Abstract #0843

Comparison of MR Fingerprinting ASL with Gd-based DSC MRI: validation and direct parametric mapping with deep learning

Pan Su^1,2, Peiying Liu¹, Yang Li¹, Ye Qiao¹, Jun Hua^1,3, Doris Lin¹, Jay J. Pillai^1,4, Argye E. Hillis^5,6,7, and Hanzhang Lu^1,3

¹The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, United States, ²Graduate School of Biomedical Sciences, University of Texas Southwestern Medical Center, Dallas, TX, United States, ³F. M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Research Institute, Baltimore, MD, United States, ⁴Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD, United States, ⁵Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, United States, ⁶Physical Medicine and Rehabilitation, Johns Hopkins University School of Medicine, Baltimore, MD, United States, ⁷Cognitive Science, Johns Hopkins University, Baltimore, MD, United States

MR Fingerprinting (MRF)-based Arterial-Spin-Labeling (ASL) has been recently proposed as a new approach to measure multiple hemodynamic parameters in a single scan. However, the previous implementation of MRF-ASL lacks the comparison with clinical standard techniques such as dynamic-susceptibility-contrast (DSC). Therefore, in this work, we validated MRF-ASL by comparing with DSC MRI. The results showed that these two methods provided visually comparable and quantitatively correlated perfusion estimations. Furthermore, we sought to directly estimate DSC-equivalent parameters from the MRF-ASL raw data using a deep-learning (DL) approach. DL-derived maps show better quality and are more consistent with DSC maps, compared to dictionary-matching results.

This abstract and the presentation materials are available to members only; a login is required.

Join Here