Efficient multi-task structure-aware sparse Bayesian learning for frequency-difference electrical impedance tomography

Frequency-difference electrical impedance tomography (fdEIT) was originally developed to mitigate the systematic artifacts induced by modeling errors when a baseline data set is unavailable. Instead of fine anatomical imaging, only coarse anomaly detection has been addressed in current fdEIT research mainly due to its low spatial resolution. On the other hand, there has been not much study on fdEIT reconstruction algorithm as well. In this paper, we propose an efficient and high-spatial-resolution algorithm for simultaneously reconstructing multiple fdEIT frames corresponding to inject currents with multiple frequencies. The EIT reconstruction problem is considered within a hierarchical Bayesian framework, where both intra-task spatial clustering and inter-task dependency are automatically learned and exploited in an unsupervised manner. The computation is accelerated by adopting a modified marginal likelihood maximization approach. Real-data experiment are conducted to verify the recovery performance of the proposed algorithm.