Electrical bioimpedance and other techniques for gastric emptying and motility evaluation

Image Reconstruction Using Supervised Learning in Wearable Electrical Impedance Tomography of the Thorax

Electrical impedance tomography (EIT) is a non-invasive technique for visualizing the internal structure of a human body. Capacitively coupled electrical impedance tomography (CCEIT) is a new contactless EIT technique that can potentially be used as a wearable device. Recent studies have shown that a machine learning-based approach is very promising for EIT image reconstruction. Most of the studies concern models containing up to 22 electrodes and focus on using different artificial neural network models, from simple shallow networks to complex convolutional networks. However, the use of convolutional networks in image reconstruction with a higher number of electrodes requires further investigation. In this work, two different architectures of artificial networks were used for CCEIT image reconstruction: a fully connected deep neural network and a conditional generative adversarial network (cGAN). The training dataset was generated by the numerical simulation of a thorax phantom with healthy and illness-affected lungs. Three kinds of illnesses, pneumothorax, pleural effusion, and hydropneumothorax, were modeled using the electrical properties of the tissues. The thorax phantom included the heart, aorta, spine, and lungs. The sensor with 32 area electrodes was used in the numerical model. The ECTsim custom-designed toolbox for Matlab was used to solve the forward problem and measurement simulation. Two artificial neural networks were trained with supervision for image reconstruction. Reconstruction quality was compared between those networks and one-step algebraic reconstruction methods such as linear back projection and pseudoinverse with Tikhonov regularization. This evaluation was based on pixel-to-pixel metrics such as root-mean-square error, structural similarity index, 2D correlation coefficient, and peak signal-to-noise ratio. Additionally, the diagnostic value measured by the ROC AUC metric was used to assess the image quality. The results showed that obtaining information about regional lung function (regions affected by pneumothorax or pleural effusion) is possible using image reconstruction based on supervised learning and deep neural networks in EIT. The results obtained using cGAN are strongly better than those obtained using a fully connected network, especially in the case of noisy measurement data. However, diagnostic value estimation showed that even algebraic methods allow us to obtain satisfactory results.

Modeling and imaging of intestinal electrical impedance based on conjugate gradient method

Colorectal disease is a digestive tract disease of high incidence worldwide. Its preliminary diagnosis methods such as anal digital diagnosis and enteroscopy are somewhat subjective. Moreover, it is difficult to locate precisely the lesions and their infiltration boundaries for an accurate diagnosis of disease. This study combines endoscope with electrodes placed on the inner wall of the intestine to obtain both the traditional image of the intestine lumen and its electrical impedance tomography (EIT). The spatial impedance distribution image is reconstructed from the data collected by different combination of excitation and detection electrodes. The multidimensional and multiparameter intestinal physiological and pathological changes can thus be analyzed by EIT. This study mainly consists of the following three contributions: (a) construct certain physical models that reflect corresponding characteristics of intestinal tissue and its pathological changes; (b) optimize targeted signal acquisition methods suitable for data processing and analysis of intestinal cavity; and (c) establish a method of image reconstruction that conforms to the morphological characteristics of the intestinal cavity, so that comparative analysis can be applied by using different algorithms for image reconstruction. Through the extraction and analysis of impedance information for intestinal characteristics, we aim to make this tool a supplementary diagnosis method of high sensitivity and specificity for related diseases. This may lay a foundation for more accurate clinical screening of high-risk population, more precise diagnosis and localization of lesion characteristics, and thus better treatment guidance.

Review on Electrical Impedance Tomography: Artificial Intelligence Methods and its Applications

Electrical impedance tomography (EIT) has been a hot topic among researchers for the last 30 years. It is a new imaging method and has evolved over the last few decades. By injecting a small amount of current, the electrical properties of tissues are determined and measurements of the resulting voltages are taken. By using a reconstructing algorithm these voltages then transformed into a tomographic image. EIT contains no identified threats and as compared to magnetic resonance imaging (MRI) and computed tomography (CT) scans (imaging techniques), it is cheaper in cost as well. In this paper, a comprehensive review of efforts and advancements undertaken and achieved in recent work to improve this technology and the role of artificial intelligence to solve this non-linear, ill-posed problem are presented. In addition, a review of EIT clinical based applications has also been presented.

Effects of occupational stress on the gastrointestinal tract

The aim of this review is to provide a general overview of the relationship between occupational stress and gastrointestinal alterations. The International Labour Organization suggests occupational health includes psychological aspects to achieve mental well-being. However, the definition of health risks for an occupation includes biological, chemical, physical and ergonomic factors but does not address psychological stress or other affective disorders. Nevertheless, multiple investigations have studied occupational stress and its physiological consequences, focusing on specific risk groups and occupations considered stressful. Among the physiological effects of stress, gastrointestinal tract (GIT) alterations are highly prevalent. The relationship between occupational stress and GIT diseases is evident in everyday clinical practice; however, the usual strategy is to attack the effects but not the root of the problem. That is, in clinics, occupational stress is recognized as a source of GIT problems, but employers do not ascribe it enough importance as a risk factor, in general, and for gastrointestinal health, in particular. The identification, stratification, measurement and evaluation of stress and its associated corrective strategies, particularly for occupational stress, are important topics to address in the near future to establish the basis for considering stress as an important risk factor in occupational health.

Effect of psychological stress on gastric motility assessed by electrical bio-impedance

AIM: To evaluate gastric motility using electrical bio-impedance (EBI) and gastric changes as a result of stress induced by psychological tests.

METHODS: A group of 57 healthy women, aged 40-60 years, was recruited, and a clinical history and physical examination were performed. The women were free from severe anxiety, chronic or acute stress, severe depression, mental diseases and conditions that affect gastric activity. The women were evaluated under fasting conditions, and using a four-electrode configuration, the gastric signals were obtained through a BIOPAC MP-150 system. The volunteers were evaluated using the following paradigm: basal state, recording during the Stroop Test, intermediate resting period, recording during the Raven Test, and a final resting period. We analyzed the relative areas of the frequency spectrum: A1 (1-2 cpm), A2 (2-4 cpm), A3 (4-8 cpm), and A4 (8-12 cpm), as well as the median of area A2 + A3. The data were analyzed by an autoregressive method using a Butterworth filter with MatLab and Origin. Analysis of variance (ANOVA) and Friedman ANOVA (for nonparametric variables) were performed; in addition, pairs of groups were compared using the T dependent and Wilcoxon T tests.

RESULTS: The results of the main values of area A2 were not significantly different comparing the five steps of the experimental paradigm. Nevertheless, there was a tendency of this A2 region to decrease during the stress tests, with recuperation at the final resting step. When an extended gastric region was considered (1-4 cpm), significant differences with the psychological stress tests were present (F = 3.85, P = 0.005). The A3 region also showed significant changes when the stress psychological tests were administered (F = 7.25, P < 0.001). These differences were influenced by the changes in the adjacent gastric region of A2. The parameter that we proposed in previous studies for the evaluation of gastric motility by electrical bio-impedance (EBI) was the median of the area under the region from 2 to 8 cpm (A2 + A3). The mean values of these frequencies (median of the A2 + A3 area) with the stress test showed significant changes (F = 5.5, P < 0.001). The results of the Wilcoxon T test for the A4 area parameter, which is influenced by the breathing response, changed significantly during the Raven stress test (P < 0.05).

CONCLUSION: We confirm that the gastric response to acute psychological stress can be evaluated by short-term EBI.