Automated Classification of Stroke Blood Clot Origin using Whole-Slide Digital Pathology Images

The classification of the origin of blood clots is a crucial step in diagnosing and treating ischemic stroke. Various imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound have been employed to detect and locate blood clots within the body. However, identifying the origin of a blood clot remains challenging due to the complexity of the blood flow dynamics and the limitations of the imaging techniques. The study suggests a novel methodology for classifying the source of a blood clot through the integration of data from whole-slide digital pathology images, which are utilized to fine-tune several cutting-edge computer vision models. Upon comparison, the SwinTransformerV2 model outperforms all the other models and achieves an accuracy score of 94.24%, precision score of 94.41%, recall score of 94.09%, and, f1-score of 94.06%. Our approach shows promising results in detecting the origin of blood clots in different vascular regions and can potentially improve the diagnosis and management of ischemic stroke.