Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference最新文献

Accurate pulse-oximeter readings are critical for clinical decisions, especially when arterial blood-gas tests - the gold standard for determining oxygen saturation levels - are not available, such as when determining COVID-19 severity. Several studies demonstrate that pulse oxygen saturation estimated from photoplethysmography (PPG) introduces a racial bias due to the more profound scattering of light in subjects with darker skin due to the increased presence of melanin. This leads to an overestimation of blood oxygen saturation in those with darker skin that is increased for low blood oxygen levels and can result in a patient not receiving potentially life-saving supplemental oxygen. This racial bias has been comprehensively studied in conventional finger pulse oximetry but in other less commonly used measurement sites, such as in-ear pulse oximetry, it remains unexplored. Different measurement sites can have thinner epidermis compared with the finger and lower exposure to sunlight (such as is the case with the ear canal), and we hypothesise that this could reduce the bias introduced by skin tone on pulse oximetry. To this end, we compute SpO₂ in different body locations, during rest and breath-holds, and compare with the index finger. The study involves a participant pool covering 6-pigmentation categories from Fitzpatrick's Skin Pigmentation scale. These preliminary results indicate that locations characterized by cartilaginous highly vascularized tissues may be less prone to the influence of melanin and pigmentation in the estimation of SpO₂, paving the way for the development of non-discriminatory pulse oximetry devices.

Growing evidence suggests that variations in cognitive and emotional behavior are associated with variations in brain function. To achieve a more comprehensive assessment, data-driven techniques, specifically independent component analysis (ICA), can be employed to generate outcome variables that describe unique but complementary aspects of functional connectivity within and between networks. In this study, resting-state fMRI and behavioral data were collected from 50 healthy participants in the Human Connectome Project. The neuropsychological battery evaluated performance in various domains, including episodic memory, fluid intelligence, attention, working memory, executive function, cognitive flexibility, inhibition, and processing speed. Emotional measures were also included to assess emotion recognition and negative affects (sadness, fear, and anger). A multivariate approach was adopted to evaluate the association between cognitive abilities and emotional correlates on spatiotemporal features of intrinsic connectivity networks (ICNs). The results were explored at a false discovery rate-corrected threshold of p < 0.05. There was a significant positive association between within-network connectivity of the left central executive network (CEN) and inhibitory control and attention, and a significant negative association between within-network connectivity of the right CEN and episodic memory. Furthermore, increased within-network connectivity of the default-mode network (DMN) was linked to higher fluid intelligence, while within-network connectivity in the salience network (SN) and dorsal attention network (DAN) was associated with cognitive flexibility. Anger was found to be significantly related to increased functional network connectivity between SN and CEN. Sadness and fear were associated with increased within-network connectivity of the right CEN. Additionally, fear was associated with low-frequency spectral power in SN and DMN. These findings offer new insights into the intricate relation between ICN features and cognitive and emotional functions.

Cardiac autonomic Neuropathy (CAN) is an acute complication of Diabetes mellitus (DM) that does not exhibit overt symptoms in the subclinical stage. Researchers have developed several techniques that have proved to give higher efficiency in classification using software tools. The challenge in implementing the same using hardware for diagnosis fails when classification boundaries are mismatched, as there are more chances of misinterpreting the classes. In this study, we have introduced translational research between the complexity analysis using software and verifying the same by deploying it in hardware using a controller board by investigating the error percentage in classifying normal (N) and early CAN (E). The study reveals that among the segments specific to CAN diagnosis, RR and ST show more error percentages (12±8 %). In contrast, PR and QT show a lesser error percentage (6±4 %) between software and hardware implementation of Fractal dimension (FD) values.

Super resolution ultrasound imaging (SR-US) methods including super-resolution optical fluctuation imaging (SOFI) have been successfully demonstrated to improve imaging performance of ultrasound (US). However, the imaging quality of US improved by conventional SOFI depends on the probability of microbubbles (MB) appearing in imaging regions. Current SOFI-based ultrasound imaging methods usually fix the probability of MBs, ignoring the effect of probability characteristics, leading to artifacts in high-order SOFI images. Inspired by active-modulated SOFI (AR-SOFI), in this paper, we propose a new method, termed as AR-SOFI-US, for further improving the performance of SR-US, which is achieved by effectively controlling the probabilities of MBs on an appropriate range. Through a series of numerical simulations, we compare the imaging resolution at differing MB probabilities and demonstrate that by controlling the probabilities of MBs when they appear in the imaging regions, incorporating the proposed AR-SOFI-US method, we can improve the spatial resolution of SR-US to a higher degree, especially for the high-order SOFI imaging results.

Pulse-wave velocity (PWV) can be used to quantify arterial stiffness, allowing for a diagnosis of this condition. Multi-beam laser-doppler vibrometry offers a cheap, non-invasive and user-friendly alternative to measuring PWV, and its feasibility has been previously demonstrated in the H2020 project CARDIS. The two handpieces of the prototype CARDIS device measure skin displacement above main arteries at two different sites, yielding an estimate of the pulse-transit time (PTT) and, consequently, PWV. The presence of multiple beams (channels) on each handpiece can be used to enhance the underlying signal, improving the quality of the signal for PTT estimation and further analysis. We propose two methods for multi-channel LDV data processing: beamforming and beamforming-driven ICA. Beamforming is done by an SNR-weighted linear combination of the time-aligned channels, where the SNR is blindly estimated from the signal statistics. ICA uses the beamformer to resolve its inherent permutation and scale ambiguities. Both methods yield a single enhanced signal at each handpiece, where spurious peaks in the individual channels as well as stochastic noise are well suppressed in the output. Using the enhanced signals yields individual PTT estimates with a low spread compared to the baseline approach. While the enhancement is introduced in the context of PTT estimation, the approaches can be used to enhance signals in other biomedical applications of multi-channel LDV as well.

A reform in the diagnosis and treatment process is urgently required as carotid artery disease remains a leading cause of death in the world. To this purpose, all computational techniques are now being applied to enhancing the most cutting-edge diagnosis techniques. Computational modeling of plaque generation and evolution is being refined over the past years to forecast the atherosclerotic progression and the corresponding risk in patient-specific carotid arteries. A prerequisite to their implementation is the reconstruction of the precise three-dimensional models of patient-specific main carotid arteries. Even with the most sophisticated algorithms, accurate reconstruction of the arterial vessel is frequently difficult. Furthermore, there are several works of plaque growth modeling that ignore the reconstruction of the artery's outer layer in favor of a virtual one. In this paper, we investigate the importance of an accurate adventitia layer in plaque growth modeling. This is done as a comparative study by implementing a novel plaque growth model in two reconstructed carotid arterial segments using either their realistic or virtual adventitia layer as input. The results indicate that accurate adventitia reconstruction is of minor importance regarding species distributions and plaque growth in carotid segments, which initially did not contain any plaque regions.Clinical Relevance- The findings of this comparative study emphasize the importance of precise adventitia geometry in plaque growth modeling. As a result, this work sets a higher standard for publishing new plaque growth models.

In Human-Robot Collaboration setting a robot may be controlled by a user directly or through a Brain-Computer Interface that detects user intention, and it may act as an autonomous agent. As such interaction increases in complexity, conflicts become inevitable. Goal conflicts can arise from different sources, for instance, interface mistakes - related to misinterpretation of human's intention - or errors of the autonomous system to address task and human's expectations. Such conflicts evoke different spontaneous responses in the human's brain, which could be used to regulate intrinsic task parameters and to improve system response to errors - leading to improved transparency, performance, and safety. To study the possibility of detecting interface and agent errors, we designed a virtual pick and place task with sequential human and robot responsibility and recorded the electroencephalography (EEG) activity of six participants. In the virtual environment, the robot received a command from the participants through a computer keyboard or it moved as autonomous agent. In both cases, artificial errors were defined to occur in 20% - 25% of the trials. We found differences in the responses to interface and agent errors. From the EEG data, correct trials, interface errors, and agent errors were truly predicted for 51.62% ± 9.99% (chance level 38.21%) of the pick movements and 46.84%±6.62% (chance level 36.99%) for the place movements in a pseudo-asynchronous fashion. Our study suggests that in a human-robot collaboration setting one may improve the future performance of a system with intention detection and autonomous modes. Specific examples could be Neural Interfaces that replace and restore motor functions.

We investigate Self-Attention (SA) networks for directly learning visual representations for prosthetic vision. Specifically, we explore how the SA mechanism can be leveraged to produce task-specific scene representations for prosthetic vision, overcoming the need for explicit hand-selection of learnt features and post-processing. Further, we demonstrate how the mapping of importance to image regions can serve as an explainability tool to analyse the learnt vision processing behaviour, providing enhanced validation and interpretation capability than current learning-based methods for prosthetic vision. We investigate our approach in the context of an orientation and mobility (OM) task, and demonstrate its feasibility for learning vision processing pipelines for prosthetic vision.

Labeled ECG data in diseased state are, however, relatively scarce due to various concerns including patient privacy and low prevalence. We propose the first study in its kind that synthesizes atrial fibrillation (AF)-like ECG signals from normal ECG signals using the AFE-GAN, a generative adversarial network. Our AFE-GAN adjusts both beat morphology and rhythm variability when generating the atrial fibrillation-like ECG signals. Two publicly available arrhythmia detectors classified 72.4% and 77.2% of our generated signals as AF in a four-class (normal, AF, other abnormal, noisy) classification. This work shows the feasibility to synthesize abnormal ECG signals from normal ECG signals.Clinical significance - The AF ECG signal generated with our AFE-GAN has the potential to be used as training materials for health practitioners or be used as class-balance supplements for training automatic AF detectors.

Electrical Impedance Tomography (EIT) is a cost-effective and fast way to visualize dielectric properties of the human body, through the injection of alternating currents and measurement of the resulting potential on the bodies surface. However, this comes at the cost of low resolution as EIT is a non-linear ill-posed inverse problem. Recently Deep Learning methods have gained the interest in this field, as they provide a way to mimic non-linear functions. Most of the approaches focus on the structure of the Artificial Neural Networks (ANNs), while only glancing over the used training data. However, the structure of the training data is of great importance, as it needs to be simulated. In this work, we analyze the effect of basic shapes to be included as targets in the training data set. We compared inclusions of ellipsoids, cubes and octahedra as training data for ANNs in terms of reconstruction quality. For that, we used the well-established GREIT figures of merit on laboratory tank measurements. We found that ellipsoids resulted in the best reconstruction quality of EIT images. This shows that the choice of simulation data has an impact on the ANN reconstruction quality.Clinical relevance- This work helps to improve time independent EIT reconstruction, which in turn allows for extraction of time independent features of e.g., the lung.