Open Extensive 3D Dataset of Geometric Objects Placed in a Watertank for Electrical Impedance Tomography

Electrical impedance tomography (EIT) is a non-invasive, radiation-free imaging method for visualizing the tomography of electrically conductive objects. The image reconstruction approach using data-driven methods or deep neural networks (DNN) has become very popular. To train such a reconstruction network, much data is required to reconstruct the conductivity distribution reliably, which is why simulation data are often used. This is an open-access experimental 3D EIT data set. The measurements were generated using the Sciospec EIT device, from which 64 electrodes were connected in two stages, with 32 electrodes, to a phantom tank filled with saline. Various ball objects of different sizes and materials were placed in this tank volume-wide. The provided dataset contains more than 124,000 samples.