A Study on the Application of Fuzzy Information Seeded Region Growing in Brain MRI Tissue Segmentation

Magnetic resonance imaging (MRI) is better than computed tomography (CT), because of its advantages of non-radiation and non-invasive. After long-term clinical trials, MRI has been proved to use in humans harmlessly, and it popular used in medical diagnosis. Although MR is highly sensitive, but it's provide abundant organization information. Therefore, how to transform the multi-spectral images which is easier to be used for doctor's clinical diagnosis. In this thesis, the fuzzy bi-directional edge detection method used to solve conventional SRG problem of growing order in the initial seeds stages. In order to overcome the problems of the different regions, but it's the same Euclidean distance for region growing and merging process stages. We present the peak detection method to improve it. The standard deviation target generation process (SDTGP) is applied to guarantee the regions merging process does not cause over or under segmentation.