文档介绍：Simulation research on evaluation of EIT image
reconstructed by different algorithms
Juan Deng, Hong Sha, Yan Wang, Shu Zhao, Chaoshi Ren
Institute of Biomedical Engineering
Chinese Academy of Medical Sciences & PUMC
Tianjin, China
E-mail: renbme@
Abstract—Reconstruction algorithm is always the important area one-step sensitivity[5], Landweber iteration[6], CG(conjugate
of electrical impedance tomography (EIT). Aiming at target with gradient)[7], Tikhonov regularization [8],and NR(Newton-
different depths, using 3 algorithms, equipotential lines back Raphson) algorithms[9], reconstructed image effect is still
projection algorithm (ELBP), conjugate gradient algorithm (CG) dissatisfied.
and Newton-Raphson algorithm (NR), simulation evaluation has There are great differences in reconstruction quality and
been carried out. Reconstruction quality function D which information quantity among different reconstructed images,
reflects the error between imaging model and reconstructed
image, and structure deviation degree function SSIM which for the same model by different algorithms and for different
reflects structure distortion of reconstructed image, are adopted models by the same algorithm. However, the evaluation of
for the quantitative evaluation of reconstructed image by 3 reconstructed images effect is customarily according to visual
algorit