Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free

TL;DR

This paper explores class conditional diffusion models for 2D medical image classification, demonstrating they achieve competitive accuracy, are inherently explainable, and can quantify uncertainty, enhancing trustworthiness in clinical applications.

Contribution

It introduces the first application of diffusion models for 2D medical image classification, with a novel voting scheme and analysis of explainability and uncertainty quantification.

Findings

Diffusion classifiers perform competitively with state-of-the-art discriminative models.

The proposed voting scheme improves classification performance.

Diffusion models inherently provide explainability and uncertainty estimates.

Abstract

Discriminative classifiers have become a foundational tool in deep learning for medical imaging, excelling at learning separable features of complex data distributions. However, these models often need careful design, augmentation, and training techniques to ensure safe and reliable deployment. Recently, diffusion models have become synonymous with generative modeling in 2D. These models showcase robustness across a range of tasks including natural image classification, where classification is performed by comparing reconstruction errors across images generated for each possible conditioning input. This work presents the first exploration of the potential of class conditional diffusion models for 2D medical image classification. First, we develop a novel majority voting scheme shown to improve the performance of medical diffusion classifiers. Next, extensive experiments on the CheXpert and ISIC Melanoma skin cancer datasets demonstrate that foundation and trained-from-scratch diffusion models achieve competitive performance against SOTA discriminative classifiers without the need for explicit supervision. In addition, we show that diffusion classifiers are intrinsically explainable, and can be used to quantify the uncertainty of their predictions, increasing their trustworthiness and reliability in safety-critical, clinical contexts. Further information is available on our project page: https://faverogian.github.io/med-diffusion-classifier.github.io/.