Diffusion models have demonstrated their effectiveness across various generative tasks. However, when applied to medical image segmentation, these models encounter several challenges, including significant resource and time requirements. They also necessitate a multi-step reverse process and multiple samples to produce reliable predictions. To address these challenges, we introduce the first latent diffusion segmentation model, named SDSeg, built upon stable diffusion (SD). SDSeg incorporates a straightforward latent estimation strategy to facilitate a single-step reverse process and utilizes latent fusion concatenation to remove the necessity for multiple samples. Extensive experiments indicate that SDSeg surpasses existing state-of-the-art methods on five benchmark datasets featuring diverse imaging modalities. Remarkably, SDSeg is capable of generating stable predictions with a solitary reverse step and sample, epitomizing the model's stability as implied by its name. The code is available at https://github.com/lin-tianyu/Stable-Diffusion-Seg

翻译：扩散模型已在多种生成任务中展现出卓越性能。然而，在医学图像分割领域应用时，这类模型面临若干挑战：需要消耗大量计算资源与时间，必须通过多步逆向过程及多次采样才能获得可靠预测结果。为应对这些挑战，我们提出了首个基于稳定扩散（SD）的潜在扩散分割模型SDSeg。该模型采用简明的潜在估计策略以实现单步逆向过程，并利用潜在融合拼接技术消除多次采样的需求。在涵盖多种成像模式的五个基准数据集上进行的大量实验表明，SDSeg的性能优于现有最先进方法。值得注意的是，SDSeg仅需单次逆向步骤和单次采样即可生成稳定的预测结果，这完美诠释了其名称所蕴含的模型稳定性特性。相关代码已发布于 https://github.com/lin-tianyu/Stable-Diffusion-Seg