Neural networks for classification of strokes in electrical impedance tomography on a 3D head model

TL;DR

This study explores neural network models for rapid, non-invasive detection of brain strokes using 3D electrical impedance tomography data, achieving high accuracy on synthetic datasets and paving the way for clinical applications.

Contribution

It introduces neural network architectures for classifying strokes in 3D EIT data, demonstrating high accuracy on synthetic datasets with various realistic conditions.

Findings

Fully connected networks achieve ≥90% accuracy

Convolutional networks achieve ≥80% accuracy

Results are promising for real-world clinical translation

Abstract

We consider the problem of the detection of brain hemorrhages from three dimensional (3D) electrical impedance tomography (EIT) measurements. This is a condition requiring urgent treatment for which EIT might provide a portable and quick diagnosis. We employ two neural network architectures -- a fully connected and a convolutional one -- for the classification of hemorrhagic and ischemic strokes. The networks are trained on a dataset with $40\,000$ samples of synthetic electrode measurements generated with the complete electrode model on realistic heads with a 3-layer structure. We consider changes in head anatomy and layers, electrode position, measurement noise and conductivity values. We then test the networks on several datasets of unseen EIT data, with more complex stroke modeling (different shapes and volumes), higher levels of noise and different amounts of electrode misplacement. On most test datasets we achieve $\geq 90\%$ average accuracy with fully connected neural networks, while the convolutional ones display an average accuracy $\geq 80\%$. Despite the use of simple neural network architectures, the results obtained are very promising and motivate the applications of EIT-based classification methods on real phantoms and ultimately on human patients.