Hierarchical Diffusion Framework for Pseudo-Healthy Brain MRI Inpainting with Enhanced 3D Consistency
This work addresses a domain-specific problem for medical imaging researchers and practitioners by providing a more data-efficient and consistent method for preprocessing pathological brain MRI scans, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of pseudo-healthy brain MRI inpainting, where existing methods suffer from either slice-wise discontinuities or high data demands, by proposing a hierarchical diffusion framework that uses two perpendicular 2D stages to achieve enhanced 3D consistency and outperforms state-of-the-art baselines in realism and consistency.
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.