Metraipolis › archive › dc_61ed4432bbb8
Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing — arXiv:2609.03981
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03981
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:08:44.051Z
- SHA-256 of the archived text
d354d14f21175cf7bddd6be0aa5b3407163bf0f64f54b0d74726cfbe819e439a- Stable URL of this page
https://metraipolis.com/documento/dc_61ed4432bbb8
How to cite
Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing — arXiv:2609.03981 — arXiv (en), https://arxiv.org/abs/2609.03981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_61ed4432bbb8 (Metraipolis archive dc_61ed4432bbb8, sha256 d354d14f21175cf7bddd6be0aa5b3407163bf0f64f54b0d74726cfbe819e439a)
BibTeX
@misc{dc61ed4432bbb8,
title = {Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing — arXiv:2609.03981},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03981},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_61ed4432bbb8; sha256 d354d14f21175cf7bddd6be0aa5b3407163bf0f64f54b0d74726cfbe819e439a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Brain-MRI inpainting replaces a masked region of a scan with synthesized, anatomically plausible healthy tissue, so that analysis tools built for healthy brains can be applied to images they would otherwise reject. On the BraTS local-synthesis benchmark, which ranks submissions on the structural similarity index (SSIM), the peak signal-to-noise ratio, and the mean squared error (MSE) jointly, the strongest recent models are accurate, but several report blurry synthesized regions and attribute this to the mean-seeking behavior of the $\ell_1$ and MSE terms in their training losses. We address this in post-processing, forming a deep ensemble of the two co-first-place 2025 models and training a lightweight residual refiner on the ensemble's own outputs under an $\ell_1$ loss augmented with a structural-similarity term whose weight $\lambda$ we vary. At a moderate $\lambda$ the refiner improves SSIM over the ensemble, from $0.8767$ to $0.8780$ on a held-out reproduction of the official scorer and from $0.8555$ to $0.8572$ on the official validation leaderboard, with essentially no change in MSE. The gain is small but consistent, improving $62.6\%$ of the held-out cases with a signed-rank $p=2.2\times10^{-7}$, whereas over-weighting the structural term reverses it. Two ablations bound the effect. Adding any third model to the two-model ensemble degrades it, and classical unsharp masking fails to improve SSIM at any strength (best $0.8765$ against $0.8767$), so the gain reflects learned rather than indiscriminate sharpening. The result is a cheap, reproducible post-processing stage that improves an already strong ensemble without any large-scale retraining.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.03981 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:47:25.637Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).