MR images segmentation and bias correction via LIC model
Lingfeng Wang, Jie Wen Huang, Bin Lav, Chunhong Pan · 2017
This paper presents a novel Linear Intrinsic Component (LIC) model for simultaneous estimation of bias field and segmentation of magnetic resonance (MR) images with the intensity inhomogene-ity. The core of LIC model is linear transformation, which is derived from Taylor expansion of non-linear model. Due to the linear transformation, observed image can be decomposed into four components, namely, true image, which characterizes a physical property of the tissues, multiplicative and additive bias fields, which result in intensity inhomogeneity, and Gaussian noises. Based on sub-space constraint on two bias fields, and piecewise smoothness restriction on the true image, we can performing the task of joint bias field estimation and image segmentation. To model the complex noises subject to non-gaussian distribution, we further extend LIC model by introducing the non-gaussian noise term, and propose the Non-Gaussian LIC (NGLIC) model. By adopting L1regularization to our solution, the NGLIC model can be effectively solved by iterative soft-thresholding approach. Both LIC and NGLIC models are evaluated on a lot of MR simulated images downloaded from Brain-Web and real images, showing the superiority to the state-of-the-art approach on both segmentation and bias field correction results.