Implicit Regression in Subspace for High-Sensitivity CEST Imaging

TL;DR

This paper introduces IRIS, an unsupervised neural network-based denoising method for CEST MRI data that models spatially variant z-spectrums in a low-dimensional subspace, improving detection sensitivity.

Contribution

The paper presents a novel implicit neural representation-based denoising algorithm for CEST MRI, enhancing quantification accuracy by modeling spatially variant spectra in a low-dimensional subspace.

Findings

IRIS outperforms existing denoising methods in qualitative assessments.

IRIS improves quantitative CEST measurement accuracy.

Experiments on synthetic and in-vivo data validate IRIS's effectiveness.

Abstract

Chemical Exchange Saturation Transfer (CEST) MRI demonstrates its capability in significantly enhancing the detection of proteins and metabolites with low concentrations through exchangeable protons. The clinical application of CEST, however, is constrained by its low contrast and low signal-to-noise ratio (SNR) in the acquired data. Denoising, as one of the post-processing stages for CEST data, can effectively improve the accuracy of CEST quantification. In this work, by modeling spatial variant z-spectrums into low-dimensional subspace, we introduce Implicit Regression in Subspace (IRIS), which is an unsupervised denoising algorithm utilizing the excellent property of implicit neural representation for continuous mapping. Experiments conducted on both synthetic and in-vivo data demonstrate that our proposed method surpasses other CEST denoising methods regarding both qualitative and quantitative performance.