CUDA based parallel wavelet algorithm in medical image fusion

Author

Li Gang ; Luo Yujun

Author_Institution

Inst. of Mol. Biol., North-Sichuan Med. Coll., Nanchong, China

fYear

2013

fDate

23-24 Dec. 2013

Firstpage

198

Lastpage

201

Abstract

The medical image fusion today mainly use the CPU and pc cluster. Based on the CUDA stream computing model, a parallel wavelet image fusion algorithm is provided. After the analyses of wavelet image fusion and the CUDA multi-layer storage structure and SIMD architecture, the data grouping and thread task being decomposed. The CUDA based wavelet image fusion algorithm can be used for clinic image analyses. The test shows this algorithm can improve the speed of CPU based one with 8-10 times and it has linear speed up ability.

Keywords

image fusion; medical image processing; parallel architectures; storage management; wavelet transforms; CPU; CUDA based parallel wavelet algorithm; CUDA multilayer storage structure; CUDA stream computing model; Compute Unified Device Architecture; GPU; PC cluster; SIMD architecture; clinic image analysis; data grouping; medical image fusion; parallel wavelet image fusion algorithm; thread task; Convolution; Graphics processing units; Image fusion; Instruction sets; Medical diagnostic imaging; Wavelet transforms; CUDA; GPU; Medical image fusion; wavelet;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement, Sensor Network and Automation (IMSNA), 2013 2nd International Symposium on

Conference_Location

Toronto, ON

Type

conf

DOI

10.1109/IMSNA.2013.6743250

Filename

6743250