Search papers, labs, and topics across Lattice.
The paper introduces Evidential Perfusion Physics-Informed Neural Networks (EPPINN), a novel framework that combines evidential deep learning with physics-informed neural networks to estimate perfusion parameters in computed tomography perfusion (CTP) imaging. EPPINN models perfusion parameters using coordinate-based networks and uses a Normal-Inverse-Gamma distribution over the physics residual to quantify aleatoric and epistemic uncertainty in physics consistency. Experiments on digital phantoms, the ISLES 2018 benchmark, and clinical data demonstrate that EPPINN achieves improved accuracy and reliability compared to classical deconvolution and PINN baselines, especially under sparse temporal sampling and low signal-to-noise conditions.
Quantifying uncertainty in physics-informed neural networks for medical imaging boosts accuracy and reliability, leading to better stroke assessment.
Physics-informed neural networks (PINNs) have shown promise in addressing the ill-posed deconvolution problem in computed tomography perfusion (CTP) imaging for acute ischemic stroke assessment. However, existing PINN-based approaches remain deterministic and do not quantify uncertainty associated with violations of physics constraints, limiting reliability assessment. We propose Evidential Perfusion Physics-Informed Neural Networks (EPPINN), a framework that integrates evidential deep learning with physics-informed modeling to enable uncertainty-aware perfusion parameter estimation. EPPINN models arterial input, tissue concentration, and perfusion parameters using coordinate-based networks, and places a Normal--Inverse--Gamma distribution over the physics residual to characterize voxel-wise aleatoric and epistemic uncertainty in physics consistency without requiring Bayesian sampling or ensemble inference. The framework further incorporates physiologically constrained parameterization and stabilization strategies to promote robust per-case optimization. We evaluate EPPINN on digital phantom data, the ISLES 2018 benchmark, and a clinical cohort. On the evaluated datasets, EPPINN achieves lower normalized mean absolute error than classical deconvolution and PINN baselines, particularly under sparse temporal sampling and low signal-to-noise conditions, while providing conservative uncertainty estimates with high empirical coverage. On clinical data, EPPINN attains the highest voxel-level and case-level infarct-core detection sensitivity. These results suggest that evidential physics-informed learning can improve both accuracy and reliability of CTP analysis for time-critical stroke assessment.
