سال انتشار: ۱۳۹۰
محل انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر
تعداد صفحات: ۵
Jamal Ghasemi – Babol University of Technology,Electrical and Computer Department, Babol, Iran
Reza Ghaderi – Babol University of Technology,Electrical and Computer Department, Babol, Iran
Mohamad Reza Karami mollaei – Babol University of Technology,Electrical and Computer Department, Babol, Iran
Ali Hojjatoleslami – University of KentCentre for BioMedical Informatics, Kent,UK
As a result of noise and intensity non-uniformity,automatic segmentation of brain tissue in magnetic resonanceimage (MRI) is a complicated concern. In this study a novel brainMRI segmentation approach is presented which employsDempster-Shafer Theory (DST) for information fusion. In theproposed method, Fuzzy C-mean (FCM) is applied to separatefeatures and then the outputs of FCM are interpreted to basicbelief structures. The salient aspect of this work is theinterpretation of each FCM outputs to the belief structures withparticular focal elements. The Results of the proposed methodare evaluated using Dice’s similarity index. Qualitative andquantitative comparisons demonstrate that our method hasbetter results and is more robust than other algorithm.