The ACE1 Electrical Impedance Tomography System for Thoracic Imaging.

The design and performance of the ACE1 (Active Complex Electrode) electrical impedance tomography system for single-ended phasic voltage measurements is presented. The design of the hardware and calibration procedures allow for reconstruction of conductivity and permittivity images. Phase measurement is achieved with the ACE1 active electrode circuit which measures the amplitude and phase of the voltage and the applied current at the location at which current is injected into the body. An evaluation of the system performance under typical operating conditions includes details of demodulation and calibration and an in-depth look at insightful metrics, such as signal-to-noise ratio variations during a single current pattern. Static and dynamic images of conductivity and permittivity are presented from ACE1 data collected on tank phantoms and human subjects to illustrate the system's utility.

Domain independent post-processing with graph U-nets: applications to electrical impedance tomographic imaging⋆.

Objective.To extend the highly successful U-Net Convolutional Neural Network architecture, which is limited to rectangular pixel/voxel domains, to a graph-based equivalent that works flexibly on irregular meshes; and demonstrate the effectiveness on electrical impedance tomography (EIT).Approach.By interpreting the irregular mesh as a graph, we develop a graph U-Net with new cluster pooling and unpooling layers that mimic the classic neighborhood based max-pooling important for imaging applications.Mainresults.The proposed graph U-Net is shown to be flexible and effective for improving early iterate total variation (TV) reconstructions from EIT measurements, using as little as the first iteration. The performance is evaluated for simulated data, and on experimental data from three measurement devices with different measurement geometries and instrumentations. We successfully show that such networks can be trained with a simple two-dimensional simulated training set, and generalize to very different domains, including measurements from a three-dimensional device and subsequent 3D reconstructions.Significance.As many inverse problems are solved on irregular (e.g. finite element) meshes, the proposed graph U-Net and pooling layers provide the added flexibility to process directly on the computational mesh. Post-processing an early iterate reconstruction greatly reduces the computational cost which can become prohibitive in higher dimensions with dense meshes. As the graph structure is independent of 'dimension', the flexibility to extend networks trained on 2D domains to 3D domains offers a possibility to further reduce computational cost in training.

Supporting conscious competency: Validation of the Generic Supervision Assessment Tool (GSAT).

OBJECTIVES: Clinical supervision is essential for ensuring effective service delivery. International imperatives to demonstrate professional competence has increased attention on the role of supervision in enhancing client outcomes. Although supervisor competency tools are recognised as important components in effective supervision, there remains a shortage of tools that are evidenced-based, applicable across workforces and freely accessible. DESIGN: An expert multidisciplinary group developed the Generic Supervision Assessment Tool (GSAT) to assess supervisor competencies across a range of professions. Initially the GSAT consisted of 32 items responded to by either a supervisor (GSAT-SR) or supervisee (GSAT-SE). The current study, using surveys, employed a cross-sectional design to test the reliability and construct validity of the GSAT. METHODS: The study consisted of two phases and included 12 professional groups across Australasia. In 2018, exploratory factor analysis (EFA) was undertaken with survey data from 479 supervisors and 447 supervisees. In 2019 survey data from 182 supervisors and 186 supervisees were used to conduct confirmatory factor analysis (CFA). The results were used to refine and validate the GSAT. RESULTS: The final GSAT-SR has four factors with 26 competency items. The final GSAT-SE has two factors with 21 competency items. The EFA and CFA confirmed that the GSAT-SR and the GSAT-SE are psychometrically valid tools that supervisors and supervisees can utilise to assess competencies. CONCLUSION: As a non-discipline specific supervision tool, the GSAT is a validated, freely available tool for benchmarking the competencies of clinical supervisors across professions, potentially optimising supervisory evaluation processes and strengthening supervision effectiveness. PRACTITIONER POINTS: Supervisor competency tools are recognised as important components of safe and effective supervision provision yet there is a dearth of valid, reliable and effective measures. The Generic Supervision Assessment Tool (GSAT-SR and GSAT-SE) are unique psychometrically valid, and reliable measures of supervisor competence. The GSAT-SR and the GSAT-SE can enhance translation of evidence-based supervision competency skills into regular practice. Validated with a broad cross section of professionals in diverse practice settings the GSAT provides a comprehensive conceptualization of supervisor competence.

Graph Convolutional Networks for Model-Based Learning in Nonlinear Inverse Problems.

The majority of model-based learned image reconstruction methods in medical imaging have been limited to uniform domains, such as pixelated images. If the underlying model is solved on nonuniform meshes, arising from a finite element method typical for nonlinear inverse problems, interpolation and embeddings are needed. To overcome this, we present a flexible framework to extend model-based learning directly to nonuniform meshes, by interpreting the mesh as a graph and formulating our network architectures using graph convolutional neural networks. This gives rise to the proposed iterative Graph Convolutional Newton-type Method (GCNM), which includes the forward model in the solution of the inverse problem, while all updates are directly computed by the network on the problem specific mesh. We present results for Electrical Impedance Tomography, a severely ill-posed nonlinear inverse problem that is frequently solved via optimization-based methods, where the forward problem is solved by finite element methods. Results for absolute EIT imaging are compared to standard iterative methods as well as a graph residual network. We show that the GCNM has good generalizability to different domain shapes and meshes, out of distribution data as well as experimental data, from purely simulated training data and without transfer training.

Incorporating a Spatial Prior into Nonlinear D-Bar EIT Imaging for Complex Admittivities.

Electrical Impedance Tomography (EIT) aims to recover the internal conductivity and permittivity distributions of a body from electrical measurements taken on electrodes on the surface of the body. The reconstruction task is a severely ill-posed nonlinear inverse problem that is highly sensitive to measurement noise and modeling errors. Regularized D-bar methods have shown great promise in producing noise-robust algorithms by employing a low-pass filtering of nonlinear (nonphysical) Fourier transform data specific to the EIT problem. Including prior data with the approximate locations of major organ boundaries in the scattering transform provides a means of extending the radius of the low-pass filter to include higher frequency components in the reconstruction, in particular, features that are known with high confidence. This information is additionally included in the system of D-bar equations with an independent regularization parameter from that of the extended scattering transform. In this paper, this approach is used in the 2-D D-bar method for admittivity (conductivity as well as permittivity) EIT imaging. Noise-robust reconstructions are presented for simulated EIT data on chest-shaped phantoms with a simulated pneumothorax and pleural effusion. No assumption of the pathology is used in the construction of the prior, yet the method still produces significant enhancements of the underlying pathology (pneumothorax or pleural effusion) even in the presence of strong noise.

The ACE1 thoracic Electrical Impedance Tomography system for ventilation and perfusion.

Electrical Impedance Tomography (EIT) is a technique which can image the varying electrical properties of biological tissues. For clinical use of EIT, it can be advantageous to know both tissue conductivity and permittivity. Presented is the hardware design for the pairwise current injection active complex electrode (ACE1) EIT system which measures phasic voltages for conductivity and permittivity image reconstruction. In this system, alternating current is injected on electrodes on the boundary of a domain and single-ended voltage measurements are used in image reconstructions of the domain's interior and in calculating the current applied at the electrodes.

Direct EIT reconstructions of complex admittivities on a chest-shaped domain in 2-D.

Electrical impedance tomography (EIT) is a medical imaging technique in which current is applied on electrodes on the surface of the body, the resulting voltage is measured, and an inverse problem is solved to recover the conductivity and/or permittivity in the interior. Images are then formed from the reconstructed conductivity and permittivity distributions. In the 2-D geometry, EIT is clinically useful for chest imaging. In this work, an implementation of a D-bar method for complex admittivities on a general 2-D domain is presented. In particular, reconstructions are computed on a chest-shaped domain for several realistic phantoms including a simulated pneumothorax, hyperinflation, and pleural effusion. The method demonstrates robustness in the presence of noise. Reconstructions from trigonometric and pairwise current injection patterns are included.