From the Department of Neuroradiology, University of Heidelberg Medical Center, Im Neuenheimer Feld 400, 69120 Heidelberg, Germany (P.K., S.B., O.E., M.B.); German Cancer Research Center (DKFZ), Department of Radiology, Heidelberg, Germany (D.B., H.P.S., A.R.); Department of Neurology, Medical University Innsbruck, Austria (M.N.); Department of Neuropathology, University of Heidelberg Medical Center, Heidelberg, Germany (A.K., A.v.D., D.C.); German Cancer Consortium (DKTK), Clinical Cooperation Unit Neuropathology, German Cancer Research Center (DKFZ), Heidelberg, Germany (A.K., A.v.D., D.C.); Division of Biostatistics, DKFZ, Heidelberg, Germany (M.S.); Neurology Clinic, University of Heidelberg Medical Center, Heidelberg, Germany (M.N., S.B., A.W., W.W.); Department of Radiation Oncology, University of Heidelberg Medical Center, Heidelberg, Germany (J.D.); Clinical Cooperation Unit Radiation Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany (J.D.); Division of Neurosurgical Research, Department of Neurosurgery, University of Heidelberg Medical Center, Heidelberg, Germany (C.H.M.); Department of Neurosurgery, University of Heidelberg Medical Center, Heidelberg, Germany (A.U.); Division of Pediatric Neurooncology, German Cancer Research Center (DKFZ), Heidelberg, Germany (D.J., S.P.); German Cancer Consortium (DKTK) Core Center Heidelberg, Heidelberg, Germany (D.J., S.P.); Department of Pediatric Oncology, Hematology and Immunology, Heidelberg University Hospital, Heidelberg, Germany (S.P.); and German Cancer Consortium (DKTK), Clinical Cooperation Unit Neurooncology, DKFZ, Heidelberg, Germany (W.W.).
Radiology. 2016 Dec;281(3):907-918. doi: 10.1148/radiol.2016161382. Epub 2016 Sep 16.
Purpose To evaluate the association of multiparametric and multiregional magnetic resonance (MR) imaging features with key molecular characteristics in patients with newly diagnosed glioblastoma. Materials and Methods Retrospective data evaluation was approved by the local ethics committee, and the requirement to obtain informed consent was waived. Preoperative MR imaging features were correlated with key molecular characteristics within a single-institution cohort of 152 patients with newly diagnosed glioblastoma. Preoperative MR imaging features (n = 31) included multiparametric (anatomic and diffusion-, perfusion-, and susceptibility-weighted images) and multiregional (contrast-enhancing regions and hyperintense regions at nonenhanced fluid-attenuated inversion recovery imaging) information with histogram quantification of tumor volumes, volume ratios, apparent diffusion coefficients, cerebral blood flow, cerebral blood volume, and intratumoral susceptibility signals. Molecular characteristics determined included global DNA methylation subgroups (eg, mesenchymal, RTK I "PGFRA," RTK II "classic"), MGMT promoter methylation status, and hallmark copy number variations (EGFR, PDGFRA, MDM4, and CDK4 amplification; PTEN, CDKN2A, NF1, and RB1 loss). Univariate analyses (voxel-lesion symptom mapping for tumor location, Wilcoxon test for all other MR imaging features) and machine learning models were applied to study the strength of association and discriminative value of MR imaging features for predicting underlying molecular characteristics. Results There was no tumor location predilection for any of the assessed molecular parameters (permutation-adjusted P > .05). Univariate imaging parameter associations were noted for EGFR amplification and CDKN2A loss, with both demonstrating increased Gaussian-normalized relative cerebral blood volume and Gaussian-normalized relative cerebral blood flow values (area under the receiver operating characteristics curve: 63%-69%, false discovery rate-adjusted P < .05). Subjecting all MR imaging features to machine learning-based classification enabled prediction of EGFR amplification status and the RTK II glioblastoma subgroup with a moderate, yet significantly greater, accuracy (63% for EGFR [P < .01], 61% for RTK II [P = .01]) than prediction by chance; prediction accuracy for all other molecular parameters was not significant. Conclusion The authors found associations between established MR imaging features and molecular characteristics, although not of sufficient strength to enable generation of machine learning classification models for reliable and clinically meaningful prediction of molecular characteristics in patients with glioblastoma. RSNA, 2016 Online supplemental material is available for this article.
目的 评估多参数和多区域磁共振（MR）成像特征与新诊断胶质母细胞瘤患者关键分子特征的相关性。
材料与方法 本回顾性数据分析经当地伦理委员会批准豁免了获得知情同意的要求。在单机构队列中对 152 例新诊断胶质母细胞瘤患者的术前 MR 成像特征与关键分子特征进行相关性分析。术前 MR 成像特征（n=31）包括多参数（解剖学和弥散、灌注和磁化率加权成像）和多区域（增强区域和非增强液体衰减反转恢复成像的高信号区域）信息，包括肿瘤体积、体积比、表观扩散系数、脑血流、脑血容量和瘤内磁化率信号的直方图定量。确定的分子特征包括全局 DNA 甲基化亚组（如间质、RTK I“PGFRA”、RTK II“经典”）、MGMT 启动子甲基化状态和标志性拷贝数变化（EGFR、PDGFRA、MDM4 和 CDK4 扩增；PTEN、CDKN2A、NF1 和 RB1 缺失）。应用单变量分析（肿瘤位置的体素病变症状映射，Wilcoxon 检验用于所有其他 MR 成像特征）和机器学习模型来研究 MR 成像特征预测潜在分子特征的关联强度和区分价值。
结果 评估的任何分子参数均无肿瘤位置倾向（置换调整 P＞.05）。EGFR 扩增和 CDKN2A 缺失与单变量成像参数相关，两者均显示出增加的高斯归一化相对脑血流和高斯归一化相对脑血流量值（受试者工作特征曲线下面积：63%-69%，错误发现率校正 P＜.05）。将所有 MR 成像特征进行基于机器学习的分类，可实现对 EGFR 扩增状态和 RTK II 胶质母细胞瘤亚组的中度、但具有显著更高准确性的预测（EGFR 为 63%[P＜.01]，RTK II 为 61%[P=.01]），而不是基于机会的预测；对所有其他分子参数的预测准确性则无显著差异。
结论 作者发现了既定的 MR 成像特征与分子特征之间的相关性，但相关性不够强，无法生成机器学习分类模型来可靠且有临床意义地预测胶质母细胞瘤患者的分子特征。
RSNA，2016
在线补充材料本文相关。
Neuroradiology. 2015-12
Biomedicines. 2025-8-12
Diagnostics (Basel). 2025-5-29
Diagnostics (Basel). 2025-5-14
Zotero 插件