Share Email Print
cover

Proceedings Paper

Brain tumor segmentation in MR slices using improved GrowCut algorithm
Author(s): Chunhong Ji; Jinhua Yu; Yuanyuan Wang; Liang Chen; Zhifeng Shi; Ying Mao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The detection of brain tumor from MR images is very significant for medical diagnosis and treatment. However, the existing methods are mostly based on manual or semiautomatic segmentation which are awkward when dealing with a large amount of MR slices. In this paper, a new fully automatic method for the segmentation of brain tumors in MR slices is presented. Based on the hypothesis of the symmetric brain structure, the method improves the interactive GrowCut algorithm by further using the bounding box algorithm in the pre-processing step. More importantly, local reflectional symmetry is used to make up the deficiency of the bounding box method. After segmentation, 3D tumor image is reconstructed. We evaluate the accuracy of the proposed method on MR slices with synthetic tumors and actual clinical MR images. Result of the proposed method is compared with the actual position of simulated 3D tumor qualitatively and quantitatively. In addition, our automatic method produces equivalent performance as manual segmentation and the interactive GrowCut with manual interference while providing fully automatic segmentation.

Paper Details

Date Published: 9 December 2015
PDF: 8 pages
Proc. SPIE 9817, Seventh International Conference on Graphic and Image Processing (ICGIP 2015), 98170F (9 December 2015); doi: 10.1117/12.2228230
Show Author Affiliations
Chunhong Ji, Fudan Univ. (China)
Jinhua Yu, Fudan Univ. (China)
Yuanyuan Wang, Fudan Univ. (China)
Liang Chen, Fudan Univ. (China)
Zhifeng Shi, Fudan Univ. (China)
Ying Mao, Fudan Univ. (China)


Published in SPIE Proceedings Vol. 9817:
Seventh International Conference on Graphic and Image Processing (ICGIP 2015)
Yulin Wang; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top