Machine Learning Detects Symptomatic Plaques on 3D high-resolution MR vessel wall images

Motivation: Reliable assessment of plaque vulnerability is crucial for identifying high-risk plaques and preventing stroke. Goal(s): To develop and validate a high-risk intracranial plaque classification model using a combination of morphological and signal features from Three-dimensional high-resolution magnetic resonance vessel wall imaging (3D HR-MRVWI) and machine learning. Approach: Using 3D HR-MRVWI, we extracted morphological and signal features, which were then input into support vector classifier (SVC) and logistic regression models to classify plaques as symptomatic or asymptomatic. Results: Adding signal features resulted in a notable increase in The Area Under the Curve(AUC) and accuracy compared to models using morphological features alone. Impact: This study validated the importance of signal features, such as enhancement degree, in identifying high-risk plaques, providing data support for future radiomic research. This approach aids in early screening and targeted preventive measures, potentially reducing the incidence of stroke.