Department of Radiology, The First People's Hospital of Kashi (Kashgar) Prefecture, Xinjiang, China, 844000; Xinjiang Key Laboratory of Artificial Intelligence assisted Imaging Diagnosis, Kashi (Kashgar), China, 844000.
Department of Spine Surgery, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China, 830054.
Acad Radiol. 2024 Aug;31(8):3384-3396. doi: 10.1016/j.acra.2024.02.040. Epub 2024 Mar 20.
Medulloblastoma (MB) and Ependymoma (EM) in children, share similarities in age group, tumor location, and clinical presentation. Distinguishing between them through clinical diagnosis is challenging. This study aims to explore the effectiveness of using radiomics and machine learning on multiparametric magnetic resonance imaging (MRI) to differentiate between MB and EM and validate its diagnostic ability with an external set.
Axial T2 weighted image (T2WI) and contrast-enhanced T1weighted image (CE-T1WI) MRI sequences of 135 patients from two centers were collected as train/test sets. Volume of interest (VOI) was manually delineated by an experienced neuroradiologist, supervised by a senior. Feature selection analysis and the least absolute shrinkage and selection operator (LASSO) algorithm identified valuable features, and Shapley additive explanations (SHAP) evaluated their significance. Five machine-learning classifiers-extreme gradient boosting (XGBoost), Bernoulli naive Bayes (Bernoulli NB), Logistic Regression (LR), support vector machine (SVM), linear support vector machine (Linear SVC) classifiers were built based on T2WI (T2 model), CE-T1WI (T1 model), and T1 + T2WI (T1 + T2 model). A human expert diagnosis was developed and corrected by senior radiologists. External validation was performed at Sun Yat-Sen University Cancer Center.
31 valuable features were extracted from T2WI and CE-T1WI. XGBoost demonstrated the highest performance with an area under the curve (AUC) of 0.92 on the test set and maintained an AUC of 0.80 during external validation. For the T1 model, XGBoost achieved the highest AUC of 0.85 on the test set and the highest accuracy of 0.71 on the external validation set. In the T2 model, XGBoost achieved the highest AUC of 0.86 on the test set and the highest accuracy of 0.82 on the external validation set. The human expert diagnosis had an AUC of 0.66 on the test set and 0.69 on the external validation set. The integrated T1 + T2 model achieved an AUC of 0.92 on the test set, 0.80 on the external validation set, achieved the best performance. Overall, XGBoost consistently outperformed in different classification models.
The combination of radiomics and machine learning on multiparametric MRI effectively distinguishes between MB and EM in childhood, surpassing human expert diagnosis in training and testing sets.
髓母细胞瘤（MB）和室管膜瘤（EM）在儿童中具有相似的年龄组、肿瘤位置和临床表现。通过临床诊断区分它们具有挑战性。本研究旨在探讨使用放射组学和机器学习对多参数磁共振成像（MRI）进行区分的有效性，并通过外部数据集验证其诊断能力。
收集两个中心的 135 名患者的轴向 T2 加权图像（T2WI）和对比增强 T1 加权图像（CE-T1WI）MRI 序列作为训练/测试集。由一名有经验的神经放射科医生手动勾画感兴趣区（VOI），由一名资深医生进行监督。特征选择分析和最小绝对收缩和选择算子（LASSO）算法确定有价值的特征，Shapley 加性解释（SHAP）评估其重要性。基于 T2WI（T2 模型）、CE-T1WI（T1 模型）和 T1+T2WI（T1+T2 模型）构建了五种机器学习分类器——极端梯度提升（XGBoost）、伯努利朴素贝叶斯（Bernoulli NB）、逻辑回归（LR）、支持向量机（SVM）和线性支持向量机（Linear SVC）。建立了人类专家诊断，并由资深放射科医生进行修正。中山大学肿瘤防治中心进行了外部验证。
从 T2WI 和 CE-T1WI 中提取了 31 个有价值的特征。XGBoost 在测试集上的曲线下面积（AUC）为 0.92，表现最佳，在外部验证中保持了 0.80 的 AUC。对于 T1 模型，XGBoost 在测试集上的 AUC 最高为 0.85，在外部验证集上的准确率最高为 0.71。在 T2 模型中，XGBoost 在测试集上的 AUC 最高为 0.86，在外部验证集上的准确率最高为 0.82。人类专家诊断在测试集上的 AUC 为 0.66，在外部验证集上的 AUC 为 0.69。集成的 T1+T2 模型在测试集上的 AUC 为 0.92，在外部验证集上的 AUC 为 0.80，表现最佳。总体而言，XGBoost 在不同的分类模型中表现始终优于人类专家诊断。
多参数 MRI 联合放射组学和机器学习可有效区分儿童期的 MB 和 EM，在训练集和测试集上均优于人类专家诊断。
