基于水平集分割方法的医学图像三维重建

为了提高医学图像处理对疾病辅助诊断和治疗的效果,提出一种新的基于先验形状的水平集方法,对多张脊柱CT切片进行分割,并将其分割结果进行三维重建。首先使用核主成分分析算法对训练样本进行降维,并用水平集来表达主成分作为先验形状;然后对水平集形状样本均值进行形态学处理,从而获得分割的初始轮廓;最后将初始轮廓引入RSF模型来构造新的总能量泛函,并依此对形态学预处理之后的每一张CT图像进行分割,进而根据分割结果进行三维重建。实验结果表明,新方法对多张CT切片的分割比传统分割方法具有更优的分割效果和更高的分割效率,能够精准地进行椎骨重建,指导脊椎的矫正手术。

Three dimensional medical image reconstruction using level set segmentation method

In order to improve the effect of the medical image processing on diagnosis and treatment of diseas-es, a novel method based on priori shaped level set method for CT slices segmentation and reconstruction is proposed. First of all, training samples are gotten , and the kernel principal component analysis algorithm is used to reduce the dimension of the samples and extract the principal component as the priori shape to guide the segmentation;Next do morphological processing on the mean shape which is used as the initial contour to effectively solve the determined problem of the initial contour of the curve evolution;And then the initial con-tour is introduced into the RSF model to construct a new total energy functional to segment each CT image af-ter morphology preprocessing, and all the segmentation results are made for 3D reconstruction. Experimental results show that the proposed method has more advantages in processing multiple CT slices than the tradition-al method with better results and higher efficiency, and the reconstructed vertebrae has a good effect and a higher degree of automation, which has certain guiding significance to virtual spine corrective surgery.