Stable Diffusion Segmentation for Biomedical Images with Single-step Reverse Process
This work addresses efficiency challenges in medical image segmentation for healthcare applications, representing an incremental improvement over existing diffusion methods.
The authors tackled the problem of high resource and time requirements in diffusion models for medical image segmentation by introducing SDSeg, a latent diffusion model that uses a single-step reverse process and single sample, achieving state-of-the-art results on five benchmark datasets.
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