Malena Español Institute: Arizona State University Date: November 7, 2024 Title: A deep learning approach for the electrical impedance tomography problem Abstract: Electrical Impedance Tomography (EIT) can map electrical property distributions within the body using a surface electrode array. EIT systems using a circumferential array applied to the abdomen can be used to monitor acute intra-abdominal hemorrhages in trauma patients. A half array (‘hemiarray’) applied only to the anterior abdomen may be more practical. However, severe reconstruction artifacts result in posterior regions using standard EIT reconstruction methods. In this talk, we introduce novel machine learning-based approaches for standard full and hemiarray EIT reconstructions, demonstrating superior reconstruction characteristics compared to conventional methods. This was joint work with Rosalind Sadleir, Mason Manning, Shelby Horth, Nicholas Wharff, and Jacob Roarty.
