SO-Mamba: state-ownership Mamba for unrolled MRI reconstruction
SO-Mamba: state-ownership Mamba for unrolled MRI reconstruction
Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State-space models such as Mamba provide efficient long-range modeling, making them attractive learned regularizers for unrolled reconstruction. However, in a data-consistency-coupled unrolled solver, different stages operate on different reconstruction iterates, where the resident carrier should preserve coherent reconstruction content across stages while stage-dependent non-resident evidence is tied to the current update. Treating these roles uniformly can place persistent resident-carrier evidence and update-dependent non-resident evidence into the same recurrent content route. We therefore propose SO-Mamba, a state-ownership Mamba regularizer that assigns reconstruction evidence within each Mamba stage to recurrent residency, state-interface access, and non-state output correction. SO-Mamba implements this ownership rule with a State-Ownership Router (SOR), which constructs a resident carrier for recurrent content and routes non-resident evidence to affine modulation of the B/C state interfaces and an output correction outlet. The resident carrier supplies the Mamba content route, while the non-resident evidence stream adapts the state interfaces and contributes through the output outlet without entering the recurrent content route. We further introduce a two-level outer-band leakage diagnostic that separates hidden-state storage from readout expression by measuring outer-band energy in the selective-scan state trajectory and the post-scan Mamba readout. Experiments on five public MRI reconstruction benchmarks spanning diverse anatomies, sampling patterns, and coil configurations show that SO-Mamba consistently improves over CNN-, Transformer-, and Mamba-based baselines with competitive computational efficiency.
cs.CV
Fang, Pengcheng
7f3b5cc1-6fd3-4e94-8338-0820f3fbd189
Chen, Hongli
3980d1d6-2d2d-442d-81a8-54488aee6aaa
Tang, Fangfang
774813e9-d906-43b1-9d30-16ad10a2259a
Liu, Feng
30a0aea2-0008-4d2b-bfb9-28527884967c
Cai, Xiaohao
de483445-45e9-4b21-a4e8-b0427fc72cee
Shan, Shanshan
fb7e00e7-30c5-42e9-8430-dfa31337b925
21 May 2026
Fang, Pengcheng
7f3b5cc1-6fd3-4e94-8338-0820f3fbd189
Chen, Hongli
3980d1d6-2d2d-442d-81a8-54488aee6aaa
Tang, Fangfang
774813e9-d906-43b1-9d30-16ad10a2259a
Liu, Feng
30a0aea2-0008-4d2b-bfb9-28527884967c
Cai, Xiaohao
de483445-45e9-4b21-a4e8-b0427fc72cee
Shan, Shanshan
fb7e00e7-30c5-42e9-8430-dfa31337b925
[Unknown type: UNSPECIFIED]
Abstract
Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State-space models such as Mamba provide efficient long-range modeling, making them attractive learned regularizers for unrolled reconstruction. However, in a data-consistency-coupled unrolled solver, different stages operate on different reconstruction iterates, where the resident carrier should preserve coherent reconstruction content across stages while stage-dependent non-resident evidence is tied to the current update. Treating these roles uniformly can place persistent resident-carrier evidence and update-dependent non-resident evidence into the same recurrent content route. We therefore propose SO-Mamba, a state-ownership Mamba regularizer that assigns reconstruction evidence within each Mamba stage to recurrent residency, state-interface access, and non-state output correction. SO-Mamba implements this ownership rule with a State-Ownership Router (SOR), which constructs a resident carrier for recurrent content and routes non-resident evidence to affine modulation of the B/C state interfaces and an output correction outlet. The resident carrier supplies the Mamba content route, while the non-resident evidence stream adapts the state interfaces and contributes through the output outlet without entering the recurrent content route. We further introduce a two-level outer-band leakage diagnostic that separates hidden-state storage from readout expression by measuring outer-band energy in the selective-scan state trajectory and the post-scan Mamba readout. Experiments on five public MRI reconstruction benchmarks spanning diverse anatomies, sampling patterns, and coil configurations show that SO-Mamba consistently improves over CNN-, Transformer-, and Mamba-based baselines with competitive computational efficiency.
Text
2605.22031v1
- Author's Original
More information
Published date: 21 May 2026
Keywords:
cs.CV
Identifiers
Local EPrints ID: 514360
URI: https://eprints.soton.ac.uk/id/eprint/514360
PURE UUID: f3a30059-c147-46d9-b9ef-33b6e0534ee8
Catalogue record
Date deposited: 17 Sep 2026 14:03
Last modified: 18 Sep 2026 02:27
Export record
Altmetrics
Contributors
Author:
Pengcheng Fang
Author:
Hongli Chen
Author:
Fangfang Tang
Author:
Feng Liu
Author:
Xiaohao Cai
Author:
Shanshan Shan
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics