Optimized breath detection algorithm in Electrical Impedance Tomography

Abstract

Abstract.Objective: This paper define a method for optimizing the breath delineation algorithms used in Electrical Impedance Tomography (EIT). In lung EIT the identification of the breath phases is central for generating tidal impedance variation images, subsequent data analysis and clinical evaluation. The optimisation of these algorithms is particularly important in neonatal care since the existing breath detectors developed for adults may give insufficient reliability in neonates due to their very irregular breathing pattern. Approach: Our approach is generic in the sense that it relies on the definition of a gold standard and the associated definition of detector sensitivity and specificity, an optimisation criterion and a set of detector parameters to be investigated. The gold standard has been defined by 11 clinicians with previous experience with EIT and the performance of our approach is described and validated using a neonatal EIT dataset acquired within the EU-funded CRADL project. Main results: Three different algorithms are proposed that are improving the breath detector performance by adding conditions on 1) maximum tidal breath rate obtained from zero-crossings of the EIT breathing signal, 2) minimum tidal impedance amplitude and 3) minimum tidal breath rate obtained from Time-Frequency (TF) analysis. Significance: Based on the gold standard, the most crucial parameters of the proposed algorithms are optimised by using a simple exhaustive search and a weighted metric defined in connection with the Receiver Operating Characterics (ROC). This provides a practical way to achieve any desirable trade-off between the sensitivity and the specificity of the detectors.

Effects of PEEP on the relationship between tidal volume and total impedance change measured via electrical impedance tomography (EIT)

“…Impedance changes were evaluated within the entire lung region generating a global region of interest (global ROI) by using a breath detection algorithm [ 25 ] in dedicated software (Ibex, Swisstom, Switzerland). Seven breaths were included in the analysis as the respiratory rate was set at 8 bpm on the ventilator.…”

NeuroKit2: A Python toolbox for neurophysiological signal processing

“…For example, the rsp_clean() function uses signal_filter() and signal_detrend(), with different sets of default parameters that can be switched with a "method" argument (corresponding to different published or established pipelines). For instance, setting method="khodadad2018" will use the cleaning workflow described in Khodadad et al (2018).…”

Effect of sternal electrode gap and belt rotation on the robustness of pulmonary electrical impedance tomography parameters

“…A single EIT patient interface could accelerate the implementation of EIT in routine neonatal care (Frerichs et al 2017). Recently a textile interface with 32 electrodes integrated into one belt has been developed (Sophocleous et al 2018. This interface offers several advantages in comparison with the use of individual adhesive electrodes.…”

“…This interface offers several advantages in comparison with the use of individual adhesive electrodes. It enables fast, accurate and reproducible positioning of the electrodes around the chest and, in addition, it does not create any discomfort, distress or adverse effects to the neonatal patients (Sophocleous et al 2018). These characteristics offer the potential for use in emergencies such as resuscitation at birth (McCall et al 2017, Tingay et al 2015, 2019a).…”

“…Although the distance between each electrode and chest circumference is known, forward and inverse models (Boyle et al 2017) may lead to a wrong result or a rotated image. In addition, the belt internal diameter may not exactly match the chest circumference, resulting in a variably sized gap at the point of fixation (closing mechanism) between the first and last electrode over the sternum (Sophocleous et al 2018).…”