Hierarchical Corpus-View-Category Refinement for Carotid Plaque Risk Grading in Ultrasound

TL;DR

This paper introduces a novel hierarchical deep learning framework for carotid plaque risk grading in ultrasound images, improving accuracy by multi-level feature refinement and class-aware modeling.

Contribution

It presents a new Corpus-View-Category refinement framework with a center-memory contrastive loss, cascaded attention, and mixture-of-experts strategy for improved carotid plaque grading.

Findings

Achieves state-of-the-art performance on carotid plaque grading

Effectively models global features through multi-level refinement

Outperforms existing methods in accuracy and robustness

Abstract

Accurate carotid plaque grading (CPG) is vital to assess the risk of cardiovascular and cerebrovascular diseases. Due to the small size and high intra-class variability of plaque, CPG is commonly evaluated using a combination of transverse and longitudinal ultrasound views in clinical practice. However, most existing deep learning-based multi-view classification methods focus on feature fusion across different views, neglecting the importance of representation learning and the difference in class features. To address these issues, we propose a novel Corpus-View-Category Refinement Framework (CVC-RF) that processes information from Corpus-, View-, and Category-levels, enhancing model performance. Our contribution is four-fold. First, to the best of our knowledge, we are the foremost deep learning-based method for CPG according to the latest Carotid Plaque-RADS guidelines. Second, we propose a novel center-memory contrastive loss, which enhances the network's global modeling capability by comparing with representative cluster centers and diverse negative samples at the Corpus level. Third, we design a cascaded down-sampling attention module to fuse multi-scale information and achieve implicit feature interaction at the View level. Finally, a parameter-free mixture-of-experts weighting strategy is introduced to leverage class clustering knowledge to weight different experts, enabling feature decoupling at the Category level. Experimental results indicate that CVC-RF effectively models global features via multi-level refinement, achieving state-of-the-art performance in the challenging CPG task.