Delta-WKV: A Novel Meta-in-Context Learner for MRI Super-Resolution

2025-02-28

AI Summary

To address challenges in clinical MRI super-resolution—including difficulty in jointly modeling local and global static patterns and high computational overhead—this paper proposes a dynamic weight adjustment framework that avoids state-space models (SSMs) or RNNs. Methodologically, it introduces three key innovations: (1) the first integration of Meta-in-Context Learning with the Delta rule for adaptive weight updates; (2) a four-directional scanning Receptance-weighted KV attention architecture to capture long-range dependencies while preserving high-frequency details; and (3) a lightweight time-channel hybrid module. Evaluated on IXI and fastMRI datasets, the method achieves consistent improvements: +0.06 dB in PSNR and +0.001 in SSIM, alongside >15% acceleration in both training and inference. Moreover, it significantly reduces parameter count and FLOPs, striking an optimal balance among reconstruction accuracy, computational efficiency, and deployment feasibility.

Technology Category

• Computer Vision: Multi-modal Vision
• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Hardware-aware ML

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Magnetic Resonance Imaging (MRI) Super-Resolution (SR) addresses the challenges such as long scan times and expensive equipment by enhancing image resolution from low-quality inputs acquired in shorter scan times in clinical settings. However, current SR techniques still have problems such as limited ability to capture both local and global static patterns effectively and efficiently. To address these limitations, we propose Delta-WKV, a novel MRI super-resolution model that combines Meta-in-Context Learning (MiCL) with the Delta rule to better recognize both local and global patterns in MRI images. This approach allows Delta-WKV to adjust weights dynamically during inference, improving pattern recognition with fewer parameters and less computational effort, without using state-space modeling. Additionally, inspired by Receptance Weighted Key Value (RWKV), Delta-WKV uses a quad-directional scanning mechanism with time-mixing and channel-mixing structures to capture long-range dependencies while maintaining high-frequency details. Tests on the IXI and fastMRI datasets show that Delta-WKV outperforms existing methods, improving PSNR by 0.06 dB and SSIM by 0.001, while reducing training and inference times by over 15%. These results demonstrate its efficiency and potential for clinical use with large datasets and high-resolution imaging.

Problem

• Enhance MRI image resolution from low-quality inputs
• Improve recognition of local and global MRI patterns
• Reduce computational effort and training time for MRI SR

Innovation

• Combines Meta-in-Context Learning with Delta rule
• Uses quad-directional scanning for long-range dependencies
• Reduces training and inference times by over 15%