Reference-driven undersampled MRI reconstruction using automated stopping deep image prior

Abstract

Magnetic resonance image (MRI) reconstruction from undersampled k-space data using unsupervised learning methods suffers from insufficient a priori knowledge and the lack of stopping criterion. This work introduces a high-resolution reference image to tackle these issues. Specifically, we explicitly broadcast the reference image into the proposed network, transferring the reference image structure priors to the recovered image. In addition, the reference image helps to develop a criterion to determine the best-reconstructed image, so training stops automatically once the conditions are met. Experimental results show that the proposed method can reduce artifacts without using a priori training set.