Computer Engineering and Applications ›› 2012, Vol. 48 ›› Issue (34): 5-10.

Previous Articles     Next Articles

Medical image segmentation and bias correction based on LGDF model

CUI Wenchao1,2, WANG Yi1, FAN Yangyu1, FENG Yan1   

  1. 1.School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China
    2.College of Science, China Three Gorges University, Yichang, Hubei 443002, China
  • Online:2012-12-01 Published:2012-11-30

基于LGDF模型的医学图像分割及有偏场校正

崔文超1,2,王  毅1,樊养余1,冯  燕1   

  1. 1.西北工业大学 电子信息学院,西安 710072
    2.三峡大学 理学院,湖北 宜昌 443002

Abstract: In order to implement segmentation and bias correction simultaneously for medical images with intensity inhomogeneity, an improved active contour model based on Local Gaussian Distribution Fitting(LGDF) energy is proposed in this paper. By analyzing the local properties of the bias field model, the multiplicative factor of bias field is induced into the local intensity means formation and thus it becomes a new variable of the energy functional. So the minimization of the energy functional by iteration not only accomplishes objective tissue segmentation but also makes an effective estimation to the bias field. Experiments on synthetic images and real medical 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 this method have better visual effect.

Key words: image segmentation, Local Gaussian Distribution Fitting(LGDF) model, bias correction, intensity inhomogeneity, medical image

摘要: 为实现对灰度不均匀医学图像分割的同时进行有偏场估计并校正,改进了基于局部高斯分布拟合(Local Gaussian Distribution Fitting,LGDF)能量的活动轮廓模型。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。合成图像和真实医学图像实验表明该方法比现有多种方法分割性能更好,且利用估计的有偏场校正后的图像具有更好的视觉效果。

关键词: 图像分割, LGDF模型, 有偏场校正, 灰度不均匀, 医学图像