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.
Zhao, Ming; Lin, Hsiao-Yu; Lin, Hsiao-Yu; Yang, Chih-Hung; Hsu, Chih-Yu; and Pan, Jeng-Shyang
"Automatic Threshold Level Set Model Applied on MRI Image Segmentation of Brain Tissue,"
Applied Mathematics & Information Sciences: Vol. 09
, Article 37.
Available at: https://dc.naturalspublishing.com/amis/vol09/iss4/37