ObjectiveTo explore the performance of deep learning-based segmentation of infarcted lesions in the brain MRI of patients with AIS and the recurrence prediction value of radiomics within 1 year after discharge as well as to develop a model incorporating radiomics features and clinical factors to accurately predict AIS recurrence. Materials and MethodsTo generate a segmentation model of MRI lesions in AIS, the deep learning algorithm multiscale residual attention UNet (MRA-UNet) was employed. Furthermore, the risk factors for AIS recurrence within 1 year were explored using logistic regression analysis. In addition, to develop the prediction model for AIS recurrence within 1 year after discharge, four machine learning algorithms, namely, LR, RandomForest, CatBoost, and XGBoost, were employed based on radiomics data, clinical data, and their combined data. ResultsIn the validation set, the MDice and MIou of the MRA-UNet segmentation model were 0.816 and 0.801, respectively. In multivariate logistic regression analysis, age, renal insufficiency, C-reactive protein, triglyceride glucose index, prognostic nutritional index, and infarct volume were identified as the independent risk factors for stroke recurrence. Furthermore, in the validation set, combining radiomics data and clinical data, the AUC was 0.835 (95%CI:0.738, 0.932), 0.834 (95%CI:0.740, 0.928), 0.858 (95%CI:0.770, 0.946), and 0.842 (95%CI:0.752, 0.932) for the LR, RandomForest, CatBoost, and XGBoost models, respectively. ConclusionThe MRA-UNet model can effectively improve the segmentation accuracy of diffusion-weighted images. The model, which was established by combining radiomics features and clinical factors, held some value for predicting ischemic stroke recurrence within 1 year.
Read full abstract