Stable Diffusion Segmentation for Biomedical Images with Single-step Reverse Process

TL;DR

This paper introduces SDSeg, a novel latent diffusion segmentation model for biomedical images that achieves reliable, stable predictions with a single reverse step and sample, significantly reducing resource requirements.

Contribution

SDSeg is the first latent diffusion segmentation model that enables single-step reverse process and eliminates the need for multiple samples, improving efficiency in medical image segmentation.

Findings

SDSeg outperforms existing methods on five benchmark datasets.

SDSeg produces stable predictions with only one reverse step and sample.

The model demonstrates robustness across diverse imaging modalities.

Abstract

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