Guo Wei, She Dejun, Xing Zhen, Lin Xiang, Wang Feng, Song Yang, Cao Dairong
Department of Radiology, First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
MR Scientific Marketing, Siemens Healthineers Ltd., Shanghai, China.
Front Oncol. 2022 Mar 3;12:796583. doi: 10.3389/fonc.2022.796583. eCollection 2022.
The performance of multiparametric MRI-based radiomics models for predicting H3 K27M mutant status in diffuse midline glioma (DMG) has not been thoroughly evaluated. The optimal combination of multiparametric MRI and machine learning techniques remains undetermined. We compared the performance of various radiomics models across different MRI sequences and different machine learning techniques.
A total of 102 patients with pathologically confirmed DMG were retrospectively enrolled (27 with H3 K27M-mutant and 75 with H3 K27M wild-type). Radiomics features were extracted from eight sequences, and 18 feature sets were conducted by independent combination. There were three feature matrix normalization algorithms, two dimensionality-reduction methods, four feature selectors, and seven classifiers, consisting of 168 machine learning pipelines. Radiomics models were established across different feature sets and machine learning pipelines. The performance of models was evaluated using receiver operating characteristic curves with area under the curve (AUC) and compared with DeLong's test.
The multiparametric MRI-based radiomics models could accurately predict the H3 K27M mutant status in DMG (highest AUC: 0.807-0.969, for different sequences or sequence combinations). However, the results varied significantly between different machine learning techniques. When suitable machine learning techniques were used, the conventional MRI-based radiomics models shared similar performance to advanced MRI-based models (highest AUC: 0.875-0.915 vs. 0.807-0.926; DeLong's test, > 0.05). Most models had a better performance when generated with a combination of MRI sequences. The optimal model in the present study used a combination of all sequences (AUC = 0.969).
The multiparametric MRI-based radiomics models could be useful for predicting H3 K27M mutant status in DMG, but the performance varied across different sequences and machine learning techniques.
基于多参数磁共振成像（MRI）的放射组学模型在预测弥漫性中线胶质瘤（DMG）中H3 K27M突变状态方面的性能尚未得到充分评估。多参数MRI与机器学习技术的最佳组合仍未确定。我们比较了不同MRI序列和不同机器学习技术下各种放射组学模型的性能。
回顾性纳入102例经病理证实的DMG患者（27例H3 K27M突变型和75例H3 K27M野生型）。从八个序列中提取放射组学特征，并通过独立组合生成18个特征集。有三种特征矩阵归一化算法、两种降维方法、四种特征选择器和七个分类器，组成168个机器学习管道。在不同特征集和机器学习管道上建立放射组学模型。使用曲线下面积（AUC）的受试者操作特征曲线评估模型性能，并与德龙检验进行比较。
基于多参数MRI的放射组学模型能够准确预测DMG中的H3 K27M突变状态（不同序列或序列组合的最高AUC：0.807 - 0.969）。然而，不同机器学习技术之间的结果差异显著。当使用合适的机器学习技术时，基于传统MRI的放射组学模型与基于先进MRI的模型具有相似的性能（最高AUC：0.875 - 0.915对0.807 - 0.926；德龙检验，P > 0.05）。大多数模型在由MRI序列组合生成时性能更好。本研究中的最佳模型使用了所有序列的组合（AUC = 0.969）。
基于多参数MRI的放射组学模型可用于预测DMG中的H3 K27M突变状态，但性能因不同序列和机器学习技术而异。
