Denoising Diffusion Medical Models
This addresses data scarcity in biomedical image analysis, though it is incremental as it applies an existing diffusion method to a specific domain.
The authors tackled the problem of limited annotated medical images for segmentation by introducing a generative model that synthesizes realistic X-ray images and segmentations, leading to improved segmentation performance with a vanilla UNet using this data augmentation.
In this study, we introduce a generative model that can synthesize a large number of radiographical image/label pairs, and thus is asymptotically favorable to downstream activities such as segmentation in bio-medical image analysis. Denoising Diffusion Medical Model (DDMM), the proposed technique, can create realistic X-ray images and associated segmentations on a small number of annotated datasets as well as other massive unlabeled datasets with no supervision. Radiograph/segmentation pairs are generated jointly by the DDMM sampling process in probabilistic mode. As a result, a vanilla UNet that uses this data augmentation for segmentation task outperforms other similarly data-centric approaches.