Applied machine learning for stroke differentiation by electrical impedance tomography with realistic numerical models

Electrical impedance tomography (EIT) may have potential to overcome existing limitations in stroke differentiation, enabling low-cost, rapid, and mobile data collection. Combining bioimpedance measurement technologies such as EIT with machine learning classifiers to support decision-making can avoid commonly faced reconstruction challenges due to the nonlinear and ill-posed nature of EIT imaging. Therefore, in this work, we advance this field through a study integrating realistic head models with clinically relevant test scenarios, and a robust architecture consisting of nested cross-validation and principal component analysis. Specifically, realistic head models are designed which incorporate the highly conductive layers of cerebrospinal fluid in the subarachnoid space and ventricles. In total, 135 unique models are created to represent a large patient population, with normal, haemorrhagic, and ischemic brains. Simulated EIT voltage data generated from these models are used to assess the classification performance of support vector machines. Parameters explored include driving frequency, signal-to-noise ratio, kernel function, and composition of binary classes. Classifier accuracy at 60 dB signal-to-noise ratio, reported as mean and standard deviation, are (79.92% ± 10.82%) for lesion differentiation, (74.78% ± 3.79%) for lesion detection, (77.49% ± 15.90%) for bleed detection, and (60.31% ± 3.98%) for ischemia detection (after ruling out bleed). The results for each method were obtained with statistics from 3 independent runs with 17,280 observations, polynomial kernel functions, and feature reduction of 76% by PCA (from 208 to 50 features). While results of this study show promise for stroke differentiation using EIT data, our findings indicate that the achievable accuracy is highly dependent on the classification scenario and application-specific classifiers may be necessary to achieve acceptable accuracy.

Bioimpedance Sensing of Implanted Stent Occlusions: Smart Stent

Coronary artery disease is one of the most common diseases in developed countries and affects a large part of the population of developing countries. Preventing restenosis in patients with implanted stents is an important current medical problem. The purpose of this work is to analyse the viability of bioimpedance sensing to detect the formation of atheromatous plaque in an implantable stent. Simulations in COMSOL Multiphysics were performed to analyse the performance of the proposed bioimpedance sensing system, based on the Sheffield technique. Both non-pathological and pathological models (with atheromatous plaque), including the flow of blood were considered. Simulations with the non-pathological model showed a homogeneous distribution of the measured current intensity in the different electrodes, for every configuration. On the other hand, simulations with the pathological model showed a significant decrease of the measured current intensity in the electrodes close to the simulated atheromatous plaque. The presence of the atheromatous plaque can, therefore, be detected by the system with a simple algorithm, avoiding the full reconstruction of the image and the subsequent computational processing requirements.

Analog Integrated Current Drivers for Bioimpedance Applications: A Review

An important component in bioimpedance measurements is the current driver, which can operate over a wide range of impedance and frequency. This paper provides a review of integrated circuit analog current drivers which have been developed in the last 10 years. Important features for current drivers are high output impedance, low phase delay, and low harmonic distortion. In this paper, the analog current drivers are grouped into two categories based on open loop or closed loop designs. The characteristics of each design are identified.