Denoising Arterial Spin Labeling Cerebral Blood Flow Images Using Deep Learning

TL;DR

This study demonstrates that deep learning, specifically CNNs, can significantly improve denoising of arterial spin labeling MRI images, enhancing SNR and CBF quantification while reducing acquisition time and enabling automatic correction.

Contribution

The paper introduces a CNN-based denoising model for ASL MRI that incorporates prior structural knowledge, achieving state-of-the-art performance over existing methods.

Findings

DL-ASL outperforms routine denoising methods in SNR improvement

Achieves 75% reduction in acquisition time

Enables automatic partial volume correction

Abstract

Arterial spin labeling perfusion MRI is a noninvasive technique for measuring quantitative cerebral blood flow (CBF), but the measurement is subject to a low signal-to-noise-ratio(SNR). Various post-processing methods have been proposed to denoise ASL MRI but only provide moderate improvement. Deep learning (DL) is an emerging technique that can learn the most representative signal from data without prior modeling which can be highly complex and analytically indescribable. The purpose of this study was to assess whether the record breaking performance of DL can be translated into ASL MRI denoising. We used convolutional neural network (CNN) to build the DL ASL denosing model (DL-ASL) to inherently consider the inter-voxel correlations. To better guide DL-ASL training, we incorporated prior knowledge about ASL MRI: the structural similarity between ASL CBF map and grey matter probability map. A relatively large sample data were used to train the model which was subsequently applied to a new set of data for testing. Experimental results showed that DL-ASL achieved state-of-the-art denoising performance for ASL MRI as compared to current routine methods in terms of higher SNR, keeping CBF quantification quality while shorten the acquisition time by 75%, and automatic partial volume correction.