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

An Augmented Reality (AR) system based on the holographic projection of the relevant anatomic structures is proposed for auxiliary visualization during surgeries. The current two-dimensional visualization systems require the surgeons to mentally extract the associated three-dimensional information during the interventions, which entails risks and complications. This work shows an AR holographic projection system for real-time three-dimensional representation of the relevant surgical information, thus overcoming this problem. As an initial proof of concept, the system is experimentally assessed as potential surgery training tool.Clinical Relevance- This work explores the potential of AR holographic projection systems for intraoperative assistance to the surgical team, starting from its possible use as surgery training and planning tool.

Background: Our previous study has shown that stimulation of the vagus nerve with low-intensity focused ultrasound could modulate blood pressure (BP), but the underlying mechanisms remain unclear. This study investigated the changes of cardiovascular neurotransmitter levels to indirectly evaluate the responses of the autonomic nervous system and renin-angiotensin system under low-intensity focused ultrasound stimulation (FUS) of the vagus nerve.

Methods: Cardiovascular neurotransmitter levels of epinephrine (EPI), norepinephrine (NE), and angiotensin II (ANGII) were measured and compared before and after the FUS in seven spontaneously hypertensive rats; and were also measured and compared between a target stimulation group (FUS, n = 6) and non-target stimulation group (Control, n = 5) after stimulation to exclude the influence of potential confounding factors.

Results: The t-test results showed that the levels of EPI, NE, and ANGII were significantly decreased (P < 0.05) after stimulation compared to before stimulation. Additionally, the levels of NE and EPI were significantly lower (P < 0.05) in the FUS group than in the Control group after stimulation, indicating that the activities of the sympathetic nervous system and renin-angiotensin system of the vagus nerve might be inhibited by FUS of the vagus nerve.

Conclusion: These findings reveal the mechanism of BP lowing in response to FUS of the vagus nerve.Clinical Relevance-This study revealed the mechanism of BP lowering in response to focused ultrasound stimulation of the vagus nerve through analyzing the changes of cardiovascular neurotransmitter levels.

Pesticides are still abused in modern agriculture. The effects of their exposure to even sub-lethal doses can be detrimental to ecosystem stability and human health. This work aims to validate the use of machine learning techniques for recognizing motor abnormalities and to assess any effect post-exposure to a minimal dosage of these substances on a model organism, gaining insights into potential risks for human health. The test subject was the Mediterranean fruit fly, Ceratitis capitata (Wiedemann) (Diptera: Tephritidae), exposed to food contaminated with the LC₃₀ of Carlina acaulis essential oil. A deep learning approach enabled the pose estimation within an arena. Statistical analysis highlighted the most significant features between treated and untreated groups. Based on this analysis, two learning-based algorithms, Random Forest (RF) and XGBoost were employed. The results were compared through different metrics. RF algorithm generated a model capable of distinguishing treated subjects with an area under the receiver operating characteristic curve of 0.75 and an accuracy of 0.71. Through an image-based analysis, this study revealed acute effects due to minimal pesticide doses. So, even small amounts of these biocides drifted far from distribution areas may negatively affect the environment and humans.

In this work, a fabrication process for implantable electrodes using a Cyclic Olefin Copolymer (COC) substrate and a SU-8 passivation layer was presented. COC and SU-8 were shown to be suitable for implantable neural electrodes due to their biocompatibility, chemical resistance, and thermal stability. The electrodes were successfully patterned on the COC film, and the SU-8 passivation layer was coated while maintaining site-opened via photolithography. The photocrosslinking lamination of the substrate and passivation layer was used to produce electrodes with fine line widths of 20um without applying heat.

Staining is a critical step in tissue analysis as it enhances the visibility and contrast of tissue structures for microscopic examination. Large tissue sections such as the human brain, heart, and liver are becoming increasingly important in studying complex tissue structures, providing critical information about the tissue's normal or abnormal development, function, and disease processes. Manual staining methods are still widely used and are prone to inconsistencies and inaccuracies, leading to unreliable results. Commercially available automated staining systems offer a more efficient alternative, but currently, these systems are only available for smaller 1" x 3" slides which are ill-suited for examining larger tissue sections. To address this challenge, we present a custom-designed Large format Automated Slide Stainer that can handle various glass slides, from the standard 1" x 3" slides to the custom-sized 2" x 3", 5" x 7", and 6" x 8" glass slides. The system uses a Cartesian robotic arm to stain the slides and has a user-friendly and intuitive interface for creating and modifying custom staining protocols. Safety features include chemical isolation, a ventilation system, an emergency shutdown, and a protective shield to minimize hazards from handling chemicals and biological materials. The automated stainer showed little variability in positioning with a mean offset error of 1.65 ± 0.65 mm and 1.73 ± 0.76 mm in the X and Y axes, respectively. In addition, the automated staining process showed better uniformity than manual staining. A pairwise distance was used to evaluate how well image histograms matched within a batch. The automated staining had a mean pairwise distance of 0.0070 ± 0.0017 (Nissl) and 0.0060 ± 0.0003 (Hematoxylin and Eosin(H&E)), which were far superior to the manual staining distances (Nissl: 0.0173 ± 0.0107 and H&E: 0.0185 ± 0.0067). This system represents a substantial advancement in tissue staining and has the potential to improve the reliability of tissue analysis significantly.Clinical relevance - Automated system for providing accurate, reproducible, and high-throughput staining of large tissue sections for use in histopathology and research.

Fatigue impairs cognitive and motor function, potentially leading to mishaps in high-pressure occupations such as aviation and emergency medical services. The current approach is primarily based on self-assessment, which is subjective and error-prone. An objective method is needed to detect severe and likely dangerous levels of fatigue quickly and accurately. Here, we present a quantitative evaluation tool that uses less than two minutes of facial video, captured using an iPad, to assess fatigue vs. alertness. The tool is fast, easy to use, and scalable since it uses cameras readily available on consumer-electronic devices. We compared the classification performance between a Long Short-Term Memory (LSTM) deep neural network and a Random Forest (RF) classifier applied to engineered features informed by domain knowledge. The preliminary results on an 11-subject dataset show that RF outperforms LSTM, with added interpretability on the features used. For the RF classifiers, the average areas under the receiver operating characteristic curve, based on the 11-fold and individualized 11-fold cross validations, are 0.72 ± 0.16 and 0.8 ± 0.12, respectively. Equal error rates are 0.34 and 0.26, respectively. This study presents a promising approach for rapid fatigue detection. Additional data will be collected to assess the generalizability across populations.

To study transcranial direct current stimulation (tDCS) and its effect on the brain, it could be useful to predict the distribution of the electric field induced in the brain with given tDCS parameters. As a solution, simulation with realistic computational models using magnetic resonance images (MRIs) have been widely used in the fields. With the recent advance of deep learning-based segmentation techniques of the brain, questions have been raised about if tDCS-induced electric field is affected by the deep brain structures. This study aimed to investigate the effect of the deep brain structure modeling on the induced electric field. To this end, we generated models with and without the deep brain structures by using an open MRI dataset comprising tDCS parameters, electric field simulation results and in-vivo intracranial recordings in the deep brain structures. We investigated the difference between the simulation results of the two models with a statistical analysis. Our results indicated that tDCS-induced electric fields and current flow in the brain are significantly different when the deep brain structures are considered.

Blood Pressure (BP) is often coined as a critical physiological marker for cardiovascular health. Multiple studies have explored either Photoplethysmogram (PPG) or ECG-PPG derived features for continuous BP estimation using machine learning (ML); deep learning (DL) techniques. Majority of those derived features often lack a stringent biological explanation and are not significantly correlated with BP. In this paper, we identified several clinically relevant (bio-inspired) ECG and PPG features; and exploited them to estimate Systolic (SBP), and Diastolic Blood Pressure (DBP) values using CatBoost, and AdaBoost algorithms. The estimation performance was then compared against popular ML algorithms. SBP and DBP achieved a Pearson's correlation coefficient of 0.90 and 0.83 between estimated and target BP values. The estimated mean absolute error (MAE) values are 3.81 and 2.22 mmHg with a Standard Deviation of 6.24 and 3.51 mmHg, respectively, for SBP and DBP using CatBoost. The results surpassed the Advancement of Medical Instrumentation (AAMI) standards. For the British Hypertension Society (BHS) protocol, the results achieved for all the BP categories resided in Grade A. Further investigation reveals that bio-inspired features along with tuned ML models can produce comparable results w.r.t parameter-intensive DL networks. ln(HR × mNPV), HR, BMI index, ageing index, and PPG-K point were identified as the top five key features for estimating BP. The group-based analysis further concludes that a trade-off lies between the number of features and MAE. Increasing the no. of features beyond a certain threshold saturates the reduction in MAE.

The tumor microenvironment (TME) is known as a chronic hypoxic environment, with spatiotemporal variation in oxygen concentration depending on the distance from blood vessels and the blood supply. In our previous studies, cancer cell behavior was observed under hypoxic conditions with spatial variation of oxygen concentration (oxygen concentration gradients); however, that under oxygen concentration gradients at low oxygen levels found in the TME has not been studied. In this study, we investigated the behavior of breast cancer cells at various oxygen concentration gradients, generated using a microfluidic device with oxygen concentration controllability. The results showed that cell distribution was altered in response to oxygen concentration, and tended to increase in a specific region at around 5% O₂. Evaluation of changes in cell numbers due to proliferation, migration, and cell death indicated that proliferation strongly affected cell distribution.

Neuromuscular electrical stimulation (NMES) has been demonstrated to effectively modulate cortical activities by evoking muscle contraction in upper limb and generating joint movements, which showed an excellent performance in motor rehabilitation. However, due to hand loss and cortical function reorganization induced by hand amputation, how neural activities in sensorimotor cortex response to NMES-evoked muscle contraction in the end of an amputation stump is not clear. In this paper, Ischemic nerve block (INB) technique was used to build an acute hand loss model, and 64-channel EEG signals were recorded from 11 healthy subjects to perform a 2×2 factorial design protocol, with the INB state and the current intensity as factors. The changes of NMES-evoked sensorimotor cortical activities were quantified by computing Beta-band event-related desynchronization (Beta ERD) patterns and the time-varying functional connectivity using adaptive directed transfer function (ADTF) before and during INB. The acute hand "loss" resulted in ipsilateral dominance of Beta ERD induced by NMES with two current intensities in the topographic maps, that is, ipsilateral Beta ERD was significantly higher than that the contralateral one (p<0.05). However, before INB, Beta ERD in the contralateral sensorimotor cortex induced by NMES above motor threshold was significantly higher than that in the ipsilateral area (p< 0.01). Meanwhile, whatever before or during INB, clustering coefficients of the ADTF network in sensorimotor cortex showed temporal dynamics during two NMES tasks. During INB, NMES above motor threshold-evoked lower clustering coefficients of the time-varying network in sensorimotor cortex than that before INB (p<0.05). The present results suggest that the loss of the hand proprioception will degrade cortical activities in the contralateral area, and increase cortical activities in the ipsilateral area compensatively responding to NMES. This finding may be particularly important to improve the reconstruction of the proprioception function of hand prosthesis.