Stroke classification using virtual hybrid edge detection from in silico electrical impedance tomography data

Abstract

Electrical impedance tomography (EIT) combined with machine learning has shown promise for the classification of strokes. However, most previous works have used raw EIT voltage data as network inputs. We build upon a recent development which suggested the use of a special noise-robust virtual hybrid edge detection (VHED) functions computed from EIT data as network inputs, although that work used only simplified and mathematically ideal models. In this work, we design models with high detail and mathematical realism. Virtual patients are created using a physically detailed 2D head model which includes features known to create challenges in real-world imaging scenarios. Simulated noisy EIT electrode data, generated using the realistic complete electrode model as opposed to the mathematically ideal continuum model, is processed to obtain VHED functions. We compare the use of VHED functions as inputs against the alternative paradigm of using raw EIT voltages. Our results show that (i) stroke classification can be performed with high accuracy using 2D EIT data from physically detailed and mathematically realistic models, and (ii) in the presence of noise, VHED functions outperform raw data as network inputs.