Synthesizing Diabetic Foot Ulcer Images with Diffusion Model

TL;DR

This study demonstrates that diffusion models can generate highly realistic synthetic diabetic foot ulcer images, which can aid medical training and research despite current evaluation metrics not fully aligning with clinician judgments.

Contribution

The paper introduces the application of diffusion models for synthesizing diabetic foot ulcer images and evaluates their realism through clinician assessments and various metrics.

Findings

Diffusion models produce visually indistinguishable DFU images.

Clinicians marked 70% of synthetic images as real.

FID and KID metrics do not strongly correlate with clinician judgments.

Abstract

Diabetic Foot Ulcer (DFU) is a serious skin wound requiring specialized care. However, real DFU datasets are limited, hindering clinical training and research activities. In recent years, generative adversarial networks and diffusion models have emerged as powerful tools for generating synthetic images with remarkable realism and diversity in many applications. This paper explores the potential of diffusion models for synthesizing DFU images and evaluates their authenticity through expert clinician assessments. Additionally, evaluation metrics such as Frechet Inception Distance (FID) and Kernel Inception Distance (KID) are examined to assess the quality of the synthetic DFU images. A dataset of 2,000 DFU images is used for training the diffusion model, and the synthetic images are generated by applying diffusion processes. The results indicate that the diffusion model successfully synthesizes visually indistinguishable DFU images. 70% of the time, clinicians marked synthetic DFU images as real DFUs. However, clinicians demonstrate higher unanimous confidence in rating real images than synthetic ones. The study also reveals that FID and KID metrics do not significantly align with clinicians' assessments, suggesting alternative evaluation approaches are needed. The findings highlight the potential of diffusion models for generating synthetic DFU images and their impact on medical training programs and research in wound detection and classification.