Patch-based local learning method for cerebral blood flow quantification with arterial spin-labeling MRI

Arterial Spin Labeling Perfusion MRI Signal Processing Through Traditional Methods and Machine Learning

Arterial spin labeling (ASL) perfusion MRI is a non-invasive technique for quantifying and mapping cerebral blood flow (CBF). Depending on the tissue signal change after magnetically labeled arterial blood enters the brain tissue, ASL MRI signal can be affected by several factors, including the volume of arrived arterial blood, signal decay of labeled blood, physiological fluctuations of the brain and CBF, and head motion, etc. Some of them can be controlled using sophisticated state-of-art ASL MRI sequences, but the others can only be resolved with post-processing strategies. Over the decades, various post-processing methods have been proposed in the literature, and many post processing software packages have been released. This self-contained review provides a brief introduction to ASL MRI, recommendations for typical ASL MRI data acquisition protocols, an overview of the ASL data processing pipeline, and an introduction to typical methods used at each step in the pipeline. Although the main focus is on traditional heuristic model-based methods, a brief introduction to recent machine learning-based approaches is provided too.

NO-HYPE: a novel hydrodynamic phantom for the evaluation of MRI flow measurements

Accurate and reproducible measurement of blood flow profile is very important in many clinical investigations for diagnosing cardiovascular disorders. Given that many factors could affect human circulation, and several parameters must be set to properly evaluate blood flows with phase-contrast techniques, we developed an MRI-compatible hydrodynamic phantom to simulate different physiological blood flows. The phantom included a programmable hydraulic pump connected to a series of pipes immersed in a solution mimicking human soft tissues, with a blood-mimicking fluid flowing in the pipes. The pump is able to shape and control the flow by driving a piston through a dedicated software. Periodic waveforms are used as input to the pump to move the fluid into the pipes, with synchronization of the MRI sequences to the flow waveforms. A dedicated software is used to extract and analyze flow data from magnitude and phase images. The match between the nominal and the measured flows was assessed, and the scope of phantom variables useful for a reliable calibration of an MRI system was accordingly defined. Results showed that the NO-HYPE phantom is a valuable tool for the assessment of MRI scanners and sequence design for the MR evaluation of blood flows. Overview of the NOvel HYdrodynamic Phantom for the Evaluation of MRI flow measurements (NO-HYPE). Left: internal of the CompuFlow 1000 MR pump unit. Right: Setting of the NO-HYPE before a MRI acquisition session. Soft tissue mimicking material is hosted in the central part of the phantom (light blue chamber). Glass pipes pass through the chamber carrying the blood mimicking fluid.

Denoising arterial spin labeling perfusion MRI with deep machine learning

PURPOSE

Arterial spin labeling (ASL) perfusion MRI is a noninvasive technique for measuring cerebral blood flow (CBF) in a quantitative manner. A technical challenge in ASL MRI is data processing because of the inherently low signal-to-noise-ratio (SNR). Deep learning (DL) is an emerging machine learning technique that can learn a nonlinear transform from acquired data without using any explicit hypothesis. Such a high flexibility may be particularly beneficial for ASL denoising. In this paper, we proposed and validated a DL-based ASL MRI denoising algorithm (DL-ASL).

METHODS

The DL-ASL network was constructed using convolutional neural networks (CNNs) with dilated convolution and wide activation residual blocks to explicitly take the inter-voxel correlations into account, and preserve spatial resolution of input image during model learning.

RESULTS

DL-ASL substantially improved the quality of ASL CBF in terms of SNR. Based on retrospective analyses, DL-ASL showed a high potential of reducing 75% of the original acquisition time without sacrificing CBF measurement quality.

CONCLUSION

DL-ASL achieved improved denoising performance for ASL MRI as compared with current routine methods in terms of higher PSNR, SSIM and Radiologic scores. With the help of DL-ASL, much fewer repetitions may be prescribed in ASL MRI, resulting in a great reduction of the total acquisition time.