Hubei University of Technology / Robarts Research Institute, Western University
Model weights not public. Contact creators for more information.
Self-supervised learning method for carotid plaque segmentation from B-mode ultrasound images, designed to reduce the amount of expert-labeled data needed to train a segmentation network. A level-set-and-least-squares-based deformation procedure synthesizes registration image pairs from unlabeled carotid ultrasound images, and a spatial-transformer-based registration pretext task pretrains a Stacked U-Net (Su-Net) to focus on plaque-contour features before fine-tuning on a small labeled dataset for total plaque area (TPA) segmentation. Evaluated on carotid ultrasound datasets from two different institutions and countries, the method showed robust generalization when trained with only a small number of labeled images.
Architecture
Hybrid
Registration-based self-supervised pretraining (spatial-transformer registration network) combined with a Stacked U-Net (Su-Net) segmentation network for carotid plaque contour delineation
Added to catalog
2026-08-12
Multi-institutional Carotid Plaque Ultrasound Dataset (Hubei / Western University)
Carotid B-mode ultrasound images with expert-delineated plaque contours, drawn from cooperating sites in Canada and China, used to train and externally evaluate self-supervised carotid plaque segmentation across different institutions and countries.
Segmentation of atherosclerotic carotid plaque from B-mode ultrasound images, used to measure total plaque area (TPA)