A Learning-from-noise Dilated Wide Activation Network for denoising Arterial Spin Labeling (ASL) Perfusion Images

TL;DR

This paper introduces a novel deep learning-based denoising network for arterial spin labeling MRI that leverages learning from noisy references, demonstrating improved image quality even with highly noisy training data.

Contribution

The study proposes a new ASLDN architecture that effectively learns from noisy references, outperforming models trained on higher quality data in ASL perfusion image denoising.

Findings

Learning-from-noise enhances denoising performance.

The proposed method surpasses traditional training approaches.

High noise training references can lead to better image quality.

Abstract

Arterial spin labeling (ASL) perfusion MRI provides a non-invasive way to quantify cerebral blood flow (CBF) but it still suffers from a low signal-to-noise-ratio (SNR). Using deep machine learning (DL), several groups have shown encouraging denoising results. Interestingly, the improvement was obtained when the deep neural network was trained using noise-contaminated surrogate reference because of the lack of golden standard high quality ASL CBF images. More strikingly, the output of these DL ASL networks (ASLDN) showed even higher SNR than the surrogate reference. This phenomenon indicates a learning-from-noise capability of deep networks for ASL CBF image denoising, which can be further enhanced by network optimization. In this study, we proposed a new ASLDN to test whether similar or even better ASL CBF image quality can be achieved in the case of highly noisy training reference. Different experiments were performed to validate the learning-from-noise hypothesis. The results showed that the learning-from-noise strategy produced better output quality than ASLDN trained with relatively high SNR reference.