Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Self-Auditing Residual Drifting for Pathology-Preserving Accelerated Knee MRI

About

Accelerated magnetic resonance imaging reduces acquisition time, but reconstruction from undersampled k-space can blur diagnostically relevant structures or introduce failures that are not captured by global image metrics. We propose SA-RDM-DC, a Self-Auditing Residual generative Drifting Model with Data Consistency for accelerated knee MRI. The method adapts the newly proposed generative drifting paradigm to accelerated MRI by training a physics-conditioned drift field from the zero-filled reconstruction toward the fully sampled residual correction. It predicts image- and missing-k-space residual corrections, enforces data consistency with acquired k-space, uses frequency-aware and residual drifting supervision to recover fine detail, and produces dense error maps and slice-level risk scores in the same inference pass. We evaluate SA-RDM-DC on multi-coil fastMRI knee data at acceleration factors of 4, 8, and 12, with fastMRI+ pathology annotations for region-level and classifier-based task preservation, and on SKM-TEA for zero-shot and fine-tuned protocol-shift evaluation. Compared with zero-filled reconstruction, UNet-image-SENSE, DC-UNet, Score-Diffusion, ELF-Diff, SENSE-VarNet, and MoDL baselines, SA-RDM-DC achieves the highest SSIM across fastMRI acceleration factors while retaining subsecond per-slice inference and avoiding the long sampling time of iterative diffusion baselines. In pathology-aware analysis, SA-RDM-DC preserves lesion-region structural fidelity and reduces meniscus prediction instability. Its self-auditing scores strongly identify high-error reconstructions on fastMRI and partially transfer as a selective-review signal under SKM-TEA protocol shift. These results support reconstruction evaluation that jointly considers image fidelity, pathology preservation, runtime, and case-specific reliability.

Qing Lyu, Jianxu Wang, Mohammad Kawas, Ge Wang, Christopher T. Whitlow• 2026

Related benchmarks

TaskDatasetResultRank
MRI ReconstructionfastMRI knee (val)
Avg SSIM86.6
29
MRI ReconstructionSKM-TEA (protocol-shift evaluation)
SSIM82.63
14
Accelerated Knee MRI ReconstructionfastMRI+ R=4 (test)
ROI SSIM0.948
8
Accelerated Knee MRI ReconstructionfastMRI+ R=8 (test)
ROI SSIM0.91
8
Accelerated Knee MRI ReconstructionfastMRI+ R=12 (test)
ROI SSIM0.877
8
Showing 5 of 5 rows

Other info

Follow for update