Developed a deep learning-based approach to detect large vessel occlusions (LVOs) in the internal carotid artery (ICA) and middle cerebral artery (MCA) from computed tomography angiography (CTA) scans. The study aimed to enhance the accuracy and speed of LVO diagnosis, which is critical for improving stroke outcomes. The researchers evaluated their models on a dataset of CTA scans, achieving a combined accuracy of 90.9%, with a sensitivity of 89.8% and specificity of 91.4%. Notably, the models produced results in under 40 seconds, demonstrating their potential for integration into clinical workflows to facilitate timely and accurate LVO detection.
