Title :
Multiscale AM-FM decompositions with GPU acceleration for diabetic retinopathy screening
Author :
Carranza, Cesar ; Murray, Victor ; Pattichis, Marios ; Barriga, E. Simon
Author_Institution :
Electr. & Comput. Eng. Dept., Univ. of New Mexico, Albuquerque, NM, USA
Abstract :
A Computer Aided Diagnosis system based on multiscale amplitude-modulation frequency-modulation (AM-FM) methods has been recently developed for discriminating between normal and pathological retinal images. The original Matlab implementation of this system required large amounts of computational time and memory resources that would not permit real-time patient consultation. In this manuscript, we present a new implementation of the multiscale AM-FM decomposition, converted from MATLAB code into C/CUDA (Compute Unified Device Architecture) code, in order to take advantage of the graphics processing units (GPU) to significantly reduce the running time and memory resources.
Keywords :
amplitude modulation; disc drives; frequency modulation; graphics processing units; hard discs; medical image processing; parallel architectures; patient diagnosis; real-time systems; C/CUDA code; GPU acceleration; Matlab code; computational time; compute unified device architecture; computer aided diagnosis system; diabetic retinopathy screening; entry-level CUDA cards; frequency scales; global memory; graphics processing units; images pixels; intensive mathematical operation parallelization; local hard drive; main memory; memory resource reduction; multiscale AM-FM decomposition; multiscale amplitude-modulation frequency-modulation methods; normal retinal images; pathological retinal images; real-time patient consultation; running time reduction; Application software; Diabetes; Graphics processing unit; Hardware; Performance evaluation; Real time systems; Retinopathy; AM-FM; GPU; diabetic retinopathy; parallel processing;
Conference_Titel :
Image Analysis and Interpretation (SSIAI), 2012 IEEE Southwest Symposium on
Conference_Location :
Santa Fe, NM
Print_ISBN :
978-1-4673-1831-0
Electronic_ISBN :
978-1-4673-1829-7
DOI :
10.1109/SSIAI.2012.6202468
