Image Reconstruction with B0 Inhomogeneity using an Interpretable Deep Unrolled Network on an Open-bore MRI-Linac

TL;DR

This paper introduces RebinNet, an interpretable deep unrolled network that effectively reconstructs distortion-free MRI images from B0 inhomogeneity-affected data, enabling faster and more accurate image guidance in radiotherapy.

Contribution

The study presents RebinNet, a novel deep unrolled network that incorporates B0 inhomogeneity information for rapid, high-quality MRI reconstruction in radiotherapy applications.

Findings

RebinNet achieves lowest RMSE (<0.05) and highest SSIM (>0.92) at fourfold acceleration.

RebinNet is ten times faster than conventional regularization methods.

RebinNet outperforms UnUNet in generalization ability.

Abstract

MRI-Linac systems require fast image reconstruction with high geometric fidelity to localize and track tumours for radiotherapy treatments. However, B0 field inhomogeneity distortions and slow MR acquisition potentially limit the quality of the image guidance and tumour treatments. In this study, we develop an interpretable unrolled network, referred to as RebinNet, to reconstruct distortion-free images from B0 inhomogeneity-corrupted k-space for fast MRI-guided radiotherapy applications. RebinNet includes convolutional neural network (CNN) blocks to perform image regularizations and nonuniform fast Fourier Transform (NUFFT) modules to incorporate B0 inhomogeneity information. The RebinNet was trained on a publicly available MR dataset from eleven healthy volunteers for both fully sampled and subsampled acquisitions. Grid phantom and human brain images acquired from an open-bore 1T MRI-Linac scanner were used to evaluate the performance of the proposed network. The RebinNet was compared with the conventional regularization algorithm and our recently developed UnUNet method in terms of root mean squared error (RMSE), structural similarity (SSIM), residual distortions, and computation time. Imaging results demonstrated that the RebinNet reconstructed images with lowest RMSE (<0.05) and highest SSIM (>0.92) at four-time acceleration for simulated brain images. The RebinNet could better preserve structural details and substantially improve the computational efficiency (ten-fold faster) compared to the conventional regularization methods, and had better generalization ability than the UnUNet method. The proposed RebinNet can achieve rapid image reconstruction and overcome the B0 inhomogeneity distortions simultaneously, which would facilitate accurate and fast image guidance in radiotherapy treatments.