Background: While non-contrast computed tomography (NCCT) is the primary imaging modality in emergency settings, it has a low sensitivity for detection of Cerebral Venous Thrombosis (CVT). This study aims to develop an Artificial Intelligence (AI) tool to screen for CVT on routine NCCT scans. Methods: We used a retrospectively collected dataset of 692 patients, including 258 with CVT from Iran Cerebral Venous Thrombosis Registry (ICVTR) (code: 9001013381) and 434 controls. NCCT images were processed using the pre-trained CT-Foundation model to generate high-dimensional embeddings. These embeddings were used to train several machine learning classifiers: Support Vector Machine (SVM) with linear, polynomial, and RBF kernels, Logistic Regression, Random Forest, an Artificial Neural Network (ANN), and a soft-voting Ensemble model. Model performance was assessed using a 10-fold cross-validation protocol. Results: The Random Forest model achieved the highest specificity of 0.856 ± 0.050, excelling at identifying non-CVT cases. Conversely, the Ensemble model yielded the highest sensitivity of 0.614 ± 0.087. The SVM with a linear kernel provided the best overall discriminative ability, with the highest AUC of 0.718 ± 0.053. No single model demonstrated superiority across all metrics, reflecting the inherent challenge of detecting CVT on NCCT. Conclusion: Our findings demonstrate the feasibility of using an AI-based model to detect CVT on non-contrast CT scans. While not yet a replacement for expert radiological interpretation, this approach serves as a promising automated screening tool. It has the potential to reduce diagnostic delays and improve patient outcomes by flagging suspicious cases in emergency workflows.
Namjoo-Moghadam et al. (Mon,) studied this question.