{"ID":2891515,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17911","arxiv_id":"2507.17911","title":"Hierarchical Diffusion Framework for Pseudo-Healthy Brain MRI Inpainting with Enhanced 3D Consistency","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.","short_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, b...","url_abs":"https://arxiv.org/abs/2507.17911","url_pdf":"https://arxiv.org/pdf/2507.17911v1","authors":"[\"Dou Hoon Kwark\",\"Shirui Luo\",\"Xiyue Zhu\",\"Yudu Li\",\"Zhi-Pei Liang\",\"Volodymyr Kindratenko\"]","published":"2025-07-23T20:21:29Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":611889,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2891515,"paper_url":"https://arxiv.org/abs/2507.17911","paper_title":"Hierarchical Diffusion Framework for Pseudo-Healthy Brain MRI Inpainting with Enhanced 3D Consistency","repo_url":"https://github.com/dou0000/3dMRI-Consistent-Inpaint","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}