|
|
 |
| |
|
|
|
Automatic Threshold Level Set Model Applied on MRI Image Segmentation of Brain Tissue |
|
|
|
PP: 1971-1980 |
|
|
|
Author(s) |
|
|
|
Ming Zhao,
Hsiao-Yu Lin,
Hsiao-Yu Lin,
Chih-Hung Yang,
Chih-Yu Hsu,
Jeng-Shyang Pan,
Meng-Ju Lin,
|
|
|
|
Abstract |
|
|
| In the paper, a mathematical proof is given for a different mean of Chan and Vese model. Based on the proof, an image
segmentation method called Automatic Threshold Level Set Without Edge was developed for the extraction of tissues in brain MR
images. Thresholds are defined to find the boundary of tissues in the brain and they can be automatically obtained by Fuzzy C Mean
algorithm. A similarity index (SI) is used for quantitative evaluation of the segmentation results. By testing MRI brain slice images and
comparing to the ground truth of tissue segmentation, the mean and the variance of SI are 0.90311 and 0.042049. The experimental
results demonstrate our method can automatically and accurately segment the regions of tissues in brain. |
|
|
|
|
|
|
|
