Implicit Modeling with Uncertainty Estimation for Intravoxel Incoherent Motion Imaging
This work addresses accuracy limitations in perfusion imaging for medical applications like fetal MRI, representing an incremental improvement over existing methods.
The paper tackled the problem of low accuracy in intravoxel incoherent motion (IVIM) imaging for perfusion quantification in MRI, particularly in fetal MRI, by proposing an implicit model with uncertainty estimation, resulting in a 65% improvement in parameter estimation accuracy on synthetic data and a 46% increase in repeatability on in vivo fetal MRI rescans.
Intravoxel incoherent motion (IVIM) imaging allows contrast-agent free in vivo perfusion quantification with magnetic resonance imaging (MRI). However, its use is limited by typically low accuracy due to low signal-to-noise ratio (SNR) at large gradient encoding magnitudes as well as dephasing artefacts caused by subject motion, which is particularly challenging in fetal MRI. To mitigate this problem, we propose an implicit IVIM signal acquisition model with which we learn full posterior distribution of perfusion parameters using artificial neural networks. This posterior then encapsulates the uncertainty of the inferred parameter estimates, which we validate herein via numerical experiments with rejection-based Bayesian sampling. Compared to state-of-the-art IVIM estimation method of segmented least-squares fitting, our proposed approach improves parameter estimation accuracy by 65% on synthetic anisotropic perfusion data. On paired rescans of in vivo fetal MRI, our method increases repeatability of parameter estimation in placenta by 46%.