Use of machine learning to diagnose breast cancer from raw electrical impedance tomography data

The aim of the present work was to study the use of support vector machines to create an automatic physician assistant for three-dimensional (3D) electrical impedance tomography (EIT) of the breast. This work showed that machine learning based on the linear support vector machine can be used to create an algorithm for classifying the raw measurement results of a 3D EIT system for breast diagnostics. The maximum sensitivity was 82%, with specificity 85% and accuracy 84%.