Surf-CDM: Score-Based Surface Cold-Diffusion Model For Medical Image Segmentation
This work addresses medical image segmentation for healthcare applications, offering improved accuracy and uncertainty estimation, but it is incremental as it builds on existing diffusion models.
The authors tackled medical image segmentation by proposing a conditional score-based generative model that uses a parametric surface representation for masks, adapted with cold-diffusion for faster convergence, and it outperformed popular methods in accuracy on a dataset of 65 echocardiogram videos (2230 frames).
Diffusion models have shown impressive performance for image generation, often times outperforming other generative models. Since their introduction, researchers have extended the powerful noise-to-image denoising pipeline to discriminative tasks, including image segmentation. In this work we propose a conditional score-based generative modeling framework for medical image segmentation which relies on a parametric surface representation for the segmentation masks. The surface re-parameterization allows the direct application of standard diffusion theory, as opposed to when the mask is represented as a binary mask. Moreover, we adapted an extended variant of the diffusion technique known as the "cold-diffusion" where the diffusion model can be constructed with deterministic perturbations instead of Gaussian noise, which facilitates significantly faster convergence in the reverse diffusion. We evaluated our method on the segmentation of the left ventricle from 65 transthoracic echocardiogram videos (2230 echo image frames) and compared its performance to the most popular and widely used image segmentation models. Our proposed model not only outperformed the compared methods in terms of segmentation accuracy, but also showed potential in estimating segmentation uncertainties for further downstream analyses due to its inherent generative nature.