Hubei University of Technology
Model weights not public. Contact creators for more information.
Self-supervised contrastive learning technique for classifying carotid plaques from ultrasound images under label scarcity. In a pretext task, a triplet network takes three augmented views (strong- and weak-augmentation) of each image and promotes their similarity from both feature- and instance-level perspectives to learn effective plaque representations; the resulting encoder is then fine-tuned on labeled ultrasound images for the downstream classification task. FeaCL achieved 83.4% classification accuracy using only 30% of the training data -- a 16.3% improvement over the same network trained without the self-supervised pretext task.
Architecture
Hybrid
Triplet network pretext task with strong- and weak-augmentation views, combining feature-level and instance-level contrastive losses to pretrain an encoder later fine-tuned for carotid plaque classification
Framework
PyTorch
Added to catalog
2026-08-14
In-House Carotid Plaque Ultrasound Dataset (FeaCL)
Carotid plaque type classification (risk stratification) from ultrasound images