Article

Physics-Informed Generalizable Framework Bridges the Sim-to-Real Gap in AI-based Cerebrovascular Hemodynamics Modeling

2026-06-11

Abstract excerpt

<title>Abstract</title> <p>Accurate characterization of spatio-temporal cerebrovascular hemodynamics is essential for neurovascular disease management. However, clinical translation is severely constrained by the "sim-to-real" gap, largely because existing models trained on idealized in silico data struggle to adapt to the immense topological variance of patient-specific anatomies inherent in in vivo measurements...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 548431c4-898e-5dd2-98be-4922467151d2
DOI: 10.21203/rs.3.rs-9923857/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Physics-Informed Generalizable Framework Bridges the Sim-to-Real Gap in AI-based Cerebrovascular Hemodynamics ModelingDOI 10.21203/rs.3.rs-9923857/v1Read

Physics-Informed AI Framework Enables Generalizable and Reliable Cerebrovascular Hemodynamic ProfilingSemantic proximity Read

Cerebrovascular super-resolution 4D Flow MRI – using deep learning to non-invasively quantify velocity, flow, and relative pressureSemantic proximity Read

Dual-Field Microvascular Segmentation: Hemodynamically-Consistent Attention Learning for Retinal Vasculature MappingSemantic proximity Read

From 3D Time-of-Flight Angiography to Accelerated 4D Arterial Spin Labeling Angiography: A Fast Few-Shot Transfer Learning ApproachSemantic proximity Read

Few-shot learning for highly accelerated 3D time-of-flight MRA reconstructionSemantic proximity Read

Geometry-Aware Abdominal Aortic Aneurysm Digital Twin for Patient-Specific Wall Stress MappingSemantic proximity Read

Automated high-throughput fabrication of patient-specific vessel-on-chips enables a generative AI digital twin—Cascade Learner of Thrombosis (CLoT) for personalized thrombosis predictionSemantic proximity Read

Redefining Hemodynamic Imaging in Stroke: Perfusion Parameter Map Generation from TOF-MRA using Artificial IntelligenceSemantic proximity Read

Generative Modeling of the Circle of Willis Using 3D-StyleGANSemantic proximity Read

Physics-Informed Neural Network for Mapping Vascular and Tissue Dynamics Using Laser Speckle Contrast ImagingSemantic proximity Read

Generative cerebral vasculature visualization using spatial transcriptomic dataSemantic proximity Read

UltimateSynth: MRI Physics for Pan-Contrast AISemantic proximity Read