一种三维分割算法在超声序列图像分割中的应用

图像分割在医学超声图像的定量分析和定性分析中具有重要的作用,它直接影响到后续的分析和处理工作。对于具有复杂特性的医学超声图像,传统的图像分割算法难以获得满意的效果。文中提出了基于一维Otsu方法的三维分割算法,具有快速性和准确性的优点。该方法应用于B超图像,实现了序列图像的自动分割,与普通的一维Otsu法相比,具有更好的分割效果。

Application of a Three-dimensional Algorithm in the Segmentation of B-Scan Ultrasonic Images

Image segmentation plays big role in quantitative and qualitative analysis of ultrasound images and it also impacts the subsequent operations.The traditional segmentation algorithms work unsatisfactorily on the ultrasound image due to image's complexity.A three-dimensional segmentation algorithm based on the one-dimensional Otsu method is proposed in this paper.The algorithm has the merit of both high speed and accuracy and is applied to the automatic segmentation of serial B-Scan ultrasonic images.It is shown that the improved algorithm can obtain better result than one-dimensional Otsu method.