Flatten Wisely: How Patch Order Shapes Mamba-Powered Vision for MRI Segmentation

TL;DR

This study systematically examines how the order of patch scanning in Mamba-powered MRI segmentation models affects performance, revealing that contiguous spatial paths significantly improve accuracy without additional costs.

Contribution

Introduces MS2D, a parameter-free module for exploring scan paths, and provides the first comprehensive analysis of scan order impact on MRI segmentation performance.

Findings

Scan order significantly affects segmentation accuracy.

Contiguous scan paths outperform disjointed diagonal scans.

Optimal scan paths can improve Dice scores by up to 27 points.

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: $\chi^{2}_{20}=43.9, p=0.0016$), 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.