AUTHOR=Ren Qingguo , An Panpan , Jin Ke , Xia Xiaona , Huang Zhaodi , Xu Jingxu , Huang Chencui , Jiang Qingjun , Meng Xiangshui 

TITLE=A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.851720

DOI=10.3389/fnins.2022.851720

ISSN=1662-453X

ABSTRACT=Background: To explore the effectiveness of radiomics features based on routine CT to reflect difference of cerebral hemispheric perfusion.
Methods: We retrospectively recruited 52 patients with severe stenosis or occlusion in unilateral middle cerebral artery (MCA), and brain CT perfusion showed MCA area with deficit perfusion. Radiomics features were extracted from the stenosis side and contralateral of MCA area based on pre-contrast CT. Two different region of interest drawing methods were applied. Then the patients were randomly grouped into training and testing sets by ratio of 8:2. In the training set, analysis of variance (ANOVA) and the Elastic Net Regression with 5-fold cross validation (5-fold CV) were conducted to filter and choose the optimized features. Moreover, different machine learning models were built. In the testing set, the area under the receiver operating characteristic curve (AUC), calibration and clinical utility were applied to evaluate the predictive performance of the models.
Results: The Logistic Regression (LR) for the triangle-contour method and Artificial Neural Network (ANN) for the semiautomatic-contour method were chosen as radiomics models for their good prediction efficacy in training phase (AUC=0.869, 0.873) and the validation phase (AUC=0.793, 0.799). The radiomics algorithms of triangle-contour and semiautomatic-contour method were implemented in the whole training set (AUC=0.870, 0.867) and were evaluated in the testing set (AUC=0.760, 0.802). According to the optimal cut-off value, these two methods can classify the vascular stenosis side class and normal side class.
Conclusion: Radiomic predictive feature based on pre-contrast CT image could reflect difference of cerebral hemispheric perfusion to some extent.