Enhanced image reconstruction of electrical impedance tomography using simultaneous algebraic reconstruction technique and K-means clustering

<span lang="EN-US">Electrical impedance tomography (EIT), as a non-ionizing method, has been widely used in various fields of application, such engineering and medical fields. This study applies an iterative process to reconstruct EIT images using the simultaneous algebraic reconstruction technique (SART) algorithm combined with K-means clustering. The started defining finite element method (FEM) model filtering measurement data Butterworth low-pass filter. next step is solving inverse problem case SART algorithm. results approach were classified clustering thresholding. evaluated peak signal noise ratio (PSNR), structural similarity indices (SSIM), normalized root mean square error (NRMSE). They compared one-step gauss-newton (GN) total variation regularization based on iteratively reweighted least-squares (TV-IRLS) methods. evaluation shows that average PSNR SSIM proposed are highest other methods, each being 24.24 0.94; meanwhile, NRMSE value lowest, which 0.04. performance also faster than methods.</span>