CRESTomics: Analyzing Carotid Plaques in the CREST-2 Trial with a New Additive Classification Model

TL;DR

This paper introduces a novel kernel-based additive model for analyzing carotid plaques in ultrasound images, improving risk assessment accuracy and interpretability in stroke prevention.

Contribution

The paper presents a new additive classification model combining coherence loss and group-sparse regularization for nonlinear analysis of radiomics features.

Findings

Accurately identifies high-risk plaques from ultrasound images.

Reveals strong association between plaque texture and clinical risk.

Provides interpretable visualizations of feature effects.

Abstract

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.