Khalid Fahad, Goya-Outi Jessica, Escobar Thibault, Dangouloff-Ros Volodia, Grigis Antoine, Philippe Cathy, Boddaert Nathalie, Grill Jacques, Frouin Vincent, Frouin Frédérique
Laboratoire d'Imagerie Translationnelle en Oncologie (LITO)-U1288, Institut Curie, Inserm, Université Paris-Saclay, Orsay, France.
DOSIsoft SA, Cachan, France.
Front Med (Lausanne). 2023 Feb 23;10:1071447. doi: 10.3389/fmed.2023.1071447. eCollection 2023.
Predicting H3.1, TP53, and ACVR1 mutations in DIPG could aid in the selection of therapeutic options. The contribution of clinical data and multi-modal MRI were studied for these three predictive tasks. To keep the maximum number of subjects, which is essential for a rare disease, missing data were considered. A multi-modal model was proposed, collecting all available data for each patient, without performing any imputation.
A retrospective cohort of 80 patients with confirmed DIPG and at least one of the four MR modalities (T1w, T1c, T2w, and FLAIR), acquired with two different MR scanners was built. A pipeline including standardization of MR data and extraction of radiomic features within the tumor was applied. The values of radiomic features between the two MR scanners were realigned using the ComBat method. For each prediction task, the most robust features were selected based on a recursive feature elimination with cross-validation. Five different models, one based on clinical data and one per MR modality, were developed using logistic regression classifiers. The prediction of the multi-modal model was defined as the average of all possible prediction results among five for each patient. The performances of the models were compared using a leave-one-out approach.
The percentage of missing modalities ranged from 6 to 11% across modalities and tasks. The performance of each individual model was dependent on each specific task, with an AUC of the ROC curve ranging from 0.63 to 0.80. The multi-modal model outperformed the clinical model for each prediction tasks, thus demonstrating the added value of MRI. Furthermore, regardless of performance criteria, the multi-modal model came in the first place or second place (very close to first). In the leave-one-out approach, the prediction of H3.1 (resp. ACVR1 and TP53) mutations achieved a balanced accuracy of 87.8% (resp. 82.1 and 78.3%).
Compared with a single modality approach, the multi-modal model combining multiple MRI modalities and clinical features was the most powerful to predict H3.1, ACVR1, and TP53 mutations and provided prediction, even in the case of missing modality. It could be proposed in the absence of a conclusive biopsy.
预测弥漫性内生性脑桥胶质瘤（DIPG）中的H3.1、TP53和ACVR1突变有助于治疗方案的选择。研究了临床数据和多模态磁共振成像（MRI）对这三项预测任务的贡献。为了保留对罕见病至关重要的最大数量的受试者，对缺失数据进行了考量。提出了一种多模态模型，收集每位患者的所有可用数据，而不进行任何插补。
建立了一个回顾性队列，纳入80例确诊为DIPG且至少具有四种MRI模态（T1加权像、T1增强像、T2加权像和液体衰减反转恢复序列）之一的患者，这些图像由两台不同的MRI扫描仪采集。应用了一个包括MRI数据标准化和肿瘤内放射组学特征提取的流程。使用ComBat方法对两台MRI扫描仪之间的放射组学特征值进行重新校准。对于每个预测任务，基于带有交叉验证的递归特征消除来选择最稳健的特征。使用逻辑回归分类器开发了五种不同的模型，一种基于临床数据，每种MRI模态各一种。多模态模型的预测被定义为每位患者在五种可能预测结果中的平均值。使用留一法比较模型的性能。
各模态和任务中缺失模态的百分比范围为6%至11%。每个单独模型的性能取决于每个特定任务，受试者工作特征（ROC）曲线的曲线下面积（AUC）范围为0.63至0.80。多模态模型在每个预测任务上均优于临床模型，从而证明了MRI的附加价值。此外，无论性能标准如何衡量，多模态模型均位居第一或第二（与第一名非常接近）。在留一法中，对H3.1（分别对应ACVR1和TP53）突变的预测实现了87.8%（分别对应82.1%和78.3%）的平衡准确率。
与单模态方法相比，结合多种MRI模态和临床特征的多模态模型在预测H3.1、ACVR1和TP53突变方面最为强大，并且即使在存在缺失模态的情况下也能提供预测。在没有确定性活检的情况下可以采用该模型。
