Cao Hang, Erson-Omay E Zeynep, Günel Murat, Moliterno Jennifer, Fulbright Robert K
Department of Neurosurgery, Xiangya Hospital, Central South University, Changsha, China.
Department of Neurosurgery, Yale School of Medicine, New Haven, CT, United States.
Front Oncol. 2021 Jan 29;10:600327. doi: 10.3389/fonc.2020.600327. eCollection 2020.
To measure the metrics of glioma pre-operative MRI reports and build IDH prediction models.
Pre-operative MRI reports of 144 glioma patients in a single institution were collected retrospectively. Words were transformed to lowercase letters. White spaces, punctuations, and stop words were removed. Stemming was performed. A word cloud method applied to processed text matrix visualized language behavior. Spearman's rank correlation assessed the correlation between the subjective descriptions of the enhancement pattern. The T1-contrast images associated with enhancement descriptions were selected. The keywords associated with IDH status were evaluated by χ2 value ranking. Random forest, k-nearest neighbors and Support Vector Machine algorithms were used to train models based on report features and age. All statistical analysis used two-tailed test with significance at p <.05.
Longer word counts occurred in reports of older patients, higher grade gliomas, and wild type IDH gliomas. We identified 30 glioma enhancement descriptions, eight of which were commonly used: peripheral, heterogeneous, irregular, nodular, thick, rim, large, and ring. Five of eight patterns were correlated. IDH mutant tumors were characterized by words related to normal, symmetric or negative findings. IDH wild type tumors were characterized words by related to pathological MR findings like enhancement, necrosis and FLAIR foci. An integrated KNN model based on report features and age demonstrated high-performance (AUC: 0.89, 95% CI: 0.88-0.90).
Report length depended on age, glioma grade, and IDH status. Description of glioma enhancement was varied. Report descriptions differed for IDH wild and mutant gliomas. Report features can be used to predict glioma IDH status.
测量胶质瘤术前MRI报告的指标并建立异柠檬酸脱氢酶（IDH）预测模型。
回顾性收集单个机构中144例胶质瘤患者的术前MRI报告。将单词转换为小写字母。去除空格、标点和停用词。进行词干提取。应用词云方法对处理后的文本矩阵进行可视化，以展示语言行为。采用Spearman等级相关性评估增强模式主观描述之间的相关性。选择与增强描述相关的T1加权对比图像。通过卡方值排序评估与IDH状态相关的关键词。使用随机森林、k近邻和支持向量机算法，基于报告特征和年龄训练模型。所有统计分析均采用双侧检验，显著性水平为p <.05。
老年患者、高级别胶质瘤和野生型IDH胶质瘤的报告中单词计数更长。我们识别出30种胶质瘤增强描述，其中8种常用：周边型（peripheral）、不均匀型（heterogeneous）、不规则型（irregular）、结节型（nodular）、厚壁型（thick）、边缘型（rim）、大型（large）和环形（ring）。8种模式中有5种具有相关性。IDH突变型肿瘤的特征是与正常、对称或阴性结果相关的词汇。IDH野生型肿瘤的特征是与增强、坏死和液体衰减反转恢复（FLAIR）病灶等病理磁共振成像结果相关的词汇。基于报告特征和年龄的综合k近邻（KNN）模型显示出高性能（曲线下面积[AUC]：0.89，95%置信区间[CI]：0.88 - 0.90）。
报告长度取决于年龄、胶质瘤级别和IDH状态。胶质瘤增强的描述各不相同。IDH野生型和突变型胶质瘤的报告描述存在差异。报告特征可用于预测胶质瘤的IDH状态。
