Saved in:
Bibliographic Details
Main Authors: Lee, Junhyeok, Choi, Minseo, Jang, Han, Jeon, Young Hun, Eum, Heeseong, Jang, Joon, Sohn, Chul-Ho, Choi, Kyu Sung
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09359
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912958523637760
author Lee, Junhyeok
Choi, Minseo
Jang, Han
Jeon, Young Hun
Eum, Heeseong
Jang, Joon
Sohn, Chul-Ho
Choi, Kyu Sung
author_facet Lee, Junhyeok
Choi, Minseo
Jang, Han
Jeon, Young Hun
Eum, Heeseong
Jang, Joon
Sohn, Chul-Ho
Choi, Kyu Sung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09359
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evidential Perfusion Physics-Informed Neural Networks with Residual Uncertainty Quantification
Lee, Junhyeok
Choi, Minseo
Jang, Han
Jeon, Young Hun
Eum, Heeseong
Jang, Joon
Sohn, Chul-Ho
Choi, Kyu Sung
Computer Vision and Pattern Recognition
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.
title Evidential Perfusion Physics-Informed Neural Networks with Residual Uncertainty Quantification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.09359