• 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

利用多序列磁共振成像（MRI）的影像组学特征对胶质瘤进行分级

Grading of Gliomas by Using Radiomic Features on Multiple Magnetic Resonance Imaging (MRI) Sequences.

作者信息

Qin Jiang-Bo, Liu Zhenyu, Zhang Hui, Shen Chen, Wang Xiao-Chun, Tan Yan, Wang Shuo, Wu Xiao-Feng, Tian Jie

机构信息

Department of Radiology, First Clinical Medical College, Shanxi Medical University, Taiyuan, Shanxi, China (mainland).

Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China (mainland).

出版信息

Med Sci Monit. 2017 May 7;23:2168-2178. doi: 10.12659/msm.901270.

DOI:10.12659/msm.901270
PMID:28478462
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5436423/
Abstract

BACKGROUND Gliomas are the most common primary brain neoplasms. Misdiagnosis occurs in glioma grading due to an overlap in conventional MRI manifestations. The aim of the present study was to evaluate the power of radiomic features based on multiple MRI sequences - T2-Weighted-Imaging-FLAIR (FLAIR), T1-Weighted-Imaging-Contrast-Enhanced (T1-CE), and Apparent Diffusion Coefficient (ADC) map - in glioma grading, and to improve the power of glioma grading by combining features. MATERIAL AND METHODS Sixty-six patients with histopathologically proven gliomas underwent T2-FLAIR and T1WI-CE sequence scanning with some patients (n=63) also undergoing DWI scanning. A total of 114 radiomic features were derived with radiomic methods by using in-house software. All radiomic features were compared between high-grade gliomas (HGGs) and low-grade gliomas (LGGs). Features with significant statistical differences were selected for receiver operating characteristic (ROC) curve analysis. The relationships between significantly different radiomic features and glial fibrillary acidic protein (GFAP) expression were evaluated. RESULTS A total of 8 radiomic features from 3 MRI sequences displayed significant differences between LGGs and HGGs. FLAIR GLCM Cluster Shade, T1-CE GLCM Entropy, and ADC GLCM Homogeneity were the best features to use in differentiating LGGs and HGGs in each MRI sequence. The combined feature was best able to differentiate LGGs and HGGs, which improved the accuracy of glioma grading compared to the above features in each MRI sequence. A significant correlation was found between GFAP and T1-CE GLCM Entropy, as well as between GFAP and ADC GLCM Homogeneity. CONCLUSIONS The combined radiomic feature had the highest efficacy in distinguishing LGGs from HGGs.

摘要

背景

胶质瘤是最常见的原发性脑肿瘤。由于传统磁共振成像（MRI）表现存在重叠，胶质瘤分级中会出现误诊。本研究的目的是评估基于多个MRI序列——液体衰减反转恢复序列（FLAIR）、T1加权增强成像（T1-CE）和表观扩散系数（ADC）图——的影像组学特征在胶质瘤分级中的效能，并通过联合特征提高胶质瘤分级的效能。

材料与方法

66例经组织病理学证实的胶质瘤患者接受了T2-FLAIR和T1WI-CE序列扫描，部分患者（n = 63）还接受了弥散加权成像（DWI）扫描。使用内部软件通过影像组学方法提取了总共114个影像组学特征。比较了高级别胶质瘤（HGG）和低级别胶质瘤（LGG）之间的所有影像组学特征。选择具有显著统计学差异的特征进行受试者操作特征（ROC）曲线分析。评估了显著不同的影像组学特征与胶质纤维酸性蛋白（GFAP）表达之间的关系。

结果

来自3个MRI序列的总共8个影像组学特征在LGG和HGG之间显示出显著差异。FLAIR的灰度共生矩阵（GLCM）簇阴影、T1-CE的GLCM熵和ADC的GLCM均匀性是每个MRI序列中区分LGG和HGG的最佳特征。联合特征最能区分LGG和HGG，与每个MRI序列中的上述特征相比，提高了胶质瘤分级的准确性。发现GFAP与T1-CE的GLCM熵以及GFAP与ADC的GLCM均匀性之间存在显著相关性。

结论

联合影像组学特征在区分LGG和HGG方面具有最高的效能。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/2934e706d7a6/medscimonit-23-2168-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/848e9761ad5d/medscimonit-23-2168-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/0613af2c3227/medscimonit-23-2168-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/fd523f888a32/medscimonit-23-2168-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/004c1e596bc4/medscimonit-23-2168-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/47b29ef73754/medscimonit-23-2168-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/2934e706d7a6/medscimonit-23-2168-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/848e9761ad5d/medscimonit-23-2168-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/0613af2c3227/medscimonit-23-2168-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/fd523f888a32/medscimonit-23-2168-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/004c1e596bc4/medscimonit-23-2168-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/47b29ef73754/medscimonit-23-2168-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b1f/5436423/2934e706d7a6/medscimonit-23-2168-g006.jpg

相似文献

1
Grading of Gliomas by Using Radiomic Features on Multiple Magnetic Resonance Imaging (MRI) Sequences.利用多序列磁共振成像（MRI）的影像组学特征对胶质瘤进行分级
Med Sci Monit. 2017 May 7;23:2168-2178. doi: 10.12659/msm.901270.
2
Grading diffuse gliomas without intense contrast enhancement by amide proton transfer MR imaging: comparisons with diffusion- and perfusion-weighted imaging.通过酰胺质子转移磁共振成像对无强化的弥漫性胶质瘤进行分级：与扩散加权成像和灌注加权成像的比较
Eur Radiol. 2017 Feb;27(2):578-588. doi: 10.1007/s00330-016-4328-0. Epub 2016 Mar 22.
3
Investigated diagnostic value of synthetic relaxometry, three-dimensional pseudo-continuous arterial spin labelling and diffusion-weighted imaging in the grading of glioma.研究综合弛豫测量法、三维伪连续动脉自旋标记和扩散加权成像在胶质瘤分级中的诊断价值。
Magn Reson Imaging. 2022 Feb;86:20-27. doi: 10.1016/j.mri.2021.11.006. Epub 2021 Nov 20.
4
Grading of Glioma: combined diagnostic value of amide proton transfer weighted, arterial spin labeling and diffusion weighted magnetic resonance imaging.胶质瘤分级：酰胺质子转移加权成像、动脉自旋标记和扩散加权磁共振成像的联合诊断价值
BMC Med Imaging. 2020 May 14;20(1):50. doi: 10.1186/s12880-020-00450-x.
5
Voxel-based clustered imaging by multiparameter diffusion tensor images for glioma grading.基于体素的多参数弥散张量成像在胶质瘤分级中的聚类成像。
Neuroimage Clin. 2014 Aug 7;5:396-407. doi: 10.1016/j.nicl.2014.08.001. eCollection 2014.
6
Radiomics strategy for glioma grading using texture features from multiparametric MRI.基于多参数 MRI 纹理特征的脑胶质瘤分级放射组学策略。
J Magn Reson Imaging. 2018 Dec;48(6):1518-1528. doi: 10.1002/jmri.26010. Epub 2018 Mar 23.
7
Radiomics-Based Machine Learning Classification for Glioma Grading Using Diffusion- and Perfusion-Weighted Magnetic Resonance Imaging.基于放射组学的机器学习在基于弥散和灌注加权磁共振成像的脑胶质瘤分级中的分类。
J Comput Assist Tomogr. 2021;45(4):606-613. doi: 10.1097/RCT.0000000000001180.
8
Intergrating conventional MRI, texture analysis of dynamic contrast-enhanced MRI, and susceptibility weighted imaging for glioma grading.整合传统磁共振成像、动态对比增强磁共振成像的纹理分析以及磁敏感加权成像用于胶质瘤分级。
Acta Radiol. 2019 Jun;60(6):777-787. doi: 10.1177/0284185118801127. Epub 2018 Sep 23.
9
Diagnostic value of apparent diffusion coefficient in differentiating between high-grade gliomas and brain metastases.表观扩散系数在鉴别高级别胶质瘤与脑转移瘤中的诊断价值
Acta Radiol. 2018 May;59(5):599-605. doi: 10.1177/0284185117727787. Epub 2017 Aug 23.
10
Glioma grading prediction using multiparametric magnetic resonance imaging-based radiomics combined with proton magnetic resonance spectroscopy and diffusion tensor imaging.基于多参数磁共振成像的放射组学与质子磁共振波谱和弥散张量成像联合预测脑胶质瘤分级。
Med Phys. 2022 Jul;49(7):4419-4429. doi: 10.1002/mp.15648. Epub 2022 Apr 18.

引用本文的文献

1
The Diagnostic Value of Susceptibility-Weighted Imaging in Preoperative Grading of Glial Tumors.磁敏感加权成像在胶质肿瘤术前分级中的诊断价值
Cureus. 2025 Aug 10;17(8):e89757. doi: 10.7759/cureus.89757. eCollection 2025 Aug.
2
Enhanced magnetic resonance imaging-based radiomics predicts CD40LG expression and survival in high-grade gliomas: a retrospective study.基于增强磁共振成像的影像组学预测高级别胶质瘤中CD40LG的表达及生存情况：一项回顾性研究
Discov Oncol. 2025 May 30;16(1):962. doi: 10.1007/s12672-025-02721-x.
3
FLAIR-based radiomics signature from brain-tumor interface for early prediction of response to EGFR-TKI therapy in NSCLC patients with brain metastasis.

本文引用的文献

1
Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer.针对肺癌和头颈癌的放射组学特征簇及预后特征
Sci Rep. 2015 Jun 5;5:11044. doi: 10.1038/srep11044.
2
CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma.基于CT的影像组学特征预测肺腺癌的远处转移。
Radiother Oncol. 2015 Mar;114(3):345-50. doi: 10.1016/j.radonc.2015.02.015. Epub 2015 Mar 4.
3
ADC texture--an imaging biomarker for high-grade glioma?表观扩散系数纹理——高级别胶质瘤的一种成像生物标志物？
基于液体衰减反转恢复序列（FLAIR）的脑肿瘤界面放射组学特征，用于早期预测非小细胞肺癌脑转移患者对表皮生长因子受体酪氨酸激酶抑制剂（EGFR-TKI）治疗的反应
Front Cell Dev Biol. 2025 May 14;13:1525989. doi: 10.3389/fcell.2025.1525989. eCollection 2025.
4
Predicting postoperative recurrence and survival in glioma patients using enhanced MRI-based delta habitat radiomics: an 8-year retrospective pilot study.使用基于增强MRI的δ栖息地放射组学预测胶质瘤患者的术后复发和生存：一项8年的回顾性初步研究。
World J Surg Oncol. 2025 Mar 28;23(1):104. doi: 10.1186/s12957-025-03760-y.
5
Simplifying Radiomics Workflow for Predicting Grade of Glioma: An Approach for Rapid and Reproducible Radiomics.简化用于预测胶质瘤分级的放射组学工作流程：一种实现快速且可重复的放射组学方法
J Biomed Phys Eng. 2025 Feb 1;15(1):27-36. doi: 10.31661/jbpe.v0i0.2208-1525. eCollection 2025 Feb.
6
Radiomics Analysis of Quantitative Maps from Synthetic MRI for Predicting Grades and Molecular Subtypes of Diffuse Gliomas.基于合成磁共振成像定量图谱的放射组学分析用于预测弥漫性胶质瘤的分级和分子亚型
Clin Neuroradiol. 2024 Dec;34(4):817-826. doi: 10.1007/s00062-024-01421-3. Epub 2024 Jun 10.
7
Medical image foundation models in assisting diagnosis of brain tumors: a pilot study.医学影像基础模型在脑肿瘤辅助诊断中的应用：一项初步研究。
Eur Radiol. 2024 Oct;34(10):6667-6679. doi: 10.1007/s00330-024-10728-1. Epub 2024 Apr 16.
8
A clinically relevant computed tomography (CT) radiomics strategy for intracranial rodent brain tumour monitoring.一种用于颅内啮齿动物脑肿瘤监测的临床相关 CT 放射组学策略。
Sci Rep. 2024 Feb 1;14(1):2720. doi: 10.1038/s41598-024-52960-1.
9
Texture feature analysis of MRI-ADC images to differentiate glioma grades using machine learning techniques.利用机器学习技术对 MRI-ADC 图像的纹理特征进行分析，以区分胶质瘤的级别。
Sci Rep. 2023 Sep 22;13(1):15772. doi: 10.1038/s41598-023-41353-5.
10
Using radiomics based on multicenter magnetic resonance images to predict isocitrate dehydrogenase mutation status of gliomas.利用基于多中心磁共振图像的影像组学预测胶质瘤异柠檬酸脱氢酶突变状态。
Quant Imaging Med Surg. 2023 Apr 1;13(4):2143-2155. doi: 10.21037/qims-22-836. Epub 2023 Mar 2.
Med Phys. 2014 Oct;41(10):101903. doi: 10.1118/1.4894812.
4
Glioma: application of whole-tumor texture analysis of diffusion-weighted imaging for the evaluation of tumor heterogeneity.胶质瘤：扩散加权成像全肿瘤纹理分析在评估肿瘤异质性中的应用
PLoS One. 2014 Sep 30;9(9):e108335. doi: 10.1371/journal.pone.0108335. eCollection 2014.
5
Glioma grading using apparent diffusion coefficient map: application of histogram analysis based on automatic segmentation.基于自动分割的直方图分析在利用表观扩散系数图进行胶质瘤分级中的应用
NMR Biomed. 2014 Sep;27(9):1046-52. doi: 10.1002/nbm.3153. Epub 2014 Jul 7.
6
Robust Radiomics feature quantification using semiautomatic volumetric segmentation.使用半自动体积分割进行稳健的放射组学特征量化。
PLoS One. 2014 Jul 15;9(7):e102107. doi: 10.1371/journal.pone.0102107. eCollection 2014.
7
Combined value of susceptibility-weighted and perfusion-weighted imaging in assessing who grade for brain astrocytomas.susceptibility加权成像与灌注加权成像联合评估脑星形细胞瘤WHO分级的价值
J Magn Reson Imaging. 2014 Jun;39(6):1569-74. doi: 10.1002/jmri.24312.
8
Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.采用定量放射组学方法通过无创成像解码肿瘤表型。
Nat Commun. 2014 Jun 3;5:4006. doi: 10.1038/ncomms5006.
9
Malignant gliomas: current perspectives in diagnosis, treatment, and early response assessment using advanced quantitative imaging methods.恶性胶质瘤：使用先进定量成像方法进行诊断、治疗及早期反应评估的当前观点
Cancer Manag Res. 2014 Mar 24;6:149-70. doi: 10.2147/CMAR.S54726. eCollection 2014.
10
Metrics and textural features of MRI diffusion to improve classification of pediatric posterior fossa tumors.磁共振成像扩散的指标和纹理特征以改善小儿后颅窝肿瘤的分类
AJNR Am J Neuroradiol. 2014 May;35(5):1009-15. doi: 10.3174/ajnr.A3784. Epub 2013 Dec 5.