基于遗传算法的电阻抗图像重建  

Image Reconstruction in Electrical Impedance Tomography Based on Genetic Algorithm

作　　者：侯卫东[1] 莫玉龙[1] 

机构地区：[1]上海大学通信工程系,上海200072

出　　处：《生物医学工程学杂志》2003年第1期107-111,共5页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目 ( 60 0 75 0 0 9);上海市高校科技发展基金资助项目

摘　　要：电阻抗图像重建是一个严重病态的非线性的逆问题。改进的 Newton- Raphson迭代算法是目前理论上最为完善的静态电阻抗图像重建算法 ,它是一种基于最小化目标函数的搜索算法 ,在实际阻抗图像重建过程中对噪声非常敏感 ,即使使用正则化技术其稳定性和图像重建精度仍较差。本文提出一种基于遗传算法的图像重建新方法 ,实验结果表明这种方法具有较强的抗噪能力 ,其重建的静态电阻抗图像精度和空间分辨率都大大好于改进的 Newton-Image reconstruction in electrical impedance tomography (EIT) is a highly ill-posed, non-linear inverse problem. The modified Newton-Raphson (MNR) iteration algorithm is deduced from the strictest theoretic analysis. It is an optimization algorithm based on minimizing the object function. The MNR algorithm with regularization technique is usually not stable, due to the serious image reconstruction model error and measurement noise. So the reconstruction precision is not high when used in static EIT. A new static image reconstruction method for EIT based on genetic algorithm (GA-EIT) is proposed in this paper. The experimental results indicate that the performance (including stability, the precision and space resolution in reconstructing the static EIT image) of the GA-EIT algorithm is better than that of the MNR algorithm.

关 键 词：遗传算法 电阻抗 图像重建 

分 类 号：R310[医药卫生—基础医学]