DCE-Qnet: deep network quantification of dynamic contrast enhanced (DCE) MRI.

ABSTRACT:

Introduction

Quantification of dynamic contrast-enhanced (DCE)-MRI has the potential to provide valuable clinical information, but robust pharmacokinetic modeling remains a challenge for clinical adoption.

Methods

A 7-layer neural network called DCE-Qnet was trained on simulated DCE-MRI signals derived from the Extended Tofts model with the Parker arterial input function. Network training incorporated B₁ inhomogeneities to estimate perfusion (K^trans, v_p, v_e), tissue T₁ relaxation, proton density and bolus arrival time (BAT). The accuracy was tested in a digital phantom in comparison to a conventional nonlinear least-squares fitting (NLSQ). In vivo testing was conducted in ten healthy subjects. Regions of interest in the

SUBMITTER: Cohen O 

PROVIDER: S-EPMC11996236 | biostudies-literature | 2024 Dec

REPOSITORIES: biostudies-literature