Paper Title:
Automatic MRI Brain Tumor Segmentation System Based on Localizing Active Contour Models
  Abstract

In this paper, an automatic segmentation system was developed for MRI brain tumor. Local region-based active contour models were suitable for heterogeneous features of brain MRI image. But the models are sensitive to initial contour, which generally requires manual setting. An automatic MRI brain tumor segmentation system were developed based on localized contour models, which can identify tumor-dominant slice, set initial contour automatically and segment tumor’s contours from all MRI slices autonomously. K-means clustering and grayscale analysis were combined to identify tumor-dominant slice. Multi-threshold algorithm with the aid of erosion and dilation operators was adopted to obtain an initial contour for the tumor-dominant slice. The segmentation contour from the local active contour models was applied as initial contours of two-side neighboring slices. MRI brain tumor data were applied to validate the automatic segmentation system.

  Info
Periodical
Advanced Materials Research (Volumes 219-220)
Edited by
Helen Zhang, Gang Shen and David Jin
Pages
1342-1346
DOI
10.4028/www.scientific.net/AMR.219-220.1342
Citation
Y. Wang, Z. X. Lin, J. G. Cao, M. Q. Li, "Automatic MRI Brain Tumor Segmentation System Based on Localizing Active Contour Models", Advanced Materials Research, Vols. 219-220, pp. 1342-1346, 2011
Online since
March 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.