Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free
- URL: http://arxiv.org/abs/2502.03687v1
- Date: Thu, 06 Feb 2025 00:37:21 GMT
- Title: Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free
- Authors: Gian Mario Favero, Parham Saremi, Emily Kaczmarek, Brennan Nichyporuk, Tal Arbel,
- Abstract summary: This work presents the first exploration of the potential of class conditional diffusion models for 2D medical image classification.
We develop a novel majority voting scheme shown to improve the performance of medical diffusion classifiers.
Experiments on the CheXpert and ISIC Melanoma skin cancer datasets demonstrate that foundation and trained-from-scratch diffusion models achieve competitive performance.
- Score: 0.7624308578421438
- License:
- 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/
Related papers
- Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis [55.959002385347645]
Scaling by training on large datasets has been shown to enhance the quality and fidelity of image generation and manipulation with diffusion models.
Latent Drifting enables diffusion models to be conditioned for medical images fitted for the complex task of counterfactual image generation.
Our results demonstrate significant performance gains in various scenarios when combined with different fine-tuning schemes.
arXiv Detail & Related papers (2024-12-30T01:59:34Z) - FairDiffusion: Enhancing Equity in Latent Diffusion Models via Fair Bayesian Perturbation [21.010861381369104]
We present the first comprehensive study on the fairness of medical text-to-image diffusion models.
We introduce FairDiffusion, an equity-aware latent diffusion model that enhances fairness in both image generation quality and semantic correlation of clinical features.
We also design and curate FairGenMed, the first dataset for studying the fairness of medical generative models.
arXiv Detail & Related papers (2024-12-29T06:33:37Z) - Mediffusion: Joint Diffusion for Self-Explainable Semi-Supervised Classification and Medical Image Generation [3.046689922445082]
We introduce Mediffusion -- a new method for semi-supervised learning with explainable classification based on a joint diffusion model.
We show that our Mediffusion achieves results comparable to recent semi-supervised methods while providing more reliable and precise explanations.
arXiv Detail & Related papers (2024-11-12T23:14:36Z) - StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples.
It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
arXiv Detail & Related papers (2024-08-11T01:22:29Z) - Training Class-Imbalanced Diffusion Model Via Overlap Optimization [55.96820607533968]
Diffusion models trained on real-world datasets often yield inferior fidelity for tail classes.
Deep generative models, including diffusion models, are biased towards classes with abundant training images.
We propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.
arXiv Detail & Related papers (2024-02-16T16:47:21Z) - Bridging Generative and Discriminative Models for Unified Visual
Perception with Diffusion Priors [56.82596340418697]
We propose a simple yet effective framework comprising a pre-trained Stable Diffusion (SD) model containing rich generative priors, a unified head (U-head) capable of integrating hierarchical representations, and an adapted expert providing discriminative priors.
Comprehensive investigations unveil potential characteristics of Vermouth, such as varying granularity of perception concealed in latent variables at distinct time steps and various U-net stages.
The promising results demonstrate the potential of diffusion models as formidable learners, establishing their significance in furnishing informative and robust visual representations.
arXiv Detail & Related papers (2024-01-29T10:36:57Z) - Certification of Deep Learning Models for Medical Image Segmentation [44.177565298565966]
We present for the first time a certified segmentation baseline for medical imaging based on randomized smoothing and diffusion models.
Our results show that leveraging the power of denoising diffusion probabilistic models helps us overcome the limits of randomized smoothing.
arXiv Detail & Related papers (2023-10-05T16:40:33Z) - DiffDis: Empowering Generative Diffusion Model with Cross-Modal
Discrimination Capability [75.9781362556431]
We propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process.
We show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks.
arXiv Detail & Related papers (2023-08-18T05:03:48Z) - Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification.
Our generative approach to classification attains strong results on a variety of benchmarks.
Our results are a step toward using generative over discriminative models for downstream tasks.
arXiv Detail & Related papers (2023-03-28T17:59:56Z) - DiffMIC: Dual-Guidance Diffusion Network for Medical Image
Classification [32.67098520984195]
We propose the first diffusion-based model (named DiffMIC) to address general medical image classification.
Our experimental results demonstrate that DiffMIC outperforms state-of-the-art methods by a significant margin.
arXiv Detail & Related papers (2023-03-19T09:15:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.