Department of Radiology, Cincinnati Children's Hospital and Medical Centre, Cincinnati, OH, USA.
Department of Radiology, Children's Hospital of Philadelphia, Philadelphia, PA, USA.
Eur Radiol. 2023 Oct;33(10):6726-6735. doi: 10.1007/s00330-023-09628-7. Epub 2023 May 13.
We evaluate MR radiomics and develop machine learning-based classifiers to predict MYCN amplification in neuroblastomas.
A total of 120 patients with neuroblastomas and baseline MR imaging examination available were identified of whom 74 (mean age ± standard deviation [SD] of 6 years and 2 months ± 4 years and 9 months; 43 females and 31 males, 14 MYCN amplified) underwent imaging at our institution. This was therefore used to develop radiomics models. The model was tested in a cohort of children with the same diagnosis but imaged elsewhere (n = 46, mean age ± SD: 5 years 11 months ± 3 years 9 months, 26 females and 14 MYCN amplified). Whole tumour volumes of interest were adopted to extract first-order histogram and second-order radiomics features. Interclass correlation coefficient and maximum relevance and minimum redundancy algorithm were applied for feature selection. Logistic regression, support vector machine, and random forest were employed as the classifiers. Receiver operating characteristic (ROC) analysis was performed to evaluate the diagnostic accuracy of the classifiers on the external test set.
The logistic regression model and the random forest both showed an AUC of 0.75. The support vector machine classifier obtained an AUC of 0.78 on the test set with a sensitivity of 64% and a specificity of 72%.
The study provides preliminary retrospective evidence demonstrating the feasibility of MRI radiomics in predicting MYCN amplification in neuroblastomas. Future studies are needed to explore the correlation between other imaging features and genetic markers and to develop multiclass predictive models.
• MYCN amplification in neuroblastomas is an important determinant of disease prognosis. • Radiomics analysis of pre-treatment MR examinations can be used to predict MYCN amplification in neuroblastomas. • Radiomics machine learning models showed good generalisability to external test set, demonstrating reproducibility of the computational models.
我们评估磁共振影像组学并开发基于机器学习的分类器来预测神经母细胞瘤中 MYCN 扩增。
共纳入 120 例神经母细胞瘤患者，这些患者均具有基线磁共振成像检查资料，其中 74 例（平均年龄±标准差为 6 岁 2 个月±4 岁 9 个月；女性 43 例，男性 31 例，14 例 MYCN 扩增）在我院进行了影像学检查，因此用于开发影像组学模型。该模型在另一组具有相同诊断但在其他地方进行影像学检查的儿童（n=46，平均年龄±标准差：5 岁 11 个月±3 岁 9 个月，女性 26 例，MYCN 扩增 14 例）中进行了测试。采用全肿瘤感兴趣区提取一阶直方图和二阶影像组学特征。采用组内相关系数和最大相关性最小冗余算法进行特征选择。采用逻辑回归、支持向量机和随机森林作为分类器。在外部测试集上进行受试者工作特征（ROC）分析以评估分类器的诊断准确性。
逻辑回归模型和随机森林的 AUC 均为 0.75。支持向量机分类器在测试集上的 AUC 为 0.78，敏感度为 64%，特异度为 72%。
该研究提供了初步的回顾性证据，证明 MRI 影像组学在预测神经母细胞瘤中 MYCN 扩增方面具有可行性。未来需要研究其他影像学特征与遗传标志物之间的相关性，并开发多类预测模型。
·神经母细胞瘤中 MYCN 扩增是疾病预后的重要决定因素。
·治疗前磁共振检查的影像组学分析可用于预测神经母细胞瘤中 MYCN 扩增。
·影像组学机器学习模型对外部测试集具有良好的泛化能力，证明了计算模型的可重复性。
