A cascade algorithm combined Kohonen feature map with fuzzy C-means applied in MR brain image segmentation

Author

Lin, Chung-Chih ; Jeng-Ren Duann ; Cheng, Hui-Cheng ; Chen, Jyh-Horng

Author_Institution

Inst. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan

Volume

3

fYear

1996

fDate

31 Oct-3 Nov 1996

Firstpage

1079

Abstract

In this study, a cascade algorithm combined Kohonen feature map with FCM was applied to segment the MR brain images. The method we proposed was proved to have better performance than FCM method usually used in image segmentation research. Because the algorithm is unsupervised, it can reduce the errors caused by intraobserver and interobserver estimation. In this paper, we also utilized the MR images acquired by PAIR protocol to verify the result of the image segmentation

Keywords

biomedical NMR; brain; feature extraction; fuzzy set theory; image classification; image segmentation; medical image processing; self-organising feature maps; unsupervised learning; MRI brain image segmentation; PAIR protocol; cascade algorithm combined Kohonen feature map; cerebrospinal fluid; clustering algorithm; fuzzy C-means; gray matter; interobserver estimation errors; intraobserver estimation errors; pixels classification; unsupervised algorithm; white matter; Biology computing; Brain; Engineering in Medicine and Biology Society; Image segmentation; Immune system; Organizing; Protocols; Protons; Sequences; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1996. Bridging Disciplines for Biomedicine. Proceedings of the 18th Annual International Conference of the IEEE

Conference_Location

Amsterdam

Print_ISBN

0-7803-3811-1

Type

conf

DOI

10.1109/IEMBS.1996.652717

Filename

652717