An Ordinal Diffusion Model for Generating Medical Images with Different Severity Levels
This work addresses the challenge of generating realistic medical images with ordinal severity levels for applications like medical training or data augmentation, though it appears incremental as it builds on existing diffusion models.
The paper tackled the problem of generating medical images with ordinal severity levels by proposing an Ordinal Diffusion Model (ODM), which achieved higher performance than conventional generative models, particularly for high-severity classes with limited training samples.
Diffusion models have recently been used for medical image generation because of their high image quality. In this study, we focus on generating medical images with ordinal classes, which have ordinal relationships, such as severity levels. We propose an Ordinal Diffusion Model (ODM) that controls the ordinal relationships of the estimated noise images among the classes. Our model was evaluated experimentally by generating retinal and endoscopic images of multiple severity classes. ODM achieved higher performance than conventional generative models by generating realistic images, especially in high-severity classes with fewer training samples.