Detection and 3D Reconstruction of Brain from MR Images.
- Author:
Seung Uk CHOI
1
;
Sang Seol LEE
;
Gun Hyee LEE
;
Young Kyu CHOI
Author Information
1. Department of Electrical Engineering, Wonkwang University, Korea.
- Publication Type:Original Article
- Keywords:
Brain images;
Image segmentation;
Gibbs Random Field;
3D visualization
- MeSH:
Brain*;
Humans;
Magnetic Resonance Imaging;
Masks
- From:Journal of Korean Society of Medical Informatics
1998;4(2):139-144
- CountryRepublic of Korea
- Language:Korean
-
Abstract:
In this paper, we propose a brain detection algorithm of cross-sectional images through a 3D volume. The proposed brain detection algorithm uses several steps. They are as follows; In the first step, the standard value and downward from input image data are removed. in the second step, the pixels with maximum intensity are removed but undesirable many small areas were appeared as by-products. In order to detect brain, these small areas need to be removed. In the third step, many small areas are removed by masking but some small areas still remained. In the fourth step, they are removed using three-dimensional connectivity. The proposed algorithm was applied to real human MRI data and the brain area was successfully detected.