Xie Huanhuan, Dong Fei, Zhang Ruiting, Yu Xinfeng, Xu Peng, Tang Yinshan, Huang Peiyu, Wang Chao
Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Neuroscience Intensive Care Unit, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Front Neurosci. 2023 Nov 28;17:1284560. doi: 10.3389/fnins.2023.1284560. eCollection 2023.
To develop and validate radiomics models on non-enhanced CT for discrimination of arteriovenous malformation (AVM) related hematomas from hypertensive intracerebral hematomas.
A total of 571 patients with acute intraparenchymal hematomas and baseline non-enhanced CT scans were retrospectively analyzed, including 297 cases of AVM related hematomas and 274 cases of hypertensive intracerebral hematomas. The patients were divided into training and validation cohorts in a 7:3 ratio with a random seed. A total of 1,688 radiomics features of hematomas were extracted from non-enhanced CT. Then, the least absolute shrinkage and selection operator (LASSO) regression was applied to select features and construct the radiomics models. In this study, a radiomics-based model was constructed that based on the radiomics features only. Furthermore, a combined model was constructed using radiomics features, clinical characteristics and radiological signs by radiologists' evaluation. In addition, we compared predictive performance of the two models for discrimination of AVM related hematomas from hypertensive intracerebral hematomas.
A total of 67 radiomics features were selected to establish radiomics signature via LASSO regression. The radiomics-based model was constructed with 2 classifiers, support vector machine (SVM) and logistic regression (LR). AUCs of the radiomics-based model in the training set were 0.894 and 0.904, in validation set were 0.774 and 0.782 in SVM classifier and LR classifier, respectively. AUCs of the combined model (combined with radiomics, age and calcification) in the training set were 0.976 and 0.981, in validation set were 0.896 and 0.907 in SVM classifier and LR classifier, respectively. The combined model showed greater AUCs than radiomics-based model in both training set and validation set.
The combined model using radiomics, age and calcification showed a satisfactory predictive performance for discrimination of AVM related hematomas from hypertensive intracerebral hematomas and hold great potential for personalized clinical decision.
开发并验证基于非增强CT的影像组学模型，以鉴别动静脉畸形（AVM）相关血肿与高血压性脑出血。
回顾性分析571例急性脑实质内血肿患者及基线非增强CT扫描资料，其中AVM相关血肿297例，高血压性脑出血274例。采用随机种子数按7:3的比例将患者分为训练组和验证组。从非增强CT中提取血肿的1688个影像组学特征。然后，应用最小绝对收缩和选择算子（LASSO）回归进行特征选择并构建影像组学模型。在本研究中，构建了一个仅基于影像组学特征的影像组学模型。此外，通过放射科医生的评估，利用影像组学特征、临床特征和放射学征象构建了一个联合模型。另外，比较了这两种模型鉴别AVM相关血肿与高血压性脑出血的预测性能。
通过LASSO回归共选择67个影像组学特征来建立影像组学特征。基于影像组学的模型由支持向量机（SVM）和逻辑回归（LR）两种分类器构建。基于影像组学的模型在训练组中，SVM分类器和LR分类器的曲线下面积（AUC）分别为0.894和0.904；在验证组中分别为0.774和0.782。联合模型（结合影像组学、年龄和钙化）在训练组中，SVM分类器和LR分类器的AUC分别为0.976和0.981；在验证组中分别为0.896和0.907。联合模型在训练组和验证组中的AUC均高于基于影像组学的模型。
结合影像组学、年龄和钙化的联合模型在鉴别AVM相关血肿与高血压性脑出血方面表现出令人满意的预测性能，具有很大的个性化临床决策潜力。
