AUTHOR=Jiang Liang , Zhang Chuanyang , Wang Siyu , Ai Zhongping , Shen Tingwen , Zhang Hong , Duan Shaofeng , Yin Xindao , Chen Yu-Chen 

TITLE=MRI Radiomics Features From Infarction and Cerebrospinal Fluid for Prediction of Cerebral Edema After Acute Ischemic Stroke

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=14

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.782036

DOI=10.3389/fnagi.2022.782036

ISSN=1663-4365

ABSTRACT=<p>Neuroimaging biomarkers that predict the edema after acute stroke may help clinicians provide targeted therapies and minimize the risk of secondary injury. In this study, we applied pretherapy MRI radiomics features from infarction and cerebrospinal fluid (CSF) to predict edema after acute ischemic stroke. MRI data were obtained from a prospective, endovascular thrombectomy (EVT) cohort that included 389 patients with acute stroke from two centers (dataset 1, <italic>n</italic> = 292; dataset 2, <italic>n</italic> = 97), respectively. Patients were divided into edema group (brain swelling and midline shift) and non-edema group according to CT within 36 h after therapy. We extracted the imaging features of infarct area on diffusion weighted imaging (DWI) (abbreviated as DWI), CSF on fluid-attenuated inversion recovery (FLAIR) (CSF<sub>FLAIR</sub>) and CSF on DWI (CSF<sub>DWI</sub>), and selected the optimum features associated with edema for developing models in two forms of feature sets (DWI + CSF<sub>FLAIR</sub> and DWI + CSF<sub>DWI</sub>) respectively. We developed seven ML models based on dataset 1 and identified the most stable model. External validations (dataset 2) of the developed stable model were performed. Prediction model performance was assessed using the area under the receiver operating characteristic curve (AUC). The Bayes model based on DWI + CSF<sub>FLAIR</sub> and the RF model based on DWI + CSF<sub>DWI</sub> had the best performances (DWI + CSF<sub>FLAIR</sub>: AUC, 0.86; accuracy, 0.85; recall, 0.88; DWI + CSF<sub>DWI</sub>: AUC, 0.86; accuracy, 0.84; recall, 0.84) and the most stability (RSD% in DWI + CSF<sub>FLAIR</sub> AUC: 0.07, RSD% in DWI + CSF<sub>DWI</sub> AUC: 0.09), respectively. External validation showed that the AUC of the Bayes model based on DWI + CSF<sub>FLAIR</sub> was 0.84 with accuracy of 0.77 and area under precision-recall curve (auPRC) of 0.75, and the AUC of the RF model based on DWI + CSF<sub>DWI</sub> was 0.83 with accuracy of 0.81 and the auPRC of 0.76. The MRI radiomics features from infarction and CSF may offer an effective imaging biomarker for predicting edema.</p>