CRESTomics: Analyzing Carotid Plaques in the CREST-2 Trial with a New Additive Classification Model
This research aims to improve stroke prevention for patients with carotid stenosis by identifying high-risk plaque characteristics from ultrasound images, which is an incremental step in medical imaging diagnostics.
This paper analyzes 500 carotid plaques from the CREST-2 trial to identify radiomics-based markers from B-mode ultrasound images associated with high stroke risk. The authors propose a new kernel-based additive model that combines coherence loss with group-sparse regularization for nonlinear classification, demonstrating accurate and interpretable assessment of plaques and revealing a strong association between plaque texture and clinical risk.
Accurate characterization of carotid plaques is critical for stroke prevention in patients with carotid stenosis. We analyze 500 plaques from CREST-2, a multi-center clinical trial, to identify radiomics-based markers from B-mode ultrasound images linked with high-risk. We propose a new kernel-based additive model, combining coherence loss with group-sparse regularization for nonlinear classification. Group-wise additive effects of each feature group are visualized using partial dependence plots. Results indicate our method accurately and interpretably assesses plaques, revealing a strong association between plaque texture and clinical risk.