Hierarchical Diffusion Framework for Pseudo-Healthy Brain MRI Inpainting with Enhanced 3D Consistency

TL;DR

This paper introduces a hierarchical diffusion framework that uses two perpendicular 2D diffusion models to perform pseudo-healthy brain MRI inpainting, achieving high realism and 3D consistency with less data.

Contribution

It proposes a novel hierarchical approach replacing direct 3D modeling with two 2D stages for improved efficiency and volumetric consistency in MRI inpainting.

Findings

Outperforms state-of-the-art methods in realism

Achieves superior volumetric consistency

Requires less training data

Abstract

Pseudo-healthy image inpainting is an essential preprocessing step for analyzing pathological brain MRI scans. Most current inpainting methods favor slice-wise 2D models for their high in-plane fidelity, but their independence across slices produces discontinuities in the volume. Fully 3D models alleviate this issue, but their high model capacity demands extensive training data for reliable, high-fidelity synthesis -- often impractical in medical settings. We address these limitations with a hierarchical diffusion framework by replacing direct 3D modeling with two perpendicular coarse-to-fine 2D stages. An axial diffusion model first yields a coarse, globally consistent inpainting; a coronal diffusion model then refines anatomical details. By combining perpendicular spatial views with adaptive resampling, our method balances data efficiency and volumetric consistency. Our experiments show our approach outperforms state-of-the-art baselines in both realism and volumetric consistency, making it a promising solution for pseudo-healthy image inpainting. Code is available at https://github.com/dou0000/3dMRI-Consistent-Inpaint.