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

This study aimed to explore the feasibility of using portable single-channel dry electrode electroencephalography (EEG) headbands to identify and distinguish human emotions elicited by multimodal stimuli presented in a 360-degree immersive environment. Such an environment was specifically chosen to facilitate naturalistic perception, in contrast to the conventional presentation of stimuli through a flat screen and headphones in the laboratory setting. To this end, this study designed multimodal stimulation and recorded the subjective scores of the subjects in multiple emotional dimensions through a self-rating scale. The differential entropy (DE) feature was used to capture the dynamic changes and complexity of the EEG signal. A variety of classic machine learning (ML) models were used for classification, and the feature performance and model effectiveness were compared and analyzed. The results show that after removing most artifacts and applying DE features, single-channel EEG signals can effectively distinguish different emotional states measured under multimodal stimulation. In summary, this study provides empirical support for emotion recognition using single-channel EEG in a 360-degree immersive environment, which allowed for naturalistic perception while maintaining the advantages of a controlled setting. This marks a step toward multi-user applications by leveraging the portability and convenience of portable devices.

Hypertrophic cardiomyopathy (HCM) represents one of the leading causes of sudden cardiac death (SCD), particularly in the young population, with a risk of approximately 1% per year. So far, no reliable electrocardiogram (ECG) biomarkers have been presented for risk assessment, but ECG in HCM patients are often abnormal due to structural and electrical abnormalities. This study aimed to extract morphological ECG biomarkers to differentiate HCM patients based on their arrhythmic risk levels (15 HCM patients with arrhythmic events vs. 40 HCM control). We extracted ECG features including width, amplitudes, slopes between fiducial points, Hermite transform coefficients, and variational mode decomposition features. Following feature selection using combined metrics, the study population was divided into two groups for each ECG biomarker, with the median value serving as the cutoff point to distinguish between the groups. QRS and T waverelated features effectively separated patients into high and low arrhythmic risk categories. Notably, univariate Cox regression analysis showed that patients having more local QRS optima or highest percentage of negative QRS present the highest risk (p< 0.01 and p< 0.05 respectively). In conclusion, we proposed automatic ECG extracted features that can be used to stratify the risk for arrhythmic events in HCM patients.Clinical Relevance-This study provides novel insights into ECG-based risk stratification for HCM patients, offering potential tools for early identification of individuals at higher risk of cardiac events.

Flexible wearable walking-assist robots, unlike rigid rehabilitation robots, offer lightweight designs and ease of wear. This study focused on quantifying differences in joint coordination patterns between robotic and human motion during gait. Eleven healthy participants completed 2-min treadmill walking trials in three conditions: normal walking (None), walking with the robot worn but inactive (Off), and walking with the robot worn and active (On). Using a vector coding technique, coupling angles and their variability were analyzed across four gait phases. An increase in the coupling angle was detected in the mid stance and late stance phases in the On condition, which was driven by changes in the knee joint angles. Coupling angle variability was significantly reduced in the terminal swing phase in the On condition compared to None, suggesting enhanced consistency in the movement. These findings suggest that a vector coding technique can detect differences in hip-knee joint coordination patterns in the mid and late stance phases between non-assisted and assisted walking with a hip assist robot and that coupling angle can be used as a measure for evaluating kinematics of assisted walking.Clinical Relevance- A vector coding technique can be used to evaluate the effect of walking assist robot on movement patterns for a better applicability in daily life.

Understanding how neural systems drive behavior is a fundamental goal in neuroscience. Numerous studies have demonstrated that the activity of large neural populations is often governed by low-dimensional neural dynamics. While much of the current research has focused on extracting informative and interpretable latent dynamics from individual motor tasks, it remains unclear whether these dynamics are preserved across different motor tasks. This question is particularly critical, as prior experience with a related task can facilitate faster learning in a new task. In this paper, we propose a Convolutional Transformer-based Variational Autoencoder (Conformer-VAE) to extract preserved neural latent dynamics across tasks by leveraging the rich spatiotemporal patterns in neural activity. We validate our approach using neural recordings from a rat, which first performed a one-lever pressing task (old task) and subsequently a two-lever discrimination task (new task). By projecting the inferred latent dynamics from both tasks onto a common 2D PCA plane, our results demonstrate that Conformer-VAE effectively captures preserved neural dynamics across tasks, outperforming baseline methods. Moreover, these preserved dynamics enable faster decoder training for the new task by transferring the neural-to-movement mapping learned from the old task. This capability facilitates seamless real-time task switching, offering promising applications for brain-machine interface systems.Clinical Relevance-This work facilitates faster adaptation in brain-machine interfaces by preserving neural dynamics across tasks, offering potential benefits for neuroprosthetics and motor rehabilitation in patients with motor impairments.

Magnetic resonance electrical properties tomography (MR-EPT) is a non-invasive imaging technique for mapping tissue electrical properties (EPs), offering significant potential for disease diagnosis and ablation therapy. Previously proposed Dixon-based techniques for liver electrical properties (EPs) were established on literature values and lack exploration of individual differences. We developed a Dixon Fat Fraction Electrical Properties (FF-EPs) model and successfully reconstructed EPs from phantoms using this model. Differences in measurements between the FF-EPs technique and the open-end coaxial probe (OECP) method were investigated by ex vivo porcine livers experiments. The absolute error of the FF-EPs reconstructed permittivity is 2.43, and the absolute error of the conductivity is 0.125 S/m. This study validates the effectiveness of FF-EPs and holds promise for clinical application in acquiring patient liver EPs, thereby aiding in disease diagnosis and guiding ablation therapy.

This study introduces an innovative framework, Ensemble Guide Fine-tuning (EGFit), for Pre-Trained Models, designed to address the challenges of data scarcity in kinase targeted drug discovery. Protein kinases play a pivotal role in cancer, immune diseases, and other complex disorders, making them a critical drug target. Despite over 100,000 recorded kinase inhibitors, only about 75 small-molecule kinase drugs have received FDA approval, underscoring the difficulty of developing kinase drugs. EGFit combines pre-trained large language models, with advanced machine learning techniques, including random forest, support vector machine, multilayer perceptrons, and logistic regression, to iteratively evaluate and refine generated compounds. Under limited data conditions, the framework efficiently explores a vast chemical space, producing biologically relevant and structurally diverse kinase inhibitors. Experimental validation on four kinases (EGFR, MET, PIM1, and CDK5) demonstrates significant improvements in compound similarity to known inhibitors while maintaining compliance with drug-likeness criteria. The iterative feedback mechanism further ensures chemical novelty and biological significance, showcasing the potential of EGFit to optimize compound generation for kinase-specific applications. This framework offers a scalable and effective solution to the challenges of kinase drug discovery, accelerating the development of novel therapeutics and paving the way for broader applications in future studies.

This paper investigates methods for estimating interaction forces during the dynamic process of upper limb elevation. By collecting data from two modalities- electromyographic (EMG) signals of the unilateral forearm and joint angles-along with synchronized interaction force data, a deep learning methodology merging convolutional neural network and long short-term memory network (CNN-LSTM) is adopted to generate a predictive model for characterizing dynamic interactive force, ultimately achieving the task of dynamic force estimation. The comparative analysis of estimation performance using two types of data, EMG signals and EMG-inertial measurement unit (IMU) signals, along with the performance comparison between the CNN-LSTM model and support vector regression (SVR) model for the dynamic force estimation task, demonstrates the advantages of multimodal data and the CNN-LSTM model in facilitating the estimation of dynamic interaction forces in the upper limb.

Traumatic brain injury (TBI) impairs sensorimotor functions, which affect static, dynamic, and reactive balance even in chronic stages. Varying levels of deficits in people with TBI (pwTBI) due to heterogeneous injury pose challenges on therapies. Since qualitative assessment-based conventional therapies are multifactorial, they may not precisely evaluate deficits or provide targeted therapy. However, robotic devices can precisely evaluate deficits and offer customized therapy progression based on deficits. Therefore, the study objective was to investigate the efficacy of a targeted robotic balance training (RBT) in pwTBI using biomechanical and functional outcomes. Data are presented for a small sample of pwTBI who received RBT (TBI-I) and for those who did not (TBI-C). After 10 sessions of training, TBI-I improved in biomechanical (static, dynamic, and reactive balance as well as limits of stability) and functional (community mobility and balance scale) outcomes. These results underscore the preliminary efficacy of RBT in improving balance and postural control in chronic TBI.Clinical Relevance - The data support the efficacy of RBT that can deliver targeted therapy for pwTBI.

Crawling Wave Sonoelastography (CWS) is a quantitative elastography technique that employs two mechanical actuators to generate an interference pattern within the tissue. Ultrasound imaging is then used to capture the resulting wave fields, and the shear wave speed (SWS) is computed to produce an elastography image. In previous studies, different time-frequency techniques have been employed to estimate the SWS, but some limitations, such as lateral artifacts and blurred SWS maps, were reported. In this paper, a novel approach based on the Fourier Synchrosqueezed Transform (FSST) is presented. To assert the veracity of the results, previous datasets in homogeneous and heterogeneous phantoms with vibration frequencies between 200 and 360 Hz have been used. The proposed metrics for comparison were SWS mean value and standard variation, coefficient of variation (CV), Bias, R₂₀₈₀, and, contrast-to-noise ratio (CNR). The new estimator demonstrates marginally superior performance in SWS mean value (at 340 Hz, inclusion: 5.13±0.01 m/s, background: 3.42±0.02 m/s) CV (at 320 Hz, inclusion: 0.11%, background: 0%) and CNR (at 320 Hz, 104.7 dB), and better performance in Bias (at 320 Hz, inclusion: 0.6%, background: 0.84%) and R₂₀₈₀ (at 320 Hz, 0.5 mm) in comparison with previous time-frequency approaches.Clinical relevance- This investigation presents a new Shear Wave Speed estimator for Crawling Waves Sonoelastography approach, which is able to quantify stiffness tissue with great accuracy showing the potential of real-time time application to allow the characterization of tissue elasticity.

Artificial intelligence (AI) has become indispensable in medical image analysis, with models such as convolutional neural networks (CNNs) and Transformer achieving remarkable success in diagnostic imaging. Despite their impressive performance, these models often lack interpretability, limiting their adoption in clinical workflows where understanding disease-specific features is critical for trust.In this study, we propose an explainability framework that enhances interpretability for multi-label disease classification in chest X-ray (CXR) diagnosis by utilizing the U-Net encoder-decoder architecture. The encoder and decoder outputs are concatenated to effectively capture hierarchical features for the classification of 14 observations in the MIMIC-CXR dataset. To further improve interpretability, we apply gradient-weighted class activation mapping (Grad-CAM) across multiple layers, providing detailed insights into the refinement of hierarchical features and the emphasis on disease-specific regions throughout the network. This integration of U-Net with an explainable AI (XAI) framework enhances transparency in the diagnostic process, supporting more informed and trustworthy clinical decision making.Clinical relevance- This study underscores the importance of interpretability in AI-based radiology. By providing clear Grad-CAM visualizations of disease-specific features, clinicians can more confidently validate model predictions and incorporate these insights into their decision-making processes. Through enhanced transparency, our approach not only improves diagnostic performance, but also fosters greater trust in AI tools, paving the way for these models to serve as robust, clinician-friendly decision support systems in routine radiological workflows.