Brain MR Image Segmentation and Bias Correction Using an Improved Gaussian Mixture Model

Brain image segmentation is an important part of clinical diagnostic tools. Due to the affection of imaging mechanism, MR images usually contain noise and bias field. Traditional Gaussian Mixed Model (GMM) method is difficult to obtain a good segmentation result. We propose a novel model based on GMM which combines segmentation with bias correction that can manage the bias field and noise while segmenting the image. Fuzzy C-means method is used for optimizing the initial value to reduce the impact of initial value. In order to obtain a smooth bias field, we employed the Legendre Polynomials to fit it and merged it to the EM framework. We also introduce the non local information to deal with the image noise and preserve geometrical edges in the image. The results show that our method can get a good segmentation results and bias field.