An Efficient MR Image Brain Tumor Segmentation Based on Discrete Wavelet Transform and Region Growing Algorithm

Brain Tumor Segmentation in Magnetic Resonance Imaging (MRI) has become an emergent research area and it plays an important role in the field of medical imaging system and it is most significant. This research paper proposes a method for MR image brain tumor segmentation based on dual tree Discrete Wavelet transform and Region Growing algorithm. The given MR image is converted to grayscale after that it performs a de-noising process for grayscale image by using median filter. The MR image has been enhanced using the filter and apply the dual tree DWT. Discrete Wavelet Transform is applied to MRI images because wavelets provide frequency information as well as time-space localization. In this process, the tumor part is segmented using region growing algorithm. This segmentation algorithm provides exact detection of tumor, since it involves seeding process. Finally the tumor image has been segmented which shows the efficiency of the output. The experimental results shown by the proposed method is effective in segmentation of MR image. In this paper, evaluate the well-known purpose image quality metrics, like Mean, Median and Standard Deviation.