MR image segmentation and bias field estimation using coherent local and global intensity clustering

This paper presents a new energy minimization method for simultaneous image segmentation and bias field estimation of magnetic resonance (MR) images. The proposed algorithm introduces the global intensity into the algorithm CLIC and combines the local and global intensity information into account. The segmentation target therefore is driven by two forces, one induced by the coherent local intensity and the other by the coherent global intensity, to ensure the smoothness of the derived optimal bias field and improve the accuracy of the segmentations. An integration of the proposed algorithm defines an energy function ,then the segmentations and bias field estimation are simultaneously achieved by minimizing this function. Moreover, the proposed algorithm is robust to the parameter setting, thereby allowing fully automatic applications. The proposed method has been successfully applied to 3T and synthetic MR images with desirable results. Comparisons with other approaches demonstrate the superior performance of the proposed algorithm.