为实现对灰度不均匀脑核磁共振(MR)图像分割的同时进行有偏场估计并校正,提出一种基于局部高斯分布拟合(LGDF)模型的多相水平集方法。通过分析图像有偏场模型的局部特性,将有偏场乘性因子引入到图像局部灰度均值的表达中,从而使有偏场乘性因子成为新的能量函数的变量。能量函数的迭代最小化既实现了目标组织分割,又有效估计了有偏场。合成图像和仿真脑MR图像实验结果表明,本文方法比现有多种方法分割性能更好,且利用本文方法估计的有偏场校正后的图像有更好的视觉效果。

In order to implement segmentation and bias correction simultaneously for brain Magnetic Resonance (MR) images with intensity inhomogeneity, a multiphase level set method based on local Gaussian distribution fitting (LGDF) model is proposed in this paper. By analyzing the local properties of the bias field model, the multiplicative factor of the bias field is induced into the local intensity means formation and thus it becomes a new variable of the energy function. Therefore, the minimization of the energy function by iteration does not only accomplish the objective tissue segmentation, but also makes an effective estimation to the bias field. Experiments on synthetic images and simulated brain MR images show the proposed method is superior to the state-of-the-art on segmentation results. Moreover, the corrected images using the bias field estimated by our method have a better visual effect.