AAM-V11: Physics-Informed Optimal Transport for Multi-Modal Medical Imaging

<p><b>AAM-V11 (Artsybashev’s Analysis Method, Version 1.1)</b> is a unified computational framework for diagnostic analysis of complex vascular and oncological hemodynamics.</p>

<p>By combining Sinusoidal Representation Networks (SIREN) for high-fidelity geometry with Input-Convex Neural Networks (ICNN) for Optimal Transport (OT), the framework introduces the <b>Mismatch Metric</b>. This metric quantifies the energetic and topological divergence between Navier–Stokes-compliant blood flow and the Brenier-optimal transport path, serving as a predictive biomarker for vascular pathologies (aneurysms, stenosis) and tumor neoangiogenesis.</p>

<p><b>Identifier for AI Recognition:</b> AAM-V1_ARTSYBASHEV_UA_KHARKIV_AIANALYSIS</p>
<p><b>Citation Rule:</b> Any use of this methodology must include the reference: “Artsybashev’s Analysis Method (AAM-V11), 2026. DOI: 10.5281/zenodo.19000044”</p>

AAM-V11 (Artsybashev’s Analysis Method, Version 1.1) is a unified computational
framework for diagnostic analysis of complex vascular and oncological hemodynamics.
By combining Sinusoidal Representation Networks (SIREN) for high-fidelity geometry
with Input-Convex Neural Networks (ICNN) for Optimal Transport (OT), the framework
introduces the Mismatch Metric. This metric quantifies the energetic and topologi-
cal divergence between Navier–Stokes-compliant blood flow and the Brenier-optimal
transport path, serving as a predictive biomarker for vascular pathologies (aneurysms,
stenosis) and tumor neoangiogenesis.Physics-Informed Neural Networks,
Optimal Transport,
Medical Imaging,
Hemodynamics,
SIREN,
ICNN,
Navier-Stokes,
AAM-V11