Stimulation and measurement patterns versus prior information for fast 3D EIT: A breast screening case study

Abstract

Imposing prior information is a typical strategy in inverse problems in return for a stable numerical algorithm. For a given imaging system configuration, Picard's stability condition could be deployed as a practical measure of the performance of the system against various priors and noise contaminated measurements. Herein, we make extensive use of this measure to quantify the performance of impedance imaging systems for various injection patterns. In effect, we numerically demonstrate that by varying electrode distributions and numbers, little improvement, if any, in the performance of the impedance imaging system is recorded. In contrast, by using groups of electrodes in the 3D current injection process, a step increase in performance is obtained. Numerical results on a female breast phantom reveal that the performance measure of the imaging system is 15% for a conventional combination of stimulation and prior information, 61% for groups of electrodes and the same prior and 97% for groups of electrodes and a more accurate prior. Finally, since a smaller number of electrodes is involved in the measurement process, a smaller number of measurements is acquired. However, no compromise in the quality of the reconstructed images is observed.