{"ID":2894578,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.13384","arxiv_id":"2507.13384","title":"Flatten Wisely: How Patch Order Shapes Mamba-Powered Vision for MRI Segmentation","abstract":"Vision Mamba models promise transformer-level performance at linear computational cost, but their reliance on serializing 2D images into 1D sequences introduces a critical, yet overlooked, design choice: the patch scan order. In medical imaging, where modalities like brain MRI contain strong anatomical priors, this choice is non-trivial. This paper presents the first systematic study of how scan order impacts MRI segmentation. We introduce Multi-Scan 2D (MS2D), a parameter-free module for Mamba-based architectures that facilitates exploring diverse scan paths without additional computational cost. We conduct a large-scale benchmark of 21 scan strategies on three public datasets (BraTS 2020, ISLES 2022, LGG), covering over 70,000 slices. Our analysis shows conclusively that scan order is a statistically significant factor (Friedman test: $χ^{2}_{20}=43.9, p=0.0016$), with performance varying by as much as 27 Dice points. Spatially contiguous paths -- simple horizontal and vertical rasters -- consistently outperform disjointed diagonal scans. We conclude that scan order is a powerful, cost-free hyperparameter, and provide an evidence-based shortlist of optimal paths to maximize the performance of Mamba models in medical imaging.","short_abstract":"Vision Mamba models promise transformer-level performance at linear computational cost, but their reliance on serializing 2D images into 1D sequences introduces a critical, yet overlooked, design choice: the patch scan order. In medical imaging, where modalities like brain MRI contain strong anatomical priors, this cho...","url_abs":"https://arxiv.org/abs/2507.13384","url_pdf":"https://arxiv.org/pdf/2507.13384v1","authors":"[\"Osama Hardan\",\"Omar Elshenhabi\",\"Tamer Khattab\",\"Mohamed Mabrok\"]","published":"2025-07-15T21:37:37Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\",\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}