交互式医疗诊断图像轮廓线自动快速生成仿真

Automatic Rapid Generation Simulationof Interactive Medical Diagnosis Image Contour Line

对交互式医疗诊断图像轮廓线的生成,能够有效提高临床诊断以及治疗水平。对交互式医疗诊断图像轮廓线自动快速的生成,需要构建轮廓线演化能量模型,提高轮廓线生成的精度,确定能量函数极小值,完成医疗诊断图像轮廓线的生成。传统方法沿着感兴趣方向对轮廓进行投影,分析扫描曲面对应的医疗诊断图像数据,但忽略了对轮廓线演化模型的构建,导致轮廓线生成精度偏低。提出基于Snake模型的交互式医疗诊断图像轮廓线自动生成方法,通过构建Snake模型曲线的能量函数,确定图像能量函数,实现交互式医疗诊断图像局部分割,利用Bayes定理对后验概率进行计算,并对概率中的参数进行分析,构建轮廓线演化能量模型,确定能量函数极小值,实现医疗诊断图像轮廓线自动生成。实验结果表明,所提方法能够准确对医疗诊断图像进行分割,保证了轮廓线自动生成的精确度。

The aim of this article is to overcome defect of traditional generation method for image contour line of interactive medical diagnosis, such as poor generation precision. Based on Snake model, an automatic generation method is presented. Energy function of the image was confirmed via building energy function of Snake model curve. Local segmentation of image of the interactive medical diagnosis was achieved. Bayes theorem was used to calculate posterior probability and analyze parameters in the probability. Energy model of contour line evolution was built. The minimum value of the energy function was confirmed. Thus, the automatic generation was achieved. Simulation re- suits show that the method can segment the image of medical diagnosis accurately and ensure precision of the automat- ic generation.