Channel-Spatial Gated and Contour Aligned Latent Diffusion for Medical Image Segmentation

Diffusion models have recently been employed for medical image segmentation due to their strong generative priors and ability to model rational anatomical structure consistent with real distribution. However, existing latent diffusion segmentation methods are largely adapted from natural image synthesis and remain constrained by parameter-heavy U-Net architectures, static skip connections, and insufficient contour-aware supervision. To align the latent diffusion paradigm with medical image segmentation tasks, we propose $\text{GCLDS}$, a channel-spatial $\text{G}$ated and $\text{C}$ontour Aligned $\text{L}$atent $\text{D}$iffusion $\text{S}$egmentation framework, with three bottom-up improvements at the architecture, feature, and loss levels. Our method redesigns the diffusion backbone with a compressed bottleneck to reduce parameter count and computational overhead without compromising segmentation accuracy. We design a channel-spatial disentangled gated skip connection to enable adaptive, context- and timestep-aware feature fusion during the denoising process. In addition, a contour alignment optimization loss is derived to enhance boundary localization and improve anatomical plausibility. Extensive experiments on multiple benchmarks demonstrate that GCLDS achieves superior segmentation accuracy and boundary delineation while maintaining efficient computation consumption.