Wagner Matthias W, Namdar Khashayar, Napoleone Marc, Hainc Nicolin, Amirabadi Afsaneh, Fonseca Adriana, Laughlin Suzanne, Shroff Manohar M, Bouffet Eric, Hawkins Cynthia, Khalvati Farzad, Bartels Ute, Ertl-Wagner Birgit B
Department of Diagnostic Imaging, Division of Neuroradiology, 7979The Hospital for Sick Children, Toronto, Canada.
Department of Medical Imaging, 7938University of Toronto, Canada.
Can Assoc Radiol J. 2023 Feb;74(1):119-126. doi: 10.1177/08465371221109921. Epub 2022 Jun 29.
Biopsy-based assessment of H3 K27 M status helps in predicting survival, but biopsy is usually limited to unusual presentations and clinical trials. We aimed to evaluate whether radiomics can serve as prognostic marker to stratify diffuse intrinsic pontine glioma (DIPG) subsets. In this retrospective study, diagnostic brain MRIs of children with DIPG were analyzed. Radiomic features were extracted from tumor segmentations and data were split into training/testing sets (80:20). A conditional survival forest model was applied to predict progression-free survival (PFS) using training data. The trained model was validated on the test data, and concordances were calculated for PFS. Experiments were repeated 100 times using randomized versions of the respective percentage of the training/test data. A total of 89 patients were identified (48 females, 53.9%). Median age at time of diagnosis was 6.64 years (range: 1-16.9 years) and median PFS was 8 months (range: 1-84 months). Molecular data were available for 26 patients (29.2%) (1 wild type, 3 K27M-H3.1, 22 K27M-H3.3). Radiomic features of FLAIR and nonenhanced T1-weighted sequences were predictive of PFS. The best FLAIR radiomics model yielded a concordance of .87 [95% CI: .86-.88] at 4 months PFS. The best T1-weighted radiomics model yielded a concordance of .82 [95% CI: .8-.84] at 4 months PFS. The best combined FLAIR + T1-weighted radiomics model yielded a concordance of .74 [95% CI: .71-.77] at 3 months PFS. The predominant predictive radiomic feature matrix was gray-level size-zone. MRI-based radiomics may predict progression-free survival in pediatric diffuse midline glioma/diffuse intrinsic pontine glioma.
基于活检对H3 K27M状态进行评估有助于预测生存期，但活检通常仅限于不常见的病例和临床试验。我们旨在评估影像组学是否可作为一种预后标志物，用于对弥漫性脑桥内生型胶质瘤（DIPG）亚组进行分层。在这项回顾性研究中，对患有DIPG的儿童的脑部诊断性MRI进行了分析。从肿瘤分割图像中提取影像组学特征，并将数据分为训练集/测试集（80:20）。应用条件生存森林模型，利用训练数据预测无进展生存期（PFS）。在测试数据上对训练好的模型进行验证，并计算PFS的一致性。使用训练/测试数据各自百分比的随机版本重复实验100次。共确定了89例患者（48名女性，占53.9%）。诊断时的中位年龄为6.64岁（范围：1 - 16.9岁），中位PFS为8个月（范围：1 - 84个月）。26例患者（29.2%）有分子数据（1例野生型，3例K27M - H3.1，22例K27M - H3.3）。FLAIR序列和未增强T1加权序列的影像组学特征可预测PFS。最佳的FLAIR影像组学模型在4个月PFS时的一致性为0.87 [95%可信区间：0.86 - 0.88]。最佳的T1加权影像组学模型在4个月PFS时的一致性为0.82 [95%可信区间：0.8 - 0.84]。最佳的FLAIR + T1加权联合影像组学模型在3个月PFS时的一致性为0.74 [95%可信区间：0.71 - 0.77]。主要的预测性影像组学特征矩阵是灰度级大小区域。基于MRI的影像组学可预测儿童弥漫性中线胶质瘤/弥漫性脑桥内生型胶质瘤的无进展生存期。
