Open AccessA VTK-based, CUDA-optimized Non-Parametric Vessel Detection Method
Author(s) -
Levent Alpöge,
Alark Joshi,
Dustin Scheinost,
John A. Onofrey,
Xiaoning Qian,
Xenophon Papademetris
Publication year - 2010
Publication title -
vtk journal
Language(s) - English
Resource type - Journals
ISSN - 2328-3459
DOI - 10.54294/z1w0uu
Subject(s) - cuda , leverage (statistics) , computer science , parametric statistics , graphics , parametric surface , parallel computing , computational science , general purpose computing on graphics processing units , computer graphics (images) , artificial intelligence , mathematics , statistics
We present a VTK-based implementation of our non-parametric vessel detection method that identifies vascular structures using a polar neighborhood profile. To accelerate the computationally intensive parts of the algorithm, we leverage the hardware capabilities in commodity graphics hardware using Compute Unified Device Architecture (CUDA). We present the results of our performance analysis and provide source code and examples to validate the reproducibility of our results.