Joint reconstruction and bias field correction for undersampled MR imaging

TL;DR

This paper introduces a joint reconstruction and bias field correction method for undersampled MRI that explicitly models bias fields to improve image quality, addressing issues of data variability and inhomogeneity.

Contribution

It presents a novel joint optimization approach combining unsupervised reconstruction with bias field estimation to enhance MRI image quality.

Findings

Improved visual quality of reconstructed images.

Reduced RMSE in reconstruction results.

Enhanced robustness to bias field variations.

Abstract

Undersampling the k-space in MRI allows saving precious acquisition time, yet results in an ill-posed inversion problem. Recently, many deep learning techniques have been developed, addressing this issue of recovering the fully sampled MR image from the undersampled data. However, these learning based schemes are susceptible to differences between the training data and the image to be reconstructed at test time. One such difference can be attributed to the bias field present in MR images, caused by field inhomogeneities and coil sensitivities. In this work, we address the sensitivity of the reconstruction problem to the bias field and propose to model it explicitly in the reconstruction, in order to decrease this sensitivity. To this end, we use an unsupervised learning based reconstruction algorithm as our basis and combine it with a N4-based bias field estimation method, in a joint optimization scheme. We use the HCP dataset as well as in-house measured images for the evaluations. We show that the proposed method improves the reconstruction quality, both visually and in terms of RMSE.