Fast 3D Structure Localization in Medical Volumes using CUDA-enabled GPUs
Siemens Corporate Research and Technologies, Bangalore, India
2nd IEEE International Conference on Parallel Distributed and Grid Computing, 2012
@article{vaswani2012fast,
title={Fast 3D Structure Localization in Medical Volumes using CUDA-enabled GPUs},
author={Vaswani, S. and Thota, R. and Vydyanathan, N. and Kale, A.},
year={2012}
}
Effective and fast localization of anatomical structures is a crucial first step towards automated analysis of medical volumes. In this paper, we propose an iterative approach for structure localization in medical volumes based on the adaptive bandwidth mean-shift algorithm for object detection (ABMSOD). We extend and tune the ABMSOD algorithm, originally used to detect 2D objects in non-medical images, to localize 3D anatomical structures in medical volumes. For fast localization, we design and develop optimized parallel implementations of the proposed algorithm on multi-cores using OpenMP, and on GPUs using CUDA. We evaluate the quality, performance and scalability of the proposed algorithm on Computed Tomography (CT) volumes for various structures.
November 15, 2012 by hgpu
