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: χ202=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.
@article{arxiv.2507.13384,
title = {Flatten Wisely: How Patch Order Shapes Mamba-Powered Vision for MRI Segmentation},
author = {Osama Hardan and Omar Elshenhabi and Tamer Khattab and Mohamed Mabrok},
journal= {arXiv preprint arXiv:2507.13384},
year = {2025}
}
Comments
Submitted to the 2025 IEEE International Conference on Future Machine Learning and Data Science (FMLDS)