IEEE Transactions on Biomedical Engineering最新文献

Objective: Von Willebrand Disease (VWD), the most common inherited bleeding disorder affecting 0.1% to 1% of the population, causes extensive mucocutaneous bleeding across various clinical contexts. Von Willebrand Factor (vWF) plays a critical role in hemostasis by mediating platelet adhesion under high shear stress conditions. We simulated platelet-vWF interactions to investigate adhesion dynamics in VWD using a multiscale modeling approach combining Dissipative Particle Dynamics (DPD) and Coarse-Grained Molecular Dynamics (CGMD).

Methods: Our platelet model provides high-resolution insights into adhesion mechanics by representing the platelet as a complex, deformable cellular entity comprising intricate membrane and subcellular components that capture the nuanced biomechanical behavior of platelets under flow conditions.

Results: Simulations under 30 dyne/cm2 shear stress revealed a threshold effect: platelets failed to complete flipping and adhesion below 40% vWF density, mirroring Type 1 VWD clinical manifestations. We identified asymmetric platelet flipping dynamics with longer lift-off periods compared to reattachment periods, and revealed a distinct temporal lag between the platelet's vertical positioning and minimum bond force/contact area configurations. In vitro experiments supported these computational findings, demonstrating a significant reduction in platelet residence duration and translocation distance as vWF surface densities decreased.

Conclusions: This work provides quantitative insights into the molecular mechanisms underlying platelet adhesion in VWD through our advanced CGMD model.

Significance: Our findings establish a comprehensive framework for understanding cellular adhesion processes in biofluid environments, potentially informing therapeutic strategies for bleeding disorders and thrombotic conditions.

Objective: Emerging technologies for electromagnetic interference (EMI) elimination have enabled radio frequency (RF) shielding-free magnetic resonance imaging (MRI), significantly reduced costs and increased accessibility. Existing methods often rely on multiple external sensors for EMI elimination, which can degrade with fewer sensors. Our goal is to develop a method that robustly eliminates EMI with fewer or no sensors.

Methods: We propose a method for multi-channel electromagnetic interference elimination in shielding-free MRI using null operations (MEENO). This approach fully exploits the inter-channel correlation across all RF receiving and EMI sensing channels. The method was comprehensively evaluated through simulation studies and human brain imaging.

Results: The MEENO approach effectively eliminates EMI artifacts, outperforming existing methods, particularly with a limited number of sensors. It shows superior performance in terms of signal-to-noise ratio and residual EMI levels.

Conclusion: We introduce a method for EMI elimination in multi-channel MRI using null operations, which fully leverages inter-channel correlation and surpasses existing approaches, especially with limited sensors.

Significance: This work offers a solution for EMI elimination with fewer or no external sensors, providing a more cost-effective and robust approach for shielding-free MRI.

Objective: Electrocardiograms (ECGs) play a crucial role in diagnosing heart conditions; however, the effectiveness of artificial intelligence (AI)-based ECG analysis is often hindered by the limited availability of labeled data. Self-supervised learning (SSL) can address this by leveraging large-scale unlabeled data. We introduce PhysioCLR (Physiology-aware Contrastive Learning Representation for ECG), a physiology-aware contrastive learning framework that incorporates domain-specific priors to enhance the generalizability and clinical relevance of ECG-based arrhythmia classification. Methods: During pretraining, PhysioCLR learns to bring together embeddings of samples that share similar clinically relevant features while pushing apart those that are dissimilar. Unlike existing methods, our method integrates ECG physiological similarity cues into contrastive learning, promoting the learning of clinically meaningful representations. Additionally, we introduce ECG-specific augmentations that preserve the ECG category post-augmentation and propose a hybrid loss function to further refine the quality of learned representations. Results: We evaluate PhysioCLR on two public ECG datasets, Chapman and Georgia, for multilabel ECG diagnoses, as well as a private ICU dataset labeled for binary classification. Across the Chapman, Georgia, and private cohorts, PhysioCLR boosts the mean AUROC by 12% relative to the strongest baseline, underscoring its robust cross-dataset generalization. Conclusion: By embedding physiological knowledge into contrastive learning, PhysioCLR enables the model to learn clinically meaningful and transferable ECG features.  Significance: PhysioCLR demonstrates the potential of physiology-informed SSL to offer a promising path toward more effective and label-efficient ECG diagnostics.

Multi-modality (MM) semi-supervised learning (SSL) based medical image segmentation has recently gained increasing attention for its ability to utilize MM data and reduce reliance on labeled images. However, current methods face several challenges: (1) Multiple networks assignment hinder scalability to scenarios with more than two modalities. (2) Focusing solely on modality-invariant representation while neglecting modality-specific features, leads to incomplete MM learning. (3) Leveraging unlabeled data with generative methods can be unreliable for SSL. To address these problems, we propose a novel unified all-in-one framework for MM-SSLmedical image segmentation. To address challenge (1), we propose a modality all-in-one segmentation network based on standard U-Net architecture that accepts data from all modalities, removing the limitation on modality count. To address challenge (2), we design two learnable plug-in banks, Modality-Level Modulation bank (MLMB) and Modality-Level Prototype (MLPB) bank, to capture both modality-invariant and modality-specific knowledge. These banks are updated using our proposed Modality Prototype Contrastive Learning (MPCL). Additionally, we design Modality Adaptive Weighting (MAW) to dynamically adjust learning weights for each modality, ensuring balanced MM learning as different modalities learn at different rates. Finally, to address challenge (3), we introduce a Dual Consistency (DC) strategy that enforces consistency at both the image and feature levels without relying on generative methods. We evaluate our method on a 2-to-4 modality segmentation task using three open-source datasets, and extensive experiments show that our method outperforms state-of-the-art approaches. The source code is publicly available at https://github.com/CYYukio/Double-Knowledge-Banking.

Artefacts compromise clinical decision-making in the use of medical time series. Pulsatile waveforms offer opportunities for accurate artefact detection, yet most approaches rely on supervised manners and overlook patient-level distribution shifts. To address these issues, we introduce GenClean, a generalised label-free framework for real-time artefact cleaning, implemented within the ICM+ clinical research monitoring software. Leveraging an in-house dataset of 180,000 ten-second arterial blood pressure (ABP) samples for training, we first investigate patient-level generalisation, demonstrating robust performance under both intra- and inter-patient distribution shifts. As an initial exploration beyond the development cohort, we further validate its effectiveness for ABP through site-level generalisation on the MIMIC-III database. We also provided an extension of our method to photoplethysmography (PPG), highlighting its potential applicability to diverse medical pulsatile signals. The real-time integration and these generalisation studies collectively demonstrate the practical utility of our framework in continuous physiological monitoring and represent a promising step towards improving the reliability of high-resolution medical time series analysis.

Endoscopic minimally invasive surgery relies on precise tissue video segmentation to avoid complications such as vascular bleeding or nerve injury. However, existing video segmentation methods often fail to maintain long-term robustness due to target loss and challenging conditions (e.g., occlusion, motion blur), limiting their applicability in prolonged surgical procedures. To address these limitations, we proposed the Unified Framework for Joint Pixel-Level Segmentation and Tracking (STF), it integrates a synergistic segmentation-guided tracking pipeline with an adaptive re-detection mechanism. First, a deep learning-based segmentation network precisely localizes the target tissue. A cost-efficient Hough Voting Network then tracks the segmented region, while a Bayesian refinement module improves compatibility between segmentation and tracking. If tracking reliability drops, an evaluation module triggers re-segmentation, ensuring continuous and stable long-term performance. Extensive experiments confirm that STF achieves superior accuracy and temporal consistency over segmentation networks in long-term surgical video segmentation, particularly under extreme conditions. This automated methodology significantly improves the robustness and re-detection capability for sustained tissue analysis, markedly reducing the dependency on manual intervention prevalent in many model-based tracking solutions.

Introduction: Premature Ventricular Contractions (PVCs) are common cardiac arrhythmias originating from the ventricles. Accurate detection remains challenging due to variability in electrocardiogram (ECG) waveforms caused by differences in lead placement, recording conditions, and population demographics.

Methods: We developed uPVC-Net, a universal deep learning model to detect PVCs from any single-lead ECG recordings. The model is developed on four independent ECG datasets comprising a total of 8.3 million beats collected from Holter monitors and a modern wearable ECG patch. uPVC-Net employs a custom architecture and a multi-source, multi-lead training strategy. For each experiment, one dataset is held out to evaluate out-of-distribution (OOD) generalization.

Results: uPVC-Net achieved an AUC between 97.8% and 99.1% on the held-out datasets. Notably, performance on wearable single-lead ECG data reached an AUC of 99.1%.

Conclusion: uPVC-Net exhibits strong generalization across diverse lead configurations and populations, highlighting its potential for robust, real-world clinical deployment.

Objective: Image distortions induced by the high refractive power of the eye's optical components challenge the accuracy of geometric information derived from intra-operative sensor data in ophthalmic surgery. Correcting these distortions is vital for advancing surgical assistance systems that rely on geometric scene comprehension. In this work, we focus on cornea induced distortions (CIDs) in surgical microscope images of the anterior eye.

Methods: We employ a convolutional neural network (CNN) with stereo fusion layers to predict distortion distribution maps (DDMs) to correct CIDs in stereo images. To enable supervised learning, we introduce CIDCAT, a synthetic surgical microscope dataset generated through a rendering pipeline using a digital eye model. We address the domain gap between the synthetic training data and the unlabeled target domain of real surgical images by employing an auxiliary task of semantic segmentation to regularizes the feature encoder.

Results: Our rectification model reduces the cornea induced pupil radius error from 8.56% to 0.72% and improves the structural similarity by over 9% for synthetic CIDCAT images. Our semantic segmentation driven domain regularization technique enables the translation to real surgical images.

Conclusion: The CIDCAT dataset enables the investigation of CIDs and the implementation of a CID rectification model. Our proposed CID rectification model demonstrate successful minimization of CIDs while preserving image integrity.

Significance: The work represents a significant advancement in research on computer-assistance and robotic solutions for ophthalmic surgery that rely on a distortion-free, three-dimensional understanding of the patient's eye.

Objective: Obstructive sleep apnea (OSA) is a prevalent yet underdiagnosed condition characterized by repetitive upper airway obstruction during sleep. Current gold standard diagnostic standards rely on polysomnography (PSG), which is resource-intensive. Since upper airway characteristics impact both OSA and speech production, speech processing has emerged as a promising alternative for OSA screening. However, prior work has focused primarily on acoustic features. This study aims to develop a speech-based screening and severity estimation pipeline for OSA using self-supervised learning (SSL) and multimodal acoustic features.

Methods: We proposed a novel fusion framework combining SSL-derived speech representations from pre-trained neural networks with traditional acoustic features and time-frequency representations of speech phase and magnitude. Elongated vowels recorded during wakefulness were used to screen for OSA at two apnea-hypopnea index (AHI) thresholds (10 and 30 events/hour) and to estimate AHI. Data were collected across three research sites, comprising participants of varied sex, race, and OSA severity.

Results: For OSA screening, the models achieved balanced accuracies of 0.79 (AHI $geq$10) and 0.74 (AHI $geq$30) in females, and 0.80 and 0.78 in males, respectively. AHI estimation yielded mean absolute errors of 12.0 events/hour (r = 0.63) in females and 14.7 events/hour (r = 0.52) in males.

Conclusion: Our results demonstrate the feasibility of using speech, especially vowel phonation during wakefulness, as a biomarker for OSA risk and severity estimation. The approach generalizes well across diverse demographic groups.

Significance: This study presents a significant step toward accessible, low-burden, and cost-effective OSA screening, with broad implications for scalable sleep health assessments.