STAIRS: Staging the Inverse Problem via Admissible-Support Scheduling for Unrolled MRI Reconstruction
Authors: Xiangjian Hou, Chang Ni, Chao Qin, Zhiwei Tan, Xin Wang, Xinrui Ye, Rong-Rong Chen, Chun Yuan, Xiaodong Ma
Organizations: Department of Radiology and Imaging Sciences and the Department of Electrical and Computer Engineering, University of Utah, Salt Lake City, UT 84112, USA · Department of Radiology and Imaging Sciences and the Department of Biomedical Engineering, University of Utah, Salt Lake City, UT 84112, USA · Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · Department of Electrical and Computer Engineering, University of Washington, Seattle, WA 98195, USA · Department of Electrical and Computer Engineering, University of Utah, Salt Lake City, UT 84112, USA · Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, UT 84112, USA · Department of Radiology, University of Washington, Seattle, WA 98195, USA
Accelerated magnetic resonance imaging (MRI) forms images from incomplete Fourier measurements, shifting acquisition burden to computational reconstruction. Deep unrolled networks interleave learned regularization and data consistency, yet typically estimate the full unmeasured spectrum at every cascade. We propose STAIRS (Staging the Inverse Problem via Admissible-Support Scheduling), which projects intermediate reconstructions onto nested Fourier supports that expand to the full spectrum and conditions each update on its support transition. Conditional increments of a regularized log-determinant score of training covariance define a normalized spectral coordinate, accounting for dependencies between newly and previously admitted frequencies. Dyadic targets allocate larger coordinate increments to earlier cascades and are mapped to fixed supports before training, enabling coarse-to-fine reconstruction with unchanged sampling masks and data consistency. On fastMRI and Stanford2D, STAIRS improves matched Transformer (HUMUSNet) and convolutional (NAFNet) backbones in single- and multi-coil reconstruction, including radiologist-annotated pathology regions. It also outperforms predictor-based progression with lower parameter overhead and inference latency. Stage-wise analysis shows repeated error correction by projection and lower intermediate reconstruction errors than the backbones alone throughout support expansion. Ablations favor dyadic allocation over uniform expansion for square and line-band supports and over manual front-loading for square windows. Support projection alone improves reconstruction, and transition conditioning strengthens the gain. Cross-dataset evaluation shows improvements for both backbones in both directions. Support allocation thus complements regularizer design in unrolled MRI reconstruction.
Figures & tables
Fig. 1: STAIRS overview. Each cascade applies a learned update, physical data consistency, and an admissible-support projection on a fixed reconstruction grid. The support schedule is computed once from training spectra using a correlation-aware log-determinant score and remains fixed during training and inference. All acquired measurements are used at every DC step, and the final cascade admits the full Fourier grid.
Fig. 2: Empirical spectral coordinates and realized support schedules for four MRI settings. Curves show the spectral coordinate Ej as a function of support width; markers indicate the selected stage supports. Insets magnify the region near full support.
Method
fastMRI knee
Stanford2D
PSNR ↑
SSIM ↑
NMSE ↓
PSNR ↑
SSIM ↑
NMSE ↓
Zero-filled
27.42
0.7000
0.0704
29.24
0.7175
0.0948
U-Net [ 44 ]
34.18
0.8601
0.0151
33.77
0.8953
0.0333
E2E-VarNet [ 8 ]
36.81
0.8873
0.0090
35.80
0.9118
0.0269
HUMUSNet [ 11 ]
36.84
0.8879
0.0092
37.36
0.9266
0.0183
+ PDAC [ 22 ]
37.12
0.8905
0.0085
37.77
0.9269
0.0169
TABLE I: Quantitative results of 8× accelerated multi-coil MRI reconstruction on fastMRI knee and Stanford2D. Best results within each host are in teal .
Method
All ROIs
Meniscus & cartilage
Ligament & support
Bone
Joint & soft tissue
( n=2498 )
( n=1414 )
( n=347 )
( n=360 )
( n=377 )
PSNR ↑
SSIM ↑
NMSE ↓
PSNR ↑
SSIM ↑
NMSE ↓
PSNR ↑
SSIM ↑
NMSE ↓
PSNR ↑
SSIM ↑
NMSE ↓
PSNR ↑
SSIM ↑
NMSE ↓
HUMUSNet
35.39
0.8922
0.0184
35.89
0.9131
0.0206
35.04
0.8739
0.0207
34.36
0.8196
0.0205
34.84
0.9003
0.0064
+ PDAC
35.44
0.8911
0.0183
35.92
0.9121
0.0205
35.11
0.8733
0.0202
34.40
0.8162
0.0204
34.90
0.9001
0.0064
+ STAIRS
35.64
0.8950
0.0174
36.12
0.9154
0.0196
35.33
0.8785
0.0191
34.58
0.8218
0.0194
35.11
0.9034
0.0061
NAFNet
35.51
0.8943
0.0181
35.98
0.9143
0.0203
35.16
0.8787
0.0194
34.52
0.8239
0.0198
35.02
0.9029
0.0062
TABLE II: ROI-based results of 8× multi-coil reconstruction within fastMRI+ pathology bounding boxes, pooled and per anatomical group. Best results within each host are in teal .
Fig. 3: Stage-wise reconstruction dynamics in 8× multi-coil MRI. (a)–(c) Intermediate k -space NMSE and (d)–(f) relative NMSE reduction after projection; error bars show pointwise 95% volume-bootstrap confidence intervals. (g), (h) Projection effects in effusion and ACL ROIs, with image-space NMSE reported below each reconstructed crop.
Fig. 4: Qualitative comparison of 8× multi-coil reconstructions on fastMRI knee. Radiologist-annotated ROIs from fastMRI+ are magnified alongside their error maps. The top ROI shows the curved border of a joint effusion; the bottom ROI shows bone contours in a bone-injury case. Cyan arrows highlight local error reductions with STAIRS.
Fig. 5: Qualitative comparison of 8× multi-coil reconstructions on Stanford2D. The top ROI shows small high-signal structures and tissue borders; the bottom ROI shows curved tissue interfaces. Cyan arrows highlight local error reductions with STAIRS.
Method
fastMRI → Stanford2D
Stanford2D → fastMRI
PSNR ↑
SSIM ↑
NMSE ↓
PSNR ↑
SSIM ↑
NMSE ↓
HUMUSNet
34.14
0.8703
0.0382
33.62
0.8516
0.0171
+ PDAC
33.57
0.8674
0.0443
32.25
0.8227
0.0232
+ STAIRS
34.93
0.8901
0.0343
33.77
0.8557
0.0167
NAFNet
33.77
0.8830
0.0440
32.16
0.8287
0.0236
+ STAIRS
34.50
0.8899
0.0368
33.22
0.8468
0.0188
TABLE III: Cross-dataset evaluation of 8× multi-coil reconstruction (A → B: trained on A, tested on B). Best results within each host are in teal .
Fig. 6: Qualitative comparison of 8× single-coil reconstructions on fastMRI knee. The top ROI shows the lobulated outline of a soft-tissue lesion; the bottom ROI shows narrow tissue interfaces in a joint-effusion case. Cyan arrows highlight local error reductions with STAIRS.
Method
4×
8×
PSNR ↑
SSIM ↑
NMSE ↓
PSNR ↑
SSIM ↑
NMSE ↓
Zero-filled
29.49
0.6541
0.0532
26.84
0.5500
0.0893
U-Net [ 44 ]
31.88
0.7142
0.0357
29.78
0.6424
0.0511
D5C5 [ 4 ]
32.25
0.7256
0.0332
29.65
0.6457
0.0512
OUCR [ 45 ]
32.61
0.7354
0.0315
30.59
0.6634
0.0443
ReconFormer [ 10 ]
32.73
0.7383
0.0310
30.89
0.6697
0.0429
TABLE IV: Quantitative results of 4× and 8× accelerated single-coil MRI reconstruction on fastMRI knee. Best results within each host are in teal .
Variant
Support
Conditioning
PSNR ↑
SSIM ↑
NMSE ↓
HUMUSNet
37.36
0.9266
0.0183
Conditioning only
✓
37.26
0.9144
0.0189
Support only
✓
37.55
0.9282
0.0176
STAIRS
✓
✓
37.96
0.9316
0.0163
TABLE V: Ablation of support projection and transition conditioning (Sec. III-D ) for 8× multi-coil reconstruction on Stanford2D with the HUMUSNet host. Best results are in teal .
Fig. 7: Expansion of square supports under alternative allocations on Stanford2D MC × 8. Solid curves use spectral targets; the dashed uniform-width curve is a geometric reference.
Schedule
PSNR ↑
SSIM ↑
NMSE ↓
Baseline (full support)
37.36
0.9266
0.0183
Square windows
Uniform width
37.23
0.9226
0.0192
Back-loaded targets
36.41
0.9196
0.0227
Uniform targets
36.96
0.9229
0.0204
Moderate front-loaded
37.51
0.9275
0.0181
TABLE VI: Ablation of stage allocation with square and line-band supports for 8× multi-coil reconstruction on Stanford2D with the HUMUSNet host. Best results within each support family are highlighted in teal .
Median
Mean
25th pct.
75th pct.
τ(×10−5)
4.825
4.668
3.707
5.695
C1
78
78
76
78
C2
186
186
182
190
C3
268
268
266
270
C4
318
318
316
320
C5
362
362
360
362
TABLE VII: Sensitivity of the Stanford2D multi-coil schedule to the lower-tail estimate of τ . Stage widths and their maximum absolute changes from the default median schedule are in pixels.
Accelerated MRI reconstruction recovers diagnostic images from undersampled k-space data to reduce scan time while preserving anatomical and quantitative information.
Unrolled variational networks achieve state-of-the-art performance for accelerated MRI reconstruction, but standard end-to-end training becomes prohibitively memory intensive as the number and width of cascades increase. We propose a memory-efficient training framework that updates a randomly sampled cascade while retaining supervision from the final reconstruction loss. The error signal is propagated from the end of the chain to the sampled cascade using an activation-light backward pass that avoids storing full chain activations, thereby decoupling training memory from chain length. A time-conditioned network shared across cascades further keeps the parameter count independent of chain length. The backward pass is approximate only through frozen normalization statistics, and a trained exact gradient control shows the approximation leaves reconstruction quality unchanged. The framework remains trainable at chain lengths and cascade widths where standard end-to-end backpropagation exhausts GPU memory. On fastMRI single-coil knee and multi-coil brain reconstruction, our method consistently outperforms other local training approaches. On high-SNR knee slices, our method surpasses E2E-VarNet at 8× and matches it at 4×, while on the complete brain validation set it surpasses E2E-VarNet at 8× and achieves comparable performance at 4×, with fewer parameters, lower peak memory, and faster per-iteration training. Code is available at https://github.com/emehillaj/scalable-unrolled-mri.
Emiljo Mëhillaj, Ender Konukoglu
Computer Vision Lab, ETH Zurich, Zurich, Switzerland · LOOP Zurich - Medical Research Center, Zurich, Switzerland
Generative MRI reconstruction maps an initial source distribution to the target image distribution along a learned recovery trajectory. Common generative methods, such as diffusion and flow, typically learn fine-grained local dynamics whose integration defines this global mapping, hence requiring many network evaluations at inference. Existing few-step sampling approaches can lower computational burden by approximating large transformations from local dynamics, albeit at the expense of reconstruction fidelity. FLEX-MRI instead partitions recovery into a small number of finite intervals between retained states defined by progressive changes in k-space support, and directly learns the reconstruction change across each interval. Because such finite transitions can admit multiple plausible outcomes, FLEX-MRI combines support-relaxed finite-transition learning with stochastic exploration. During training, randomized k-space sampling masks define finite-transition targets with varying support, while the prediction loss remains unrestricted by each individual mask. At inference, FLEX-MRI perturbs a random subset of currently estimated k-space coefficients, allowing the learned predictor to stochastically explore alternative transition paths. Each predicted state is then reconciled with the acquired measurements through data consistency. We theoretically show that this stochastic exploration induces nonzero transition-level variation through the learned recovery map and data consistency without requiring an auxiliary generative sampler. Experiments on multi-coil MRI datasets show that FLEX-MRI outperforms competing methods while maintaining computational efficiency comparable to few-step baselines.
Muhammad Usama Mirza, Esin Öztürk Işık, Tolga Çukur
Dept. of Electrical-Electronics Engineering and National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey, 06800 · Institute of Biomedical Engineering, Bogazici University, Istanbul, Turkey, 34684
Deep-learning unrolled networks are the leading approach to accelerated MRI reconstruction. State-of-the-art models such as PromptMR+ learn a distinct block for every cascade, so their size grows with the number of cascades. Sharing one block across iterations avoids adding parameters, but earlier shared-weight models typically used a tiny block and produced worse images than models with distinct weights. Therefore, it remained unclear whether weight sharing itself or the choice of block was the problem. Recent advances in looped transformers, which reuse the same block across layers, show that they can match or outperform their distinct-weight counterparts on several tasks. Motivated by this, we propose LoopMR, which reuses a single Restormer block at every iteration as its core. Besides the current image estimate, the block receives data-consistency inputs and latent images. On four datasets covering the brain (CC359), knee (fastMRI), heart (CMRxRecon2023) and carotid (in-house), LoopMR significantly outperforms E2E-VarNet, PromptMR and PromptMR+ in PSNR and SSIM at every acceleration factor (p < 0.01), with about 1/9 of PromptMR+'s parameters (10.3M versus 92.9M). It also keeps its lead at unseen acceleration factors and on an unseen dataset. With our transformer block, the shared model matches or outperforms its distinct-weight counterpart at 6, 12 and 24 iterations. At a fixed number of iterations, shared transformer blocks match or outperform their distinct-weight versions, while shared CNN blocks perform worse. These results suggest that looping one well-chosen block can outperform stacking distinct cascades in MRI reconstruction, with a fraction of the parameters.
Yimeng He, Yibin Xie, Yi Zheng +7
All authors are with Cedars-Sinai Medical Center, Los Angeles, CA 90048 USA. Yimeng He is with the Biomedical Imaging Research Institute and the Department of Computational Biomedicine · All authors are with Cedars-Sinai Medical Center, Los Angeles, CA 90048 USA. the other authors are with the Biomedical Imaging Research Institute · All authors are with Cedars-Sinai Medical Center, Los Angeles, CA 90048 USA. Xiuzhen Huang is with the Department of Computational Biomedicine