The Community for Technology Leaders
Healthcare Informatics, Imaging and Systems Biology, IEEE International Conference on (2012)
La Jolla, CA, USA USA
Sept. 27, 2012 to Sept. 28, 2012
ISBN: 978-1-4673-4803-4
pp: 1
The growth of medical image data produced on a daily basis in modern hospitals forces the adaptation of traditional medical image analysis and indexing approach to scalable solutions. The number of images and their dimensionality increased dramatically during the past 20 years. We propose solutions for largescale medical image analysis based on parallel computing and algorithm optimization. The MapReduce framework is used to speed up and make possible three largescale medical image processing usecases: (i) parameter optimization for lung texture segmentation using support vector machines, (ii) contentbased medical image indexing, and (iii) threedimensional directional wavelet analysis for solid texture classification. A cluster of heterogeneous computing nodes was set up in our institution using Hadoop allowing for a maximum of 42 concurrent map tasks. The majority of the machines used are desktop computers that are also used for regular office work. The cluster showed to be minimally invasive and well stable. The runtimes of each of the three usecase have been significantly reduced when compared to a sequential execution.
texture analysis, largescale, medical, image analysis, big data, scalability, MapReduce, Hadoop, support vector machines, contentbased image retrieval

I. Eggel, A. Depeursinge, R. Schaer, H. Muller and D. Markonis, "Using MapReduce for Large-Scale Medical Image Analysis," Healthcare Informatics, Imaging and Systems Biology, IEEE International Conference on(HISB), La Jolla, CA, USA USA, 2012, pp. 1.
87 ms
(Ver 3.3 (11022016))