Image reconstruction in electrical impedance tomography is sensitive to errors in the (forward) model of the measurement system. We propose a new approach, based on the GREIT algorithm, where the reconstruction matrix is trained on real rather than simulated data, obviating the need for an accurate numerical forward model. We observe a substantial improvement in image quality, particularly for changes close to the boundary.

Additional Metadata
Publisher International Steering Committee on Electrical Impedance Tomography
Series 15th International Conference on Biomedical Applications of Electrical Impedance Tomography (EIT 2014)
Citation
Gaggero, Pascal O., Adler, A, & Grychtol, Bartłomiej. (2014). Using real data to train GREIT improves image quality. In 15th International Conference on Biomedical Applications of Electrical Impedance Tomography (EIT 2014). International Steering Committee on Electrical Impedance Tomography.