Predicting mortality rate in ischemic stroke using artificial intelligence with NCCT imaging

In this study, the Core-Penumbra Acute Ischemic Stroke Dataset (CPAISD), a publicly available radiological image dataset, was used for stroke classification and segmentation tasks. The dataset includes brain Non-Contrast Computed Tomography (NCCT) images of patients with different ages, genders, and clinical conditions. In our study, a transformer-based model is preferred, the most effective 40 radiomic features detected from NCCT images are extracted, and the effects of transformer architecture on the classification of ischemic stroke lethality are observed with loss functions and Simple Attention, Multi Head Attention mechanisms. Our RadiomicsTransformer (RT) model, with radiomics selection, focal loss, 5-fold cross-validation, and simple attention applications, provides 0.6889 accuracy, 0.6930 precision, 0.6778 sensitivity, 0.6854 F1-score and 0.7167 ROC AUC values. The results demon- strate that, on imbalanced and limited datasets, the transformer-based deep learning (DL) model outperforms classical machine learning (ML) models, and that our transformer architecture holds clinically testable potential for stroke diagnosis.