Clean self-supervised MRI reconstruction from noisy, sub-sampled training data with Robust SSDU

TL;DR

This paper introduces Robust SSDU, a self-supervised MRI reconstruction method that effectively denoises and reconstructs images from noisy, sub-sampled training data, outperforming existing methods and enabling training without fully sampled datasets.

Contribution

Robust SSDU is a novel self-supervised MRI reconstruction approach that simultaneously denoises and reconstructs from noisy, sub-sampled data, with provable guarantees and broad applicability.

Findings

Performs competitively with models trained on clean data

Effectively denoises and reconstructs from noisy, sub-sampled data

Applicable to any network architecture

Abstract

Most existing methods for Magnetic Resonance Imaging (MRI) reconstruction with deep learning use fully supervised training, which assumes that a high signal-to-noise ratio (SNR), fully sampled dataset is available for training. In many circumstances, however, such a dataset is highly impractical or even technically infeasible to acquire. Recently, a number of self-supervised methods for MR reconstruction have been proposed, which use sub-sampled data only. However, the majority of such methods, such as Self-Supervised Learning via Data Undersampling (SSDU), are susceptible to reconstruction errors arising from noise in the measured data. In response, we propose Robust SSDU, which provably recovers clean images from noisy, sub-sampled training data by simultaneously estimating missing k-space samples and denoising the available samples. Robust SSDU trains the reconstruction network to map from a further noisy and sub-sampled version of the data to the original, singly noisy and sub-sampled data, and applies an additive Noisier2Noise correction term at inference. We also present a related method, Noiser2Full, that recovers clean images when noisy, fully sampled data is available for training. Both proposed methods are applicable to any network architecture, straight-forward to implement and have similar computational cost to standard training. We evaluate our methods on the multi-coil fastMRI brain dataset with a novel denoising-specific architecture and find that it performs competitively with a benchmark trained on clean, fully sampled data.