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

TL;DR

Delta-WKV introduces a dynamic, efficient MRI super-resolution model that effectively captures local and global patterns, outperforming existing methods in quality and speed, with potential for clinical application.

Contribution

It presents Delta-WKV, a novel MRI super-resolution approach combining Meta-in-Context Learning with the Delta rule, enhancing pattern recognition with fewer parameters and computational resources.

Findings

Outperforms existing methods in PSNR and SSIM metrics.

Reduces training and inference times by over 15%.

Effectively captures both local and global MRI image patterns.

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.