MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstruction
About
Undersampled magnetic resonance imaging (MRI) reconstruction seeks to recover temporally or contrast-varying image series from incomplete multicoil k-space data while preserving state-dependent fidelity for dynamic and quantitative MRI (qMRI). Existing scan-specific implicit neural representations (INRs) often use monolithic spatiotemporal coordinate fields, explicit subspaces, motion or deformation models, calibration variables, or sequence-specific quantitative signal models. These design choices can limit flexibility in sharing spatial information while adapting image synthesis across acquisition states. Moreover, many INR-based baselines remain computationally demanding, typically requiring per-scan optimization times on the order of hundreds to thousands of seconds. We propose MoE-dqINR, a scan-specific multicoil MRI reconstruction framework that factorizes the image-domain representation into shared spatial experts and a state-conditioned routing pathway. Spatial experts encode reusable coordinate-dependent image content, whereas routing weights, conditioned on ordered acquisition states, synthesize each dynamic frame or contrast state from a common expert bank. The representation is coupled to a multicoil MRI forward model, uses the normalized state index to drive routing in both dynamic and quantitative MRI. By separating shared spatial representation from state-dependent synthesis, the framework provides an image-first architecture for dynamic and quantitative MRI while reducing scan-specific INR optimization to approximately 30 s per scan in our experiments. The proposed formulation establishes state-conditioned mixture-of-experts INR as a scan-specific multicoil MRI reconstruction prior that unifies shared spatial representation, dynamic- and qMRI-specific synthesis, and practical per-scan efficiency.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Cine MRI reconstruction | OCMR cine AF 2x 0.55T (test) | PSNR34.26 | 10 | |
| Cine MRI reconstruction | OCMR cine (AF 4x) 0.55T (test) | PSNR31.86 | 10 | |
| Cine MRI reconstruction | OCMR cine (AF 6x) 0.55T (test) | PSNR30.63 | 10 | |
| Cine MRI reconstruction | CMRxRecon AF 4x | PSNR37.31 | 10 | |
| Cine MRI reconstruction | CMRxRecon AF 6x | PSNR35.77 | 10 | |
| Cine MRI reconstruction | CMRxRecon AF 8x | PSNR34.32 | 10 | |
| T1-mapping reconstruction | CMRxRecon AF 4x | PSNR35.32 | 9 | |
| T1-mapping reconstruction | CMRxRecon AF 6x | PSNR34.26 | 9 | |
| T1-mapping reconstruction | CMRxRecon AF 8x | PSNR32.97 | 9 |