Improving microstructural integrity, interstitial fluid, and blood microcirculation images from multi-b-value diffusion MRI using physics-informed neural networks in cerebrovascular disease

Paulien H.M. Voorter, Walter H. Backes, Oliver J. Gurney-Champion, Sau May Wong, Julie Staals, Robert J. van Oostenbrugge, Merel M. van der Thiel, Jacobus F.A. Jansen, Gerhard S. Drenthen (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

4 Citations (Scopus)

Abstract

Purpose: To obtain better microstructural integrity, interstitial fluid, and microvascular images from multi-b-value diffusion MRI data by using a physics-informed neural network (PINN) fitting approach. Methods: Test–retest whole-brain inversion recovery diffusion-weighted images with multiple b-values (IVIM: intravoxel incoherent motion) were acquired on separate days for 16 patients with cerebrovascular disease on a 3.0T MRI system. The performance of the PINN three-component IVIM (3C-IVIM) model fitting approach was compared with conventional fitting approaches (i.e., non-negative least squares and two-step least squares) in terms of (1) parameter map quality, (2) test–retest repeatability, and (3) voxel-wise accuracy. Using the in vivo data, the parameter map quality was assessed by the parameter contrast-to-noise ratio (PCNR) between normal-appearing white matter and white matter hyperintensities, and test–retest repeatability was expressed by the coefficient of variation (CV) and intraclass correlation coefficient (ICC). The voxel-wise accuracy of the 3C-IVIM parameters was determined by 10,000 computer simulations mimicking our in vivo data. Differences in PCNR and CV values obtained with the PINN approach versus conventional fitting approaches were assessed using paired Wilcoxon signed-rank tests. Results: The PINN-derived 3C-IVIM parameter maps were of higher quality and more repeatable than those of conventional fitting approaches, while also achieving higher voxel-wise accuracy. Conclusion: Physics-informed neural networks enable robust voxel-wise estimation of three diffusion components from the diffusion-weighted signal. The repeatable and high-quality biological parameter maps generated with PINNs allow for visual evaluation of pathophysiological processes in cerebrovascular disease.

Original languageEnglish
Pages (from-to)1657-1671
Number of pages15
JournalMagnetic Resonance in Medicine
Volume90
Issue number4
DOIs
Publication statusPublished - Oct 2023

Keywords

  • free water
  • intravoxel incoherent motion
  • microvascular perfusion
  • multi-b-value diffusion MRI
  • parenchymal diffusion
  • physics-informed deep learning

Fingerprint

Dive into the research topics of 'Improving microstructural integrity, interstitial fluid, and blood microcirculation images from multi-b-value diffusion MRI using physics-informed neural networks in cerebrovascular disease'. Together they form a unique fingerprint.

Cite this