Local Ai
End-to-End Autonomous Recursive Arborescence Deformable Flow and Non-Linear Hemodynamics for Patient-Specific Coronary Centerline Extraction
arXiv:2610.05900v1 Announce Type: new Abstract: Extracting patient-specific vascular trees from volumetric medical images is fundamental to computational angiography and non-invasive hemodynamic asses
arXiv:2610.05900v1 Announce Type: new Abstract: Extracting patient-specific vascular trees from volumetric medical images is fundamental to computational angiography and non-invasive hemodynamic assessment. Conventional voxel segmentation models often sever delicate bifurcations, while heuristic Euclidean Minimum Spanning Trees introduce non-anatomical shortcuts. Moreover, linear Poiseuille flow neglects quadratic kinetic dissipation across arterial narrowings, underestimating ischemia. We formulate an end-to-end framework decoupling continuous geometric arborescence generation from non-linear hemodynamics. First, an autonomous 3D Ostium Landmark Localization Head with dual-sinus query channels and spherical-gated refinement eliminates centerline seeding dependency, achieving cohort mean localization error of 7.63 mm (7.43 mm LCA, 7.83 mm RCA; 71.4% 0.80) in 14/14 cases, whereas our non-linear solver captures functional ischemia (FFR = 0.5864, lesion disparity 32.89 mmHg, p = 6.10e-5) with 3.66x collateral shunting. Test set firewall isolation was maintained.
Related
- CORA: Generalizable coronary artery disease assessment and risk stratification from coronary CT angiography using pathology-centric representation learning
- RadYOLO: Computationally Efficient 3D Object Detection and Segmentation in CT and MRI
- LHMCF-Net: A Learned Hyperbolic Mean Curvature Flow Network for Medical Images Segmentation
Source: arXiv cs.CV | 2026-10-06