应用影像组学方法鉴别儿童室管膜瘤与髓母细胞瘤
本研究对51例患儿(24例室管膜瘤、27例髓母细胞瘤)的增强T1加权图像和表观扩散系数图进行三维半自动分割并提取影像组学特征,采用三种特征选择方法与四种分类器组合构建12种模型。以多变量逻辑回归为特征选择方法、随机森林为分类器的模型表现最佳,曲线下面积达0.91(95%CI 0.787-0.968),5个相关特征与鉴别室管膜瘤和髓母细胞瘤高度相关。结论认为三维多模态MRI影像组学与机器学习方法可较好区分儿童室管膜瘤与髓母细胞瘤,辅助医生临床诊断,但需尝试不同组合方法。
要点
- 增强T1加权图像与表观扩散系数图的三维影像组学特征可用于鉴别儿童室管膜瘤与髓母细胞瘤。
- 多变量逻辑回归特征选择联合随机森林分类器模型表现最佳,AUC为0.91(95%CI 0.787-0.968)。
- 5个相关特征与鉴别室管膜瘤和髓母细胞瘤高度相关,可能作为预测肿瘤类型的影像生物标志物。
核心结论
- 三维多模态MRI影像组学与机器学习方法可较好区分儿童室管膜瘤与髓母细胞瘤,辅助医生临床诊断。
研究设计与样本
- 研究纳入51例患儿(24例室管膜瘤、27例髓母细胞瘤),由放射科医生在增强T1加权图像和表观扩散系数图上对三维肿瘤进行半自动分割。
- 提取影像组学特征后采用三种特征选择方法降维,每种特征选择方法搭配4种分类器,共产生12种不同模型。
- 经过广泛交叉验证后,在受试者工作特征曲线上进行成对检验以比较各模型性能。
关键影像表现/征象
- 增强T1加权图像和表观扩散系数图的三维影像组学特征可用于鉴别儿童室管膜瘤与髓母细胞瘤。
- 5个相关特征与鉴别室管膜瘤和髓母细胞瘤高度相关,可能作为预测肿瘤类型的影像生物标志物。
诊断标准与关键数值
- 以多变量逻辑回归为特征选择方法、随机森林为分类器的影像组学模型表现最佳,曲线下面积为0.91(95%CI 0.787-0.968)。
临床应用与阅片要点
- 作者认为影像组学与机器学习方法可辅助医生临床诊断儿童室管膜瘤与髓母细胞瘤。
- 作者指出由于没有统一模型能在每个特定数据集上获得最佳性能,有必要尝试不同的组合方法。
局限性
- 原文指出由于没有统一模型能在每个特定数据集上获得最佳性能,有必要尝试不同的组合方法。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Ependymoma (EP) and medulloblastoma (MB) of children are similar in age, location, manifestations and symptoms. Therefore, it is difficult to differentiate them through visual observation in clinical diagnosis. The aim of this study is to investigate the effectiveness of radiomics and machine-learning techniques on multimodal magnetic resonance imaging (MRI) in distinguish EP from MB.
MATERIALS AND METHODS: Three dimensional (3D) tumors were semi-automatic segmented by radiologists from postcontrast T1-weighted images and apparent diffusion coefficient maps in 51 patients (24 EPs, 27 MBs). Then, we extracted radiomics features and further reduced them by three feature selection methods. For each feature selection method, 4 classifiers were adopted which yield 12 different models. After extensive crossvalidation, pairwise test were carried out in receiver operating characteristic curves to explore performance of these models.
RESULTS: The radiomics model built with multivariable logistic regression as feature selection method and random forests as classifier had the best performance, area under the curve achieved 0.91 (95 % confidence interval 0.787-0.968). Five relevant features were highly correlated to discriminate EP and MB, which may used as imaging biomarkers to predict the kinds of tumors.
CONCLUSION: The combination of radiomics and machine-learning approach on 3D multimodal MRI could well distinguish EP and MB of childhood, which assistant doctors in clinical diagnosis. Since there is no uniform model to obtained best performance for every specific data set, it is necessary to try different combination methods.
引用
- Dong J, Li L, Liang S, et al. Differentiation Between Ependymoma and Medulloblastoma in Children with Radiomics Approach. Acad Radiol. 2020. PMID: 32222329. doi:10.1016/j.acra.2020.02.012
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。