Accelerating Biomedical Imaging using parallel Fuzzy C-Means Algorithm

Abstract

The focus is mainly on the development, acquisition and image reconstruction strategies, using MRI, to accurately and quantitatively image physiology. Primary applications include functional brain imaging, structural brain imaging, and neuromuscular. The software used is OpenACC, to accelerate their advanced imaging model. OpenACC is a directive based programming model designed for scientists and researchers looking to tap into the computational power of accelerators without significant programming effort. This software provides the significant speed-ups using the new PGI compiled software on the NVIDIA GPU. Hence it is now able to develop some other application software that reduced the time it would normally take to reconstruct the MRI scan from 40 days down to a couple of hours, OpenACC also allowed to run on one of the fastest supercomputers in the world.