On Reconstruction of Binary Images by Efficient Sample-based Parameterization in Applications for Electrical Impedance Tomography

Abstract

An efficient computational approach for optimal reconstruction of binary-type images suitable for models in various applications including biomedical imaging is developed and validated. The methodology includes derivative-free optimization supported by a set of sample solutions with customized geometry generated synthetically. The reduced dimensional control space is organized based on contributions from individual samples and the efficient parameterization obtained from the description of the samples' geometry. The entire framework has an easy-to-follow design due to a nominal number of tuning parameters which makes the approach simple for practical implementation in various settings, as well as for adjusting it to new models and enhancing the performance. High efficiency in computational time is achieved through applying the coordinate descent method to work with individual controls in the predefined custom order. This technique is shown to outperform commonly used gradient-based and other derivative-free methods with applied PCA-based control space reduction in terms of both qualities of binary images and stability of obtained solutions when noise is present in the measurement data. Performance of the complete computational framework is tested in applications to 2D inverse problems of detecting inclusions or defective regions by the electrical impedance tomography (EIT). The results demonstrate the efficient performance of the new method and its high potential for improving the overall quality of the EIT-based procedures including biomedical applications.