Deep generative priors for 3D brain analysis

2025-10-16

AI Summary

Traditional mathematical priors struggle to capture complex anatomical structures in brain MRI inverse problems. Method: We propose a data-driven score-based diffusion model as a generic generative prior embedded within a Bayesian inversion framework. The approach requires no paired training data, seamlessly integrating the forward physical model and domain-specific knowledge to jointly address super-resolution, bias-field correction, and image inpainting. Contribution/Results: This work presents the first application of diffusion models as a universal prior in medical imaging inverse problems. By combining unsupervised learning with physics-based constraints, it ensures anatomical consistency. Evaluated on multi-center clinical and research MRI datasets, our method significantly outperforms conventional optimization-based techniques and state-of-the-art deep learning models, achieving new SOTA performance in reconstruction fidelity and structural integrity.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• 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: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Diffusion models have recently emerged as powerful generative models in medical imaging. However, it remains a major challenge to combine these data-driven models with domain knowledge to guide brain imaging problems. In neuroimaging, Bayesian inverse problems have long provided a successful framework for inference tasks, where incorporating domain knowledge of the imaging process enables robust performance without requiring extensive training data. However, the anatomical modeling component of these approaches typically relies on classical mathematical priors that often fail to capture the complex structure of brain anatomy. In this work, we present the first general-purpose application of diffusion models as priors for solving a wide range of medical imaging inverse problems. Our approach leverages a score-based diffusion prior trained extensively on diverse brain MRI data, paired with flexible forward models that capture common image processing tasks such as super-resolution, bias field correction, inpainting, and combinations thereof. We further demonstrate how our framework can refine outputs from existing deep learning methods to improve anatomical fidelity. Experiments on heterogeneous clinical and research MRI data show that our method achieves state-of-the-art performance producing consistent, high-quality solutions without requiring paired training datasets. These results highlight the potential of diffusion priors as versatile tools for brain MRI analysis.

Problem

• Combining diffusion models with domain knowledge for brain imaging
• Replacing classical priors to capture complex brain anatomy structure
• Solving diverse medical imaging inverse problems without paired training data

Innovation

• Using diffusion models as anatomical priors
• Leveraging score-based diffusion with flexible forward models
• Refining outputs to improve anatomical fidelity