Department of Radiology, Huashan Hospital Affiliated to Fudan University, 12 Wulumuqi Rd. Middle, Shanghai 200040, China.
Department of Pathology, Huashan Hospital Affiliated to Fudan University, 12 Wulumuqi Rd. Middle, Shanghai 200040, China.
J Neuroradiol. 2019 Sep;46(5):281-287. doi: 10.1016/j.neurad.2019.05.013. Epub 2019 Jun 18.
To assess whether a machine-learning model based on texture analysis (TA) could yield a more accurate diagnosis in differentiating malignant haemangiopericytoma (HPC) from angiomatous meningioma (AM).
Sixty-seven pathologically confirmed cases, including 24 malignant HPCs and 43 AMs between May 2013 and September 2017 were retrospectively reviewed. In each case, 498 radiomic features, including 12 clinical features and 486 texture features from MRI sequences (T2-FLAIR, DWI and enhanced T1WI), were extracted. Three neuroradiologists independently made diagnoses by vision. Four Support Vector Machine (SVM) classifiers were built, one based on clinical features and three based on texture features from three MRI sequences after feature selection. The diagnostic abilities of these classifiers and three neuroradiologists were evaluated by receiver operating characteristic (ROC) analysis.
Malignant HPCs were found to have larger sizes, slighter degrees of peritumoural oedema compared with AMs (P<0.05), and more serpentine-like vessels. The AUC of the enhanced T1WI-based classifier was 0.90, significantly higher than that of T2-FLAIR-based or DWI-based classifiers (0.77 and 0.73). The AUC of the SVM classifier based on clinical features was 0.66, slightly but not significantly lower than the performances of 3 neuroradiologists (AUC=0.69, 0.70 and 0.73).
Machine-learning models based on clinical features alone could not provide a better diagnostic performance than that of radiologists. The SVM classifier built by texture features extracted from enhanced T1WI is a promising tool to differentiate malignant HPC from AM before surgery.
评估基于纹理分析（TA）的机器学习模型是否能更准确地区分恶性血管外皮细胞瘤（HPC）和血管外皮细胞瘤样脑膜瘤（AM）。
回顾性分析 2013 年 5 月至 2017 年 9 月期间经病理证实的 67 例病例，包括 24 例恶性 HPC 和 43 例 AM。在每个病例中，从 MRI 序列（T2-FLAIR、DWI 和增强 T1WI）中提取了 498 个放射组学特征，包括 12 个临床特征和 486 个纹理特征。三位神经放射科医生独立进行了视觉诊断。建立了四个支持向量机（SVM）分类器，一个基于临床特征，三个基于三个 MRI 序列的纹理特征，在特征选择后。通过受试者工作特征（ROC）分析评估这些分类器和三位神经放射科医生的诊断能力。
恶性 HPC 的体积较大，瘤周水肿程度较 AM 轻（P<0.05），且血管呈蛇形。基于增强 T1WI 的分类器的 AUC 为 0.90，明显高于基于 T2-FLAIR 或 DWI 的分类器（0.77 和 0.73）。基于临床特征的 SVM 分类器的 AUC 为 0.66，略低于但无统计学意义上低于三位神经放射科医生的表现（AUC=0.69、0.70 和 0.73）。
仅基于临床特征的机器学习模型不能提供比放射科医生更好的诊断性能。基于增强 T1WI 提取的纹理特征构建的 SVM 分类器是一种有前途的术前鉴别恶性 HPC 和 AM 的工具。
