images for differentiating benign and malignant lung lesions.基于 18F-FDG PET/CT 图像的良恶性肺病变鉴别中潜在特征的探索和模型开发。
Eur J Radiol. 2019 Dec;121:108735. doi: 10.1016/j.ejrad.2019.108735. Epub 2019 Nov 6.
8
Is integrated 18F-FDG PET/MRI superior to 18F-FDG PET/CT in the differentiation of incidental tracer uptake in the head and neck area?在头颈部区域偶然发现的示踪剂摄取的鉴别诊断中，一体化18F-FDG PET/MRI是否优于18F-FDG PET/CT？
Diagn Interv Radiol. 2017 Mar-Apr;23(2):127-132. doi: 10.5152/dir.2016.15610.
9
Role of FDG-PET/MRI, FDG-PET/CT, and Dynamic Susceptibility Contrast Perfusion MRI in Differentiating Radiation Necrosis from Tumor Recurrence in Glioblastomas.氟代脱氧葡萄糖正电子发射断层扫描/磁共振成像（FDG-PET/MRI）、氟代脱氧葡萄糖正电子发射断层扫描/计算机断层扫描（FDG-PET/CT）及动态磁敏感对比灌注磁共振成像在鉴别胶质母细胞瘤放射性坏死与肿瘤复发中的作用
J Neuroimaging. 2018 Jan;28(1):118-125. doi: 10.1111/jon.12460. Epub 2017 Jul 18.
10
18F-FDG PET/CT and whole-body MRI diagnostic performance in M staging for non-small cell lung cancer: a systematic review and meta-analysis.18F-FDG PET/CT 和全身 MRI 在非小细胞肺癌 M 分期中的诊断性能：系统评价和荟萃分析。
Eur Radiol. 2020 Jul;30(7):3641-3649. doi: 10.1007/s00330-020-06703-1. Epub 2020 Mar 3.

引用本文的文献

1
Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases.定量生理磁共振成像结合特征工程用于开发基于机器学习的预测模型以区分胶质母细胞瘤与单发脑转移瘤
Diagnostics (Basel). 2024 Dec 27;15(1):38. doi: 10.3390/diagnostics15010038.
2
High-performance presurgical differentiation of glioblastoma and metastasis by means of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics.通过多参数神经丝取向分散和密度成像（NODDI）放射组学对胶质母细胞瘤和转移瘤进行高性能术前鉴别。
Eur Radiol. 2024 Oct;34(10):6616-6628. doi: 10.1007/s00330-024-10686-8. Epub 2024 Mar 15.
3

本文引用的文献

1
An Integrated Radiomics Model Incorporating Diffusion-Weighted Imaging and F-FDG PET Imaging Improves the Performance of Differentiating Glioblastoma From Solitary Brain Metastases.一种整合扩散加权成像和F-FDG PET成像的放射组学模型可提高鉴别胶质母细胞瘤与孤立性脑转移瘤的性能。
Front Oncol. 2021 Aug 30;11:732704. doi: 10.3389/fonc.2021.732704. eCollection 2021.
2
A radiomics-based model to differentiate glioblastoma from solitary brain metastases.基于放射组学的模型，用于区分脑胶质母细胞瘤与单发脑转移瘤。
Clin Radiol. 2021 Aug;76(8):629.e11-629.e18. doi: 10.1016/j.crad.2021.04.012. Epub 2021 Jun 4.
3
Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation.
Harnessing imaging biomarkers for glioblastoma metastasis diagnosis: a correspondence.
利用成像生物标志物进行胶质母细胞瘤转移诊断：一封通信
J Neurooncol. 2024 Apr;167(2):365-367. doi: 10.1007/s11060-024-04606-5. Epub 2024 Feb 23.
4
Artificial Intelligence Technologies in the Microsurgical Operating Room (Review).人工智能技术在微创手术手术室中的应用（综述）。
Sovrem Tekhnologii Med. 2023;15(2):86-94. doi: 10.17691/stm2023.15.2.08. Epub 2023 Mar 29.
5
Radiomics in Determining Tumor-to-Normal Brain SUV Ratio Based on C-Methionine PET/CT in Glioblastoma.脑胶质母细胞瘤 C-蛋氨酸 PET/CT 基于影像组学的肿瘤与正常脑 SUV 比值测定
Sovrem Tekhnologii Med. 2023;15(1):5-11. doi: 10.17691/stm2023.15.1.01. Epub 2023 Jan 28.
6
Bibliometric research on the developments of artificial intelligence in radiomics toward nervous system diseases.关于人工智能在神经系统疾病放射组学发展方面的文献计量研究。
Front Neurol. 2023 Jun 9;14:1171167. doi: 10.3389/fneur.2023.1171167. eCollection 2023.
7
The Role of Molecular Imaging in Patients with Brain Metastases: A Literature Review.分子成像在脑转移瘤患者中的作用：文献综述
Cancers (Basel). 2023 Apr 6;15(7):2184. doi: 10.3390/cancers15072184.
8
Improving the Classification of PCNSL and Brain Metastases by Developing a Machine Learning Model Based on F-FDG PET.通过开发基于F-FDG PET的机器学习模型来改进原发性中枢神经系统淋巴瘤和脑转移瘤的分类
J Pers Med. 2023 Mar 17;13(3):539. doi: 10.3390/jpm13030539.
9
Differentiation of Glioblastoma and Brain Metastases by MRI-Based Oxygen Metabolomic Radiomics and Deep Learning.基于MRI的氧代谢组学放射组学和深度学习对胶质母细胞瘤和脑转移瘤的鉴别
Metabolites. 2022 Dec 14;12(12):1264. doi: 10.3390/metabo12121264.
10
Towards updated understanding of brain metastasis.迈向对脑转移的更新理解。
Am J Cancer Res. 2022 Sep 15;12(9):4290-4311. eCollection 2022.
深度学习利用放射组学特征区分胶质母细胞瘤与单发脑转移瘤的稳健性能：模型的建立与验证。
Sci Rep. 2020 Jul 21;10(1):12110. doi: 10.1038/s41598-020-68980-6.
4
Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach.基于 MRI 纹理分析的放射组学方法对胶质母细胞瘤和脑转移瘤的鉴别诊断。
Phys Med. 2020 Aug;76:44-54. doi: 10.1016/j.ejmp.2020.06.016. Epub 2020 Jun 24.
5
Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region-derived radiomic features and multiple classifiers.利用瘤周水肿区衍生的放射组学特征和多分类器对幕上单发脑转移瘤和胶质母细胞瘤进行鉴别。
Eur Radiol. 2020 May;30(5):3015-3022. doi: 10.1007/s00330-019-06460-w. Epub 2020 Jan 31.
6
F-FDG-PET-based radiomics features to distinguish primary central nervous system lymphoma from glioblastoma.基于 F-FDG-PET 的影像组学特征可用于区分原发性中枢神经系统淋巴瘤和胶质母细胞瘤。
Neuroimage Clin. 2019;23:101912. doi: 10.1016/j.nicl.2019.101912. Epub 2019 Jun 27.
7
Differentiation of glioblastoma from solitary brain metastases using radiomic machine-learning classifiers.使用放射组学机器学习分类器对胶质母细胞瘤与单发脑转移瘤进行鉴别。
Cancer Lett. 2019 Jun 1;451:128-135. doi: 10.1016/j.canlet.2019.02.054. Epub 2019 Mar 13.
8
Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis.使用放射组学分析对胶质母细胞瘤、脑转移瘤和亚型进行区分。
J Magn Reson Imaging. 2019 Aug;50(2):519-528. doi: 10.1002/jmri.26643. Epub 2019 Jan 11.
9
How good is collaboration between maternity service providers in the Netherlands?荷兰产科服务提供者之间的合作情况如何？
J Multidiscip Healthc. 2018 Dec 24;12:21-30. doi: 10.2147/JMDH.S179811. eCollection 2019.
10
Multi-disciplinary and shared decision-making approach in the management of organ-confined prostate cancer.器官局限性前列腺癌管理中的多学科与共同决策方法
Arab J Urol. 2018 Aug 6;16(4):367-377. doi: 10.1016/j.aju.2018.06.008. eCollection 2018 Dec.