AI Insight
HemoPIC is a new physics-informed computational framework that creates a digital twin model of brain blood flow from perfusion imaging data. The system uses tracer mass conservation principles and hemodynamic modeling to automatically quantify brain perfusion parameters like cerebral blood flow, blood volume, and mean transit time, eliminating the need for manual arterial input function selection and traditional deconvolution methods. The approach produces clinically actionable perfusion maps while simultaneously providing a mechanistic model that can simulate blood flow dynamics and perform counterfactual analyses.
Why it matters
This technology could streamline clinical assessment of stroke and brain tumors by automating perfusion analysis and reducing operator-dependent variability. The digital twin capability enables physicians to simulate different treatment scenarios and better understand individual patient hemodynamics, potentially improving diagnostic accuracy and treatment planning decisions.
Understand the Science
arXiv:2607.08799v1 Announce Type: new
Abstract: Perfusion imaging guides clinical evaluation of stroke and brain tumors by characterizing tissue-level hemodynamics. Routine quantification relies on manual arterial input function (AIF) selection followed by deconvolution, producing summary maps without an executable temporal model for simulation or mechanistic insight. Tracer-dynamics-based models infer transport or compartmental parameters from perfusion time series, but do not yield clinically actionable perfusion indices (e.g., CBF, CBV, MTT) that inform diagnosis and treatment decisions. In this work, we propose HemoPIC, a physics-informed cerebral hemodynamics digital twin that explains perfusion time series through tracer mass conservation and a lumped parameter hemodynamic model. Specifically, HemoPIC solves a constrained inverse problem that jointly estimates digital twin parameters and latent states from perfusion imaging, eliminating manual AIF selection and deconvolution from routine perfusion quantification while directly producing clinically actionable perfusion summary maps. Experiments demonstrate that HemoPIC reconstructs tracer dynamics, generates physiologically consistent perfusion maps with lesion hypoperfusion patterns, satisfies central volume consistency, and yields a mechanistic hemodynamic digital twin that enables forward simulation and counterfactual intervention analysis. Code is publicly available at https://github.com/jhuldr/HemoPIC.
Source: HemoPIC: A Physics-Informed Cerebral Hemodynamics Digital Twin for Brain Perfusion