Object extraction from T2 weighted brain MR image using histogram based gradient calculation

摘要

Several segmentation methods have been reported with their own pros and cons. Here we proposed a method for object extraction from T2 weighted (T2) brain magnetic resonance (MR) images. The proposed method is purely based on histogram processing for gradient calculation. The proposed method utilizes the histogram filtering technique as a pre-processing. The primary brain areas; gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) are extracted out efficiently from 2D and 3D images. The method has been successfully implemented on human brain MR images obtained in clinical environment.