GPU implementation of map-MRF for microscopy imagery segmentation

Author

Crookes, Danny ; Miller, Paul ; Gribben, Hugh ; Gillan, Charles ; McCaughey, Damian

Author_Institution

Inst. of Electron., Commun. & Inf. Technol. (ECIT), Queen´´s Univ. Belfast, Belfast, UK

fYear

2009

fDate

June 28 2009-July 1 2009

Firstpage

526

Lastpage

529

Abstract

Recent developments in 3D low-light level CCD (L3CCD) image capture have enabled the study of the dynamics of biomedical bodies within cells. This paper firstly presents an improved algorithm for automatic segmentation of such imagery. It allows for the specific nature of noise in L3CCD data. Secondly, the massive volume of data produced by continuous real time 3D scans requires a high performance computation facility for automatic segmentation and tracking. The paper presents details and results of a GPU implementation of a version of the segmentation algorithm, and shows that on an NVIDIA GeForce 8800GTX, coded in CUDA C, the algorithm runs around 550 times faster than the Matlab version of the algorithm running on a PC.

Keywords

CCD image sensors; biomedical optical imaging; cellular biophysics; computer graphics; image segmentation; medical image processing; optical microscopy; 3D low-light level CCD; CUD C; NVIDIA GeForce 8800GTX; automatic segmentation; automatic tracking; biomedical bodies; cells; image capture; microscopy; Biomedical computing; Biomedical image processing; Charge coupled devices; Electron microscopy; Gaussian distribution; High performance computing; Image segmentation; Information technology; Layout; Statistical distributions; Image segmentation; accelerators;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Imaging: From Nano to Macro, 2009. ISBI '09. IEEE International Symposium on

Conference_Location

Boston, MA

ISSN

1945-7928

Print_ISBN

978-1-4244-3931-7

Electronic_ISBN

1945-7928

Type

conf

DOI

10.1109/ISBI.2009.5193100

Filename

5193100