AI RESEARCH
Deep Unrolled Meta-Learning for Multi-Coil and Multi-Modality MRI with Adaptive Optimization
arXiv CS.CV
•
ArXi:2505.11518v2 Announce Type: replace-cross We propose a unified deep meta-learning framework for accelerated magnetic resonance imaging (MRI) that jointly addresses multi-coil reconstruction and cross-modality synthesis. Motivated by the limitations of conventional methods in handling undersampled data and missing modalities, our approach unrolls a provably convergent optimization algorithm into a structured neural network architecture.