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

Abstract

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.