A Comprehensive Framework for Uncertainty Quantification of Voxel-wise Supervised Models in IVIM MRI
This work addresses uncertainty quantification for IVIM MRI fitting, which is important for medical imaging researchers and clinicians, but it is incremental as it builds on existing probabilistic methods like Deep Ensembles and Mixture Density Networks.
The authors tackled the challenge of accurately estimating intravoxel incoherent motion (IVIM) parameters from diffusion-weighted MRI, which is prone to noise and ill-posedness, by proposing a probabilistic deep learning framework using Deep Ensembles of Mixture Density Networks, resulting in more calibrated and sharper predictive distributions for diffusion parameters, with slight overconfidence in one parameter.
Accurate estimation of intravoxel incoherent motion (IVIM) parameters from diffusion-weighted MRI remains challenging due to the ill-posed nature of the inverse problem and high sensitivity to noise, particularly in the perfusion compartment. In this work, we propose a probabilistic deep learning framework based on Deep Ensembles (DE) of Mixture Density Networks (MDNs), enabling estimation of total predictive uncertainty and decomposition into aleatoric (AU) and epistemic (EU) components. The method was benchmarked against non probabilistic neural networks, a Bayesian fitting approach and a probabilistic network with single Gaussian parametrization. Supervised training was performed on synthetic data, and evaluation was conducted on both simulated and an in vivo dataset. The reliability of the quantified uncertainties was assessed using calibration curves, output distribution sharpness, and the Continuous Ranked Probability Score (CRPS). MDNs produced more calibrated and sharper predictive distributions for the diffusion coefficient D and fraction f parameters, although slight overconfidence was observed in pseudo-diffusion coefficient D*. The Robust Coefficient of Variation (RCV) indicated smoother in vivo estimates for D* with MDNs compared to Gaussian model. Despite the training data covering the expected physiological range, elevated EU in vivo suggests a mismatch with real acquisition conditions, highlighting the importance of incorporating EU, which was allowed by DE. Overall, we present a comprehensive framework for IVIM fitting with uncertainty quantification, which enables the identification and interpretation of unreliable estimates. The proposed approach can also be adopted for fitting other physical models through appropriate architectural and simulation adjustments.