Diffusion Models for Implicit Image Segmentation Ensembles

TL;DR

This paper introduces a novel medical image segmentation method using diffusion models that generates multiple segmentation hypotheses and uncertainty maps, improving accuracy and interpretability.

Contribution

It adapts diffusion models for lesion segmentation, enabling image-specific training and sampling that produce an implicit ensemble and uncertainty estimation.

Findings

Achieves competitive segmentation accuracy on BRATS2020 dataset.

Provides detailed pixel-wise uncertainty maps.

Demonstrates improved robustness through implicit ensemble sampling.

Abstract

Diffusion models have shown impressive performance for generative modelling of images. In this paper, we present a novel semantic segmentation method based on diffusion models. By modifying the training and sampling scheme, we show that diffusion models can perform lesion segmentation of medical images. To generate an image specific segmentation, we train the model on the ground truth segmentation, and use the image as a prior during training and in every step during the sampling process. With the given stochastic sampling process, we can generate a distribution of segmentation masks. This property allows us to compute pixel-wise uncertainty maps of the segmentation, and allows an implicit ensemble of segmentations that increases the segmentation performance. We evaluate our method on the BRATS2020 dataset for brain tumor segmentation. Compared to state-of-the-art segmentation models, our approach yields good segmentation results and, additionally, detailed uncertainty maps.