Learning the Regularization in DCE-MR Image Reconstruction for Functional Imaging of Kidneys

TL;DR

This paper introduces a deep neural network approach for kidney DCE-MRI image reconstruction that reduces under-sampling artifacts without compromising the accuracy of functional biomarkers, outperforming traditional compressed sensing methods.

Contribution

A novel single image trained deep neural network that promotes regularization through lower dimensional representations, improving artifact reduction and biomarker accuracy in kidney DCE-MRI reconstruction.

Findings

The proposed method reduces artifacts more effectively than multiple regularization weights in CS.

It maintains high correlation with ground truth biomarkers.

It enhances image quality without sacrificing functional analysis accuracy.

Abstract

Kidney DCE-MRI aims at both qualitative assessment of kidney anatomy and quantitative assessment of kidney function by estimating the tracer kinetic (TK) model parameters. Accurate estimation of TK model parameters requires an accurate measurement of the arterial input function (AIF) with high temporal resolution. Accelerated imaging is used to achieve high temporal resolution, which yields under-sampling artifacts in the reconstructed images. Compressed sensing (CS) methods offer a variety of reconstruction options. Most commonly, sparsity of temporal differences is encouraged for regularization to reduce artifacts. Increasing regularization in CS methods removes the ambient artifacts but also over-smooths the signal temporally which reduces the parameter estimation accuracy. In this work, we propose a single image trained deep neural network to reduce MRI under-sampling artifacts without reducing the accuracy of functional imaging markers. Instead of regularizing with a penalty term in optimization, we promote regularization by generating images from a lower dimensional representation. In this manuscript we motivate and explain the lower dimensional input design. We compare our approach to CS reconstructions with multiple regularization weights. Proposed approach results in kidney biomarkers that are highly correlated with the ground truth markers estimated using the CS reconstruction which was optimized for functional analysis. At the same time, the proposed approach reduces the artifacts in the reconstructed images.