IEEE Transactions on Biomedical Engineering最新文献

Objective: Hydrocephalus is a severe disorder characterized by pathological enlargement of the brain ventricles, leading to compression and deformation of brain tissue. The pathophysiological mechanisms underlying some subtypes of hydrocephalus remain poorly understood. Normal pressure hydrocephalus (NPH) continues to be a clinically significant and unresolved issue in elderly care. This study proposes a novel approach to investigate this pathology using mathematical modeling techniques.

Methods: Using stationary multicomponent poroelasticity equations with physiological boundary conditions, we examine the interactions between brain parenchyma and fluid (including arterial, capillary, venous blood, and interstitial fluid). The model describes these interactions through four specific"interaction coefficients".

Results: Analysis revealed how interaction coefficients govern ventricular wall pressure and displacement. The derived analytical approximations of these relationships provide a foundation for hypothesizing the mechanisms of NPH initiation and development.

Conclusions: This hypothesis suggests that NPH results from compromised vascular autoregulation, which under normal conditions maintains stable ventricular volume.

Significance: This work identifies specific interaction parameters that govern transitions between physiological stability and pathological ventricular dilation. These results may assist in refining diagnostic criteria and in developing therapeutic strategies aimed at correcting the condition and treating NPH.

Background: The increasing demand for personalized healthcare solutions highlights the limitations of one-size-fits-all treatment strategies. Digital twin (DT) technology, which enables real-time virtual replicas of physical systems, offers a promising approach to advance personalized medicine through continuous monitoring, simulation, and prediction.

Methods: This study presents the foundational phase of a machine-learning-driven biosensor DT designed to support personalized infertility treatment through integration with a Smart Health Monitoring System. The DT replicates the behavior of a field-effect transistor (FET)-based biosensor functionalized with 17$beta$-estradiol aptamers and trained on experimental data obtained from silicon nanonet BioFET prototypes.

Results: Seven supervised machine learning algorithms were evaluated to predict hormone concentration from electrical parameters ($V_{g}$, $I_{sd}$). The K-Nearest Neighbors (KNN) model achieved the highest predictive accuracy ($R^{2} = 0.99$, $text{CV}text{-}R^{2} = 0.98$, RMSE = 11.87 pg/mL) and demonstrated robust cross-device generalization under Leave-One-Biosensor-Out validation ($R^{2} = 0.59$). These results confirm the model's capability to capture nonlinear relationships and generalize across independently fabricated sensors.

Conclusion: The developed model constitutes a validated predictive core of a biosensor digital twin. At the current stage, the DT is limited to predictive modeling and does not yet implement real-time synchronization or closed-loop feedback, which are planned in future work.

Significance: This study establishes a practical framework for data-driven digital twins of biosensors and demonstrates their potential for integration into smart health monitoring systems supporting personalized infertility care. The proposed approach provides a foundation for real-time, adaptive, and clinically relevant biosensor twins in precision medicine.

Accurate control, monitoring of acoustic power, and flexible waveform generation are essential for safe and reproducible transcranial focused ultrasound (tFUS) neuromodulation, which is not comprehensively supported by existing benchtop platforms. This work presents a low-complexity and programmable tFUS stimulation system. The system integrates a direct digital synthesis module, a DAC-controlled programmable DC-DC supply, a full-bridge driver, and an impedance matching network to achieve flexible waveform generation and efficient transducer excitation. Acoustic power is monitored using a nonuniform discrete Fourier transform method at the driving frequency. Direct amplitude regulation enables highly linear pressure control up to 4.85 MPa. Impedance matching raised the maximum peak-to-peak excitation voltage from 86 V to 206 V (×2.4) and reduced total harmonic distortion (THD) by 19.19 dB. The power monitor achieves <5% error for outputs above 3 W. In vivo safety was evaluated in mice using both acute (single 20-min exposure) and chronic (21-day, 20-min/day) protocols. Four stimulation groups at $mathrm{I_{SPPA}}$ = 40 W/cm² with duty cycles from 1.8% to 14.4% ($mathrm{I_{SPTA}}$ = 0.72-5.76 W/cm²) were compared with sham and controls. Behavioral outcomes and histological analysis revealed no abnormalities under these conditions. The $mathrm{I_{SPTA}}$ range corresponds to one to eight times the FDA guideline limit, thereby encompassing and extending typical safety margins in neuromodulation studies. These results demonstrate the feasibility of the proposed platform, with validation at both the circuit level and through preclinical safety studies.

Objective: Near-infrared fluorescence (NIRF) imaging systems often require multiple operators and lack standardized acquisition constraints, limiting reproducibility across users and sites. We present a single-operator, wearable Cancer Vision Goggles (CVG) platform for hands-free NIRF guidance while preserving a radiometrically faithful reference stream for quantitative analysis.

Methods: The head-mounted binocular CVG integrates synchronized visible/NIR cameras, real-time co-registration to an optical see-through display, green alignment lasers converging at a preset 50-cm distance to standardize geometry, and a posture-dependent laser safety interlock. A Bluetooth foot pedal and graphical user interface enable hands-free paired laser-on/laser-off snapshot capture. Performance was characterized using USAF targets and ICG Intralipid phantoms, and validated in vivo in a 4T1 murine tumor model using LS301-HSA and in the operating room by ex vivo imaging of head and neck cancer specimens from patients injected with Pegsitacianine.

Results: At 50 cm, spatial resolution was 281 μm; the excitation field exhibited peak irradiance of 26.4 ± 2.2 mW/cm2 with 73.8 ± 3.2 mm FWMH. Phantom studies achieved signal-to-background ratio (SBR) >1 at 100 pM (raw Bayer) and 300 pM (Y-luminance), with linear behavior at low-to-moderate concentrations. Murine tumors and human specimens demonstrated consistent tumor-associated NIRF localization. Real-time dynamic thresholding enhanced tumor-background delineation and on-display reporting of fluorescence metrics for data-driven guidance.

Conclusion: This CVG platform offers a wearable, single-operator NIRF imaging system that combines distance-enforced acquisition, integrated safety, a hands-free workflow, and dual-spectral imaging, preserving a radiometrically linear reference for quantitative analysis.

Significance: Standardized acquisition supports reproducible fluorescence imaging and analyzable translational datasets.

Spreading depolarizations (SDs) are key drivers of secondary brain injury, yet existing bedside monitoring methods that use electrocorticography (ECoG) analyze electrodes and frequency bands separately, thereby obscuring the joint spatiotemporal patterns of SDs. Therefore, this paper introduces a multi-scale signal-image fusion framework that for the first time enables SDmonitoring as a joint multi-modal multi-band spectral image-based analysis. The ECoG signal is converted into a persistent spectral de-weighted spectrogram (PSd-Spec) and joined with multi-band features, through Transformer-CNN jointly empowered blocks: Multi-Channel and Band Transformer Block (MCBTB) and Multi-Scale Adaptive Fusion (MSAF). The network extracts short- and long-range dynamics in a multi-scale time window, while an attention-driven channel weighting module adaptively models the spatial propagation of the electrode strips. On 500h of neuro-ICU recordings, the proposed approach achieved 92.6% accuracy, 84.9% sensitivity. Relative to the best single-modality base line, performance improved by at least 18%, and SD onset was identified on average of 8 min before expert observation. The results suggest that multi-scale fusion of spectral images with ECoG signals yields a clinically actionable early-warning approach and extends quantitative imaging methods to intracranial electrophysiology.

Objective: Despite recent advances in wearable technology and its use in quantifying movement, there is still a need for reliable methods of quantifying complex walking tasks beyond steady-state gait (SSG). The purpose of this study is to evaluate an inertial sensor-based processing pipeline that uses a deep learning method for event detection during stride segmentation and established methods for trajectory reconstruction and gait parameter calculation of simple and complex walking tasks.

Methods: We propose a method that utilizes a Temporal Convolutional Network (TCN) during stride segmentation and pre-established methods for trajectory reconstruction and parameter extraction to accurately quantify spatiotemporal parameters of steady state gait (SSG), turn, gait initiation (GI), and termination (GT) strides. The results from this pipeline were evaluated against a pressure walkway as the reference system.

Results: Overall, our method was able to derive temporal and spatial parameters with small mean errors (≤ 1 ms and ≤ 2.3 cm, respectively) and strong correlation (r ≥ 0.96) with the pressure walkway for SSG strides. Turn, GI, and GT strides temporal and spatial parameters had similar performance (≤ 7 ms and ≤ 2.9 cm, respectively) and strong correlation (r ≥ 0.95) with the walkway.

Conclusion: This study demonstrated that IMU derived gait metrics using TCN model event detection for stride segmentation and Gaitmap functions for stride reconstruction and parameter calculation can be used to quantify gait during both simple and complex walking tasks.

Significance: The proposed method provides a reliable way to quantify complex walking tasks, allowing for a more complete understanding of mobility in home and community environments.

Objective: Intravitreal injection (IVI), a critical treatment for ophthalmic diseases requiring precise scleral puncture, is traditionally performed manually, demanding high skill, limiting efficiency, and lacking standardization. This study aims to develop and evaluate an automated IVI (A-IVI) robotic system to improve accuracy, efficiency, and safety.

Methods: The proposed system comprises a custom-designed compact injection robot, a structured-light camera, and a general robotic arm. Based on the optimal injection pose determined from point clouds acquired by the vision sensor, the injection robot performs IVI. Before needle insertion, the eyeball is pre-fixed using a compliance-controlled fixture to enhance safety and comfort. A motion-planning strategy coordinates the degrees of freedom (DOFs) of the remote-center-of-motion (RCM) mechanism and robotic arm, enabling safe and flexible needle puncture.

Results: Experiments were conducted on eye phantoms and ex-vivo porcine eyes. Mean execution times were 38.3 s and 40.8 s, puncture accuracy was 3.79±0.31 mm and 3.68±0.83 mm, and compliant interaction forces ranged from 0.25-1.15 N and 0.18-0.98 N, respectively, all within the clinically acceptable range.

Conclusion: The proposed robotic system achieves clinically acceptable accuracy and safe interaction forces while reducing variability and standardizing the IVI procedure.

Significance: This is the first application of structured-light-based measurement to IVI, enabling automation with precision and safety. The system demonstrates potential to improve efficiency, reduce surgeon workload, and establish a standardized approach to IVI in clinical practice.

Objective: Reliable identification of fibrotic regions is essential for targeted catheter ablation therapy, as current imaging modalities such as cardiac magnetic resonance imaging face technical and clinical limitations, particularly in resolution and compatibility with implanted devices. This work presents the quantitative assessment of optical coherence tomography (OCT) images to classify myocardium into fibro-elastic versus normal.

Methods: We acquired ultrahigh resolution OCT images from a sheep model with chronic myocardial infarction and performed pixelwise depth-resolved analysis to generate attenuation coefficient maps. In addition, we extracted radiomic features from three dimensional subvolumes to train a XGBoost classifier and validated our results against histological ground truth using Masson's trichrome staining histology to assess diagnostic accuracy.

Results: Attenuation and prediction probabilities effectively highlighted fibro-elastic regions. Widefield en face representations offered fast three dimensional screening of cardiac fibrosis. The radiomics-based XGBoost classifier achieved an area under the curve of 0.97 for binary classification.

Conclusions: Combining ultrahigh resolution OCT with a straightforward attenuation coefficient and a robust radiomics pipeline for optical property extraction and high throughput radiomic feature analysis enables label-free assessment of fibrotic microstructures in the myocardium.

Significance: The proposed quantitative framework enhances the detection and characterization of fibrotic myocardial tissue, offering potential for improved diagnostic precision and clinical integration of OCT in cardiology workflows towards data-driven catheter therapy guidance.

To develop and evaluate machine learning (ML) models that infer preoperative cognitive function from intraoperative electroencephalography (EEG). This was a retrospective ML study that used a training dataset derived from the MINDDS study (306 patients, USA), and an external testing dataset from the Electroencephalographic Biomarker to Predict Acute Post-Operatory Cognitive Dysfunction study (92 patients, Chile). Both contained patients older than 60 years undergoing either cardiac (training dataset) or non-cardiac (testing dataset) surgery under general anesthesia. Preoperative cognitive function was assessed using the Montreal Cognitive Assessment (MoCA) in both cohorts. Four types of ML models were used: logistic regression with L2 penalty, random forest, gradient boosting tree, and extreme gradient boosting. Models were evaluated in terms of weighted root mean square error (WRMSE) and monotonic correlations towards actual MoCA scores (Spearman's rho). A logistic regression model with L2 regularization performed best in the training dataset (WRMSE 2.82 [2.60 - 3.03 95%CI], Spearman's rho 0.18 [0.06 - 0.29], p 0.0015). This performance mostly generalized to the test dataset (WRMSE 2.72 [2.51 - 2.94], Spearman's rho 0.14 [-0.05 - 0.31], p 0.18). This study shows that ML models trained on intraoperative EEG can effectively infer preoperative cognitive function in older patients, with generalizability across distinct populations and relatively low error (<3 MoCA points). However, the correlations were weak, indicating limited ability to capture consistent monotonic relationships. Incorporating this approach into perioperative care could enable early detection and mitigation of neurocognitive disorders, improving surgical outcomes through tailored interventions. Further refinement and validation are required before clinical implementation.

Most traditional myoelectric pattern recognition (MPR) systems are limited to recognizing a fixed set of gesture classes and are prone to performance degradation when exposed to unknown gestures. This study proposes a robust MPR framework that simultaneously enhances intra-class compactness and improves open-set rejection performance. Time-domain features of high-density surface electromyography (HD-sEMG) signals are first decomposed into pattern-specific and pattern-variant components, preserving essential muscle activations and reducing intra class variability. A unified model is then constructed by integrating dissimilarity metric learning with classification, enabling simultaneous estimation of an anomaly score and class label for the input gesture. For each known gesture, a pattern-specific decision boundary is defined based on the maximum anomaly score. This allows accurate classification of known gestures and effective rejection of unknown ones. The proposed method is evaluated on a self-collected dataset containing 17 gestures and a public benchmark dataset containing 65 gestures. In intra-session experiments on both datasets, it achieves over 99% classification accuracy for known gestures and more than 98% rejection accuracy for unknown gestures. Under challenging inter-session conditions, it still maintains over 77% open-set recognition accuracy, substantially outperforming existing open-set MPR methods. These results demonstrate the effectiveness of combining muscle synergy decomposition with dissimilarity metric learning to improve the robustness of myoelectric interfaces.