DeepASL: Kinetic Model Incorporated Loss for Denoising Arterial Spin Labeled MRI via Deep Residual Learning

TL;DR

DeepASL introduces a deep learning method that enhances arterial spin labeling MRI images by incorporating cerebral blood flow models into the loss function, resulting in higher quality images and more accurate blood flow estimates from fewer measurements.

Contribution

This work presents a novel deep residual learning approach that integrates CBF estimation into the loss function for improved ASL image denoising and quantification.

Findings

Enhanced image quality in synthetic and clinical datasets.

Accurate cerebral blood flow estimation.

Reduced computation time during testing.

Abstract

Arterial spin labeling (ASL) allows to quantify the cerebral blood flow (CBF) by magnetic labeling of the arterial blood water. ASL is increasingly used in clinical studies due to its noninvasiveness, repeatability and benefits in quantification. However, ASL suffers from an inherently low-signal-to-noise ratio (SNR) requiring repeated measurements of control/spin-labeled (C/L) pairs to achieve a reasonable image quality, which in return increases motion sensitivity. This leads to clinically prolonged scanning times increasing the risk of motion artifacts. Thus, there is an immense need of advanced imaging and processing techniques in ASL. In this paper, we propose a novel deep learning based approach to improve the perfusion-weighted image quality obtained from a subset of all available pairwise C/L subtractions. Specifically, we train a deep fully convolutional network (FCN) to learn a mapping from noisy perfusion-weighted image and its subtraction (residual) from the clean image. Additionally, we incorporate the CBF estimation model in the loss function during training, which enables the network to produce high quality images while simultaneously enforcing the CBF estimates to be as close as reference CBF values. Extensive experiments on synthetic and clinical ASL datasets demonstrate the effectiveness of our method in terms of improved ASL image quality, accurate CBF parameter estimation and considerably small computation time during testing.