Deep generative priors for 3D brain analysis
Ana Lawry Aguila, Dina Zemlyanker, You Cheng, Sudeshna Das, Daniel C. Alexander, Oula Puonti, Annabel Sorby-Adams, W. Taylor Kimberly, Juan Eugenio Iglesias
TL;DR
The paper introduces a general-purpose diffusion-prior framework for brain MRI inverse problems, integrating a data-driven brain prior with flexible forward models to handle restoration, inpainting, and refinement without requiring paired data or acquisition parameters. It trains a large, diverse 1 mm isotropic brain MRI prior and uses the DAPS posterior-sampling method to generate principled reconstructions that respect anatomical structure. Across restoration, inpainting, and refinement tasks on heterogeneous clinical and ultra-low-field data, the approach achieves state-of-the-art performance and produces anatomically plausible results, outperforming both traditional priors and task-specific deep-learning baselines. The work demonstrates the potential of diffusion priors as versatile tools for robust, data-efficient brain MRI analysis with broad clinical and research impact.
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.