Analysis of grid performance using an Optical Flow algorithm for Medical Image processing

摘要

The development of bigger and faster computers has not yet provided the computing power for medical image processing required nowadays. This is the result of several factors, including: ⅰ) the increasing number of qualified medical image users requiring sophisticated tools; ⅱ) the demand for more performance and quality of results; ⅲ) researchers are addressing problems that were previously considered extremely difficult to achieve; ⅳ) medical images are produced with higher resolution and on a larger number. These factors lead to the need of exploring computing techniques that can boost the computational power of Healthcare Institutions while maintaining a relative low cost. Parallel computing is one of the approaches that can help solving this problem. Parallel computing can be achieved using multi-core processors, multiple processors, Graphical Processing Units (GPU), clusters or Grids. In order to gain the maximum benefit of parallel computing it is necessary to write specific programs for each environment or divide the data in smaller subsets. In this article we evaluate the performance of the two parallel computing tools when dealing with a medical image processing application. We compared the performance of the EELA-2 (E-science grid facility for Europe and Latin-America) grid infrastructure with a small Cluster (3 nodes × 8 cores = 24 cores) and a regular PC (Intel i3 - 2 cores). As expected the grid had a better performance for a large number of processes, the cluster for a small to medium number of processes and the PC for few processes.