A high-frequency feature guided diffusion model for musculoskeletal ultrasound image segmentation | Synapse
April 4, 2026Open Access
A high-frequency feature guided diffusion model for musculoskeletal ultrasound image segmentation
Key Points
To develop a model that improves the accuracy of ultrasound image segmentation in noisy environments.
Developed a high-frequency feature guided diffusion model
Tested the model in various noisy ultrasound conditions
Evaluated segmentation accuracy against standard benchmarks
Achieved precise extraction of structural boundaries in ultrasound images
Demonstrated robustness in challenging noisy conditions
Improved diagnostic capabilities compared to existing methods
Abstract
Our proposed model enables accurate extraction of structural boundaries in noisy ultrasound environments, offering a promising solution for robust and precise ultrasound-assisted clinical diagnosis.