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

2025-02-06

AI Summary

To address the weak interpretability and difficulty in quantifying predictive uncertainty in 2D medical image classification, this paper proposes a novel discriminative paradigm based on class-conditional diffusion models that performs classification via reconstruction error differences—without requiring explicit supervision labels. Our key contributions are: (1) the first diffusion-model-driven unsupervised/weakly supervised framework for medical image classification; (2) a reconstruction-oriented majority voting mechanism to enhance robustness; and (3) intrinsic support for pixel-level saliency map generation and calibrated confidence estimation. Evaluated on CheXpert and ISIC, our method achieves performance competitive with state-of-the-art discriminative models while significantly improving clinical decision trustworthiness and reliability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Graphical Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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/

Problem

• Medical image classification using diffusion models
• Explainability and uncertainty in diagnostic models
• Performance comparison with discriminative classifiers

Innovation

• Class conditional diffusion models
• Majority voting scheme improves performance
• Explainable uncertainty quantification