Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types
Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types
复制标题
非增强 CT 扫描的放射组学特征可以将 AVM 相关血肿与其他自发性实质内血肿类型精确分类
DOI：
10.1007/s00330-018-5747-x
复制
发表时间：
2019-04-01
影响因子：
5.9
通讯作者：
Jiang, Chuhan
中科院分区：
文献类型：
--
作者：
Zhang, Yupeng;Zhang, Baorui;Jiang, Chuhan
目的探讨非对比增强CT（NECT）图像上提取的定量放射组学特征的分类能力，以区分AVM相关血肿与其他病因引起的血肿。方法2012年至2017年，我中心对261例脑实质内血肿患者进行基线CT扫描。病例被分成训练数据集（n=180）和测试数据集（n=81）。血肿类型分为两类，即AVM相关血肿（AVM-H）和其他病因引起的血肿。从NECT中提取了6个特征组共576个放射组学特征。我们应用了11种特征选择方法从每个特征组中选择信息特征。然后使用选定的放射组学特征和临床特征年龄来拟合机器学习分类器。结合11种特征选择方法和8种分类器，我们构建了88个预测模型。预测模型进行了评估，并选择最佳的一个，并evaluated.ResultsThe选定的放射组学模型是RELF_Ada，这是训练与Adaboost分类器和救济方法选择的功能。训练数据集的交叉验证曲线下面积（AUC）为0.988，相对标准偏差（RSD%）为0.062。测试数据集上的AUC为0.957。准确性（ACC），灵敏度，特异性，阳性预测值（PPV），和阴性预测值（NPV）分别为0.926，0.889，0.937，0.800，和0.967，conclusionsMachine learning models with radiomics features extracted from NECT scan accurately discussed AVM相关脑实质内血肿从其他病因引起的。该技术提供了一种快速、非侵入性的方法，无需使用造影剂来诊断这种疾病。关键点中心点放射组学特征从非造影剂增强CT准确区分AVM相关血肿与其他AVM相关血肿。AVM相关血肿往往直径更大，纹理更粗糙，在composition.center etiologies.center com中更不均匀。Adaboost分类器是分析放射组学特征的有效方法。
ObjectiveTo investigate the classification ability of quantitative radiomics features extracted on non-contrast-enhanced CT (NECT) image for discrimination of AVM-related hematomas from those caused by other etiologies.MethodsTwo hundred sixty-one cases with intraparenchymal hematomas underwent baseline CT scan between 2012 and 2017 in our center. Cases were split into a training dataset (n=180) and a test dataset (n=81). Hematoma types were dichotomized into two classes, namely, AVM-related hematomas (AVM-H) and hematomas caused by other etiologies. A total of 576 radiomics features of 6 feature groups were extracted from NECT. We applied 11 feature selection methods to select informative features from each feature group. Selected radiomics features and the clinical feature age were then used to fit machine learning classifiers. In combination of the 11 feature selection methods and 8 classifiers, we constructed 88 predictive models. Predictive models were evaluated and the optimal one was selected and evaluated.ResultsThe selected radiomics model was RELF_Ada, which was trained with Adaboost classifier and features selected by Relief method. Cross-validated area under the curve (AUC) on training dataset was 0.988 and the relative standard deviation (RSD%) was 0.062. AUC on the test dataset was 0.957. Accuracy (ACC), sensitivity, specificity, positive prediction value (PPV), and negative predictive value (NPV) were 0.926, 0.889, 0.937, 0.800, and 0.967, respectively.ConclusionsMachine learning models with radiomics features extracted from NECT scan accurately discriminated AVM-related intraparenchymal hematomas from those caused by other etiologies. This technique provided a fast, non-invasive approach without use of contrast to diagnose this disease.Key Points center dot Radiomics features from non-contrast-enhanced CT accurately discriminated AVM-related hematomas from those caused by other etiologies.center dot AVM-related hematomas tended to be larger in diameter, coarser in texture, and more heterogeneous in composition.center dot Adaboost classifier is an efficient approach for analyzing radiomics features.