医学超声图像的对比度增强与分割

Segmentation of Ultrasound images with Fuzzy Enhancement

医学超声图像因对比度较低、形成过程产生的独有的斑点噪声等影响了手动与计算机辅助分析的效果,尤其是影响了计算机定量测量的效果。为了增强超声图像的对比度,提出了一种模糊增强算法对超声图像进行显著增强,并利用马尔可夫随机场与最大后验概率理论对增强后的图像进行分割,得到了满意的分割效果。

Ultrasound B-scan images often have low contrast and the characteristic speckle noise. These cause major problems for image analysis, both by manual and computer-aided techniques, particularly the computation of quantitative measurements. We present a new fuzzy algorithm to enhance the contrast of Ultrasound images, and use Markov random field (MRF) and the maximum a posteriori theory to segmentation the result images. Significant improvement is achieved in tissue contrast and segmentation result.