Automatic Detection of Brain Tumor using Novel Segmentation Method

( Vol-1,Issue-9,December 2015 )

Author(s): Hema Rajini N

Total View : 643
Downloads : 164
Page No: 28-34
DOI:

Keywords:

Bilateral filter; Fast bounding box; Watershed segmentation.

Abstract:

A new brain tumor detection system has been designed and developed. This work presents a new approach to the automated detection of brain tumor based on hybrid segmentation, which separate brain tumor from healthy tissues in magnetic resonance images. The magnetic resonance imaging has become a widely used method of high-quality medical imaging, especially in brain imaging where the soft-tissue contrast and non-invasiveness is a clear advantage. The magnetic resonance feature image used for the tumor detection consists of T2-weighted magnetic resonance images for each axial slice through the head. To remove the unwanted noises in the magnetic resonance image, bilateral filtering is used. Fast bounding box-based watershed segmentation algorithm is used to segment the images. The application of the proposed method for tracking tumor is demonstrated to help pathologists distinguish exactly tumor region. The results are quantitatively evaluated by a human expert. The average overlap metric, average precision and the average recall between the results obtained using the proposed approach and ground truth are 0.85, 0.80 and 0.97, respectively.

Cite This Article:

Share: