AUTOMATED EDGE-DRIVEN MARKOV RANDOM FIELD SEGMENTATION OF EX VIVO MOUSE BRAIN MRM IMAGES

Author

Scheenstra, A.E.H. ; Dijkstra, J. ; van de Ven, R.C.G. ; van der Weerd, L. ; Reiber, J.H.C.

Author_Institution

Dept. of Radiol., Leiden Univ. Med. Center

fYear

2007

fDate

12-15 April 2007

Firstpage

1292

Lastpage

1295

Abstract

In biological image processing the segmentation of a volume is, although tedious, required for many applications, like the comparison of structures and annotation purposes. To automate this process, we present a segmentation method for various structures of the mouse brain which consists of two parts. First a rough affine atlas based registration was performed and second, the edges were refined by an adapted Markov random field clustering approach. The segmentations results were compared to manual segmentations of two experts which resulted in good kappa indices for 11 out of 16 structures. The presented segmentation method is quick, intuitive and suitable for biological objectives, like comparison, annotation but also registration purposes

Keywords

Markov processes; biomedical MRI; brain; image registration; image segmentation; medical image processing; pattern clustering; MRM images; Markov random field clustering; Markov segmentation; automated segmentation; biological image processing; biological objectives; edge-driven segmentation; ex vivo mouse brain; image registration; kappa indices; random field segmentation; rough affine atlas; volume segmentation; Brain; Clustering algorithms; Humans; Image segmentation; Markov random fields; Mice; Mutual information; Noise shaping; Protocols; Signal to noise ratio;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on

Conference_Location

Arlington, VA

Print_ISBN

1-4244-0672-2

Electronic_ISBN

1-4244-0672-2

Type

conf

DOI

10.1109/ISBI.2007.357096

Filename

4193530