Neural network for enhancement of FCM based brain MRI segmentation

摘要

As a result of some artifacts, Brain MRI Segmentation (BMS) is a difficult concern. FCM (Fuzzy C-Mean) is one of the most common methods in segmenting MR images. One of the limitations of this method is its high sensitivity to noise. In this study by using intensities of neighborhood pixels and using neural network for segmenting a group of pixels, some limitations of FCM algorithm have been overcome. The results show that our proposed method has acceptable output in comparison with other methods.