AI RESEARCH
SDUM: A Scalable Deep Unrolled Model for Universal MRI Reconstruction
arXiv CS.AI
•
ArXi:2512.17137v2 Announce Type: replace-cross Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We