Acceleration of cerebral blood flow and arterial transit time maps estimation from multiple post-labeling delay arterial spin-labeled MRI via deep learning

TL;DR

This paper introduces a deep learning approach to accurately estimate cerebral blood flow and arterial transit time maps from fewer post-labeling delays in arterial spin-labeled MRI, reducing scan time while maintaining high quality.

Contribution

The study presents a novel neural network that significantly reduces the number of post-labeling delays needed for reliable CBF and ATT estimation, improving efficiency over traditional methods.

Findings

Deep learning models outperform conventional methods visually.

Two-PLD model provides more accurate ATT structure.

Reduced PLDs do not compromise SNR or quality.

Abstract

Purpose: Arterial spin labeling (ASL) perfusion imaging indicates direct and absolute measurement of cerebral blood flow (CBF). Arterial transit time (ATT) is a related physiological parameter reflecting the duration for the labeled spins to reach the brain region of interest. Multiple post-labeling delay (PLDs) can provide robust measures of both CBF and ATT, allowing for optimization of regional CBF modeling based on ATT. The prolonged acquisition time can potentially reduce the quality and accuracy of the CBF and ATT estimation. We proposed a novel network to significantly reduce the number of PLDs with higher signal-to-noise ratio (SNR). Method: CBF and ATT estimations were performed for one PLD and two PLDs sepa-rately. Each model was trained independently to learn the nonlinear transformation from perfusion weighted image (PWI) to CBF and ATT images. Results: Both one-PLD and two-PLD models outperformed the conventional method visually on CBF and two-PLD model showed more accurate structure on ATT estima-tion. The proposed method significantly reduces the number of PLDs from 6 to 2 on ATT and even to single PLD on CBF without sacrificing the SNR. Conclusion: It is feasible to generate CBF and ATT maps with reduced PLDs using deep learning with high quality.