CTrans-SegDiff: CTransfomer-Based Diffusion Model for Ultrasound Image Segmentation

Deep generative models, particularly diffusion probabilistic models, have recently shown promise in medical ultrasound image segmentation due to their powerful denoising and detail restoration capabilities. However, most existing generative models focus primarily on image enhancement, with limited consideration for segmentation-specific challenges. To address this, we propose CTrans-SegDiff, a novel segmentation framework that integrates a denoising diffusion probabilistic model with a Transformer-enhanced dynamic conditioning mechanism. Specifically, we design a dual-channel dynamic conditioning module to jointly capture lesion-specific semantics and global contextual dependencies, and a Gaussian Distribution Fusion Module (GDFM) to harmonize the fusion of conditioning features with diffusion-encoded representations. Extensive experiments on two ultrasound datasets demonstrate that our method effectively suppresses noise, enhances structural clarity, and achieves superior segmentation performance compared to existing approaches.