Variational Network with Wavelet-based UNET in Accelerated MRI Reconstruction from Under Sampled K-space Data

2026-06-13

AI Summary

This work addresses artifacts, noise amplification, and loss of high-frequency details in accelerated MRI caused by k-space undersampling by proposing a novel method that integrates physics-guided iterative reconstruction with a learnable multi-scale frequency-domain representation. The key innovation lies in embedding the discrete wavelet transform into the U-Net architecture of a variational network (termed W-UNet), replacing conventional pooling with invertible downsampling to preserve low-frequency structures while enhancing high-frequency edges. This approach is jointly employed for image refinement and coil sensitivity map estimation, synergistically combining parallel imaging and compressed sensing strategies. Evaluated on the fastMRI knee and M4Raw brain datasets, the proposed method substantially suppresses aliasing artifacts, improves reconstruction fidelity, and achieves state-of-the-art performance.

Abstract

Fully sampled MRI requires dense k-space acquisition, leading to long scan times, reduced clinical throughput, and increased sensitivity to patient motion. Accelerated MRI addresses this by acquiring undersampled k-space data and reconstructing the missing information computationally. However, reconstruction from undersampled measurements is highly ill-posed and can introduce aliasing artifacts, noise amplification, and loss of anatomical detail. Although conventional parallel imaging and compressed sensing methods mitigate these issues, and deep learning methods have further improved reconstruction quality, preserving high-frequency structures under aggressive undersampling remains challenging. In this work, we propose a Variational Network with a Wavelet-based U-Net (W-UNet) for accelerated MRI reconstruction. The framework combines physics-guided iterative reconstruction with learnable multi-scale frequency representations. Standard pooling operations are replaced with Discrete Wavelet Transform and Inverse Wavelet Transform modules, enabling lossless downsampling while preserving low-frequency structure and high-frequency edge details. Integrated into the refinement and sensitivity map estimation stages, the proposed design improves artifact suppression, feature preservation, and reconstruction fidelity in both single-coil and multi-coil settings. Experiments on fastMRI knee and M4Raw brain datasets show state-of-the-art performance. Ablation studies further confirm the effectiveness of wavelet-based feature decomposition for accelerated MRI reconstruction.

Problem

• accelerated MRI
• undersampled k-space
• image reconstruction
• aliasing artifacts
• high-frequency preservation

Innovation

• Wavelet-based U-Net
• Variational Network
• Accelerated MRI Reconstruction
• Discrete Wavelet Transform
• Physics-guided Deep Learning