From the Department of Radiology (C.J.P.), Yonsei University College of Medicine, Seoul, Korea.
Department of Radiology (K.H., H.K., S.S.A., Y.W.P., S.-K.L.), Research Institute of Radiological Sciences, Center for Clinical Imaging Data Science.
AJNR Am J Neuroradiol. 2021 Mar;42(3):448-456. doi: 10.3174/ajnr.A6983. Epub 2021 Jan 28.
() wild-type lower-grade gliomas (histologic grades II and III) with () amplification or () promoter mutation are reported to behave similar to glioblastoma. We aimed to evaluate whether MR imaging features could identify a subset of wild-type lower-grade gliomas that carry molecular features of glioblastoma.
In this multi-institutional retrospective study, pathologically confirmed wild-type lower-grade gliomas from 2 tertiary institutions and The Cancer Genome Atlas constituted the training set (institution 1 and The Cancer Genome Atlas, 64 patients) and the independent test set (institution 2, 57 patients). Preoperative MRIs were analyzed using the Visually AcceSAble Rembrandt Images and radiomics. The molecular glioblastoma status was determined on the basis of the presence of amplification and promoter mutation. Molecular glioblastoma was present in 73.4% and 56.1% in the training and test sets, respectively. Models using clinical, Visually AcceSAble Rembrandt Images, and radiomic features were built to predict the molecular glioblastoma status in the training set; then they were validated in the test set.
In the test set, a model using both Visually AcceSAble Rembrandt Images and radiomic features showed superior predictive performance (area under the curve = 0.854) than that with only clinical features or Visually AcceSAble Rembrandt Images (areas under the curve = 0.514 and 0.648, respectively; < . 001, both). When both Visually AcceSAble Rembrandt Images and radiomics were added to clinical features, the predictive performance significantly increased (areas under the curve = 0.514 versus 0.863, < .001).
MR imaging features integrated with machine learning classifiers may predict a subset of wild-type lower-grade gliomas that carry molecular features of glioblastoma.
（）野生型低级别胶质瘤（组织学等级 II 和 III）存在（）扩增或（）启动子突变，其表现类似于胶质母细胞瘤。我们旨在评估磁共振成像（MRI）特征是否可以识别出具有胶质母细胞瘤分子特征的野生型低级别胶质瘤亚组。
在这项多机构回顾性研究中，来自 2 个三级机构和癌症基因组图谱（The Cancer Genome Atlas）的经病理证实的野生型低级别胶质瘤构成了训练集（机构 1 和癌症基因组图谱，64 例患者）和独立测试集（机构 2，57 例患者）。使用可视可访问的 Rembrandt 图像和放射组学分析术前 MRI。根据存在扩增和启动子突变来确定分子胶质母细胞瘤状态。在训练集和测试集中，分别有 73.4%和 56.1%的患者存在分子胶质母细胞瘤。在训练集中构建使用临床、可视可访问的 Rembrandt 图像和放射组学特征的模型以预测分子胶质母细胞瘤状态，然后在测试集中进行验证。
在测试集中，使用可视可访问的 Rembrandt 图像和放射组学特征的模型显示出优于仅使用临床特征或可视可访问的 Rembrandt 图像的预测性能（曲线下面积=0.854 与 0.514 和 0.648，分别；均<0.001）。当可视可访问的 Rembrandt 图像和放射组学与临床特征结合使用时，预测性能显著提高（曲线下面积=0.514 与 0.863，均<0.001）。
MR 成像特征与机器学习分类器相结合可以预测携带胶质母细胞瘤分子特征的野生型低级别胶质瘤亚组。
