IEEE Transactions on Biomedical Engineering最新文献

Objective: Frequency selection is a crucial step for calibration-based magnetic particle imaging (MPI) reconstruction, enabling improvement in computational efficiency and noise suppression. Current methods combine signal-to-noise ratio (SNR) feature with a selection threshold. However, the selection threshold determination is experience-dependent, and the utilization of the system matrix (SM) and the imaging phantom signal is insufficient.

Method: To suppress these issues, an adaptive and robust frequency selection framework (AR-FSF) is proposed, including three modules: (i) Velocity-corrected feature calculation, which limits feature calculation to the calibration points with high field-free-region velocity, (ii) Adaptive threshold calculation, which adaptively calculates the noise level using the feature spectrum, (iii) Forward-backward selection, which selects high-SNR frequency components for both SM and imaging phantom for reconstruction.

Results: Signal experiments validate the effectiveness and the robustness of the introduced modules respectively. Reconstruction experiments further validate that the AR-FSF method can provide a simple and robust frequency selection process for reconstruction. In experiments using in-house data, the AR-FSF method provides suitable frequency components for fast and high-quality imaging, requiring a minimum reconstruction time of 4.5% compare to current methods.

Conclusion: The proposed AR-FSF method effectively simplifies the frequency selection process, enabling adaptive selection of frequency component for different phantoms, thereby achieving fast and high-quality reconstruction.

Significance: The AR-FSF method simplifies the frequency component selection process and can be widely applied in calibration-based MPI reconstruction, laying a methodological foundation for future biomedical applications.

Objective: This study aimed to develop a seizure detection algorithm using surface electromyography (sEMG) and accelerometry (ACC) signals recorded with miniaturized wearable sensors.

Methods: Continuous sEMG-ACC signals were acquired from patients wearing eight sensors positioned bilaterally on the upper trapezius, anterior deltoid, biceps brachii, and tibialis anterior muscles. We trained an extreme gradient boosting classifier to identify seizure epochs using setups with eight, two, and one sensor(s). Performance was evaluated via patient-wise nested cross-validation, and specificity was further assessed on an independent patient cohort without seizures.

Results: Eleven generalized tonic-clonic seizures (GTCS) and focal-to-bilateral tonic-clonic seizures (FBTCS) were recorded from nine patients over 1359.6 h. The best results were obtained with a dual-sensor setup combining data from the right biceps brachii and the left tibialis anterior, achieving 100% sensitivity, 0.12 FAR/24h, and median detection latency of 22 s. On 1744.18 h of data from 19 patients without seizures, FAR/24h was 0.06.

Conclusion: The developed algorithm effectively detected GTCS and FBTCS in an epilepsy monitoring unit, even with a reduced number of sensors.

Significance: This approach could enable timely interventions in outpatient settings, potentially improving safety and independence for people with epilepsy.

Objective: The development of brain-computer interface (BCI) technology has enabled animals to execute movements in accordance with human intent. The rat robot represents a novel robotic system based on BCI technology. However, due to limitations in electrode fabrication techniques and the use of simplistic control strategies, current rat robots are restricted to limited movement patterns, which hinder their applicability in real-world scenarios. To address these challenges, we have developed a portable wireless neural stimulator and a novel 3D integrated stimulating electrode. By refining the locomotion control strategy, we aim to achieve complex, high-degree-of-freedom movement in rat robot systems.

Methods: 3D integrated electrodes were implanted into the rats' head, with no reward-based training required. By utilizing a wearable wireless stimulation backpack to connect the electrodes and deliver electrical stimulation to multiple brain regions, thereby enabling the rat to perform forward movement, turning, and stopping behaviors.

Results: The experimental results demonstrate that under optimized stimulation parameters, the forward speed of the rat robot can be controlled to achieve 31.06 ± 1.21 m/min, the turning angle can reach up to 150 ± 1.22°, and the stopping duration can be flexibly adjusted. Furthermore, we presented a practical scenario in which the rat robot successfully executed a predefined navigation task in a real-world environment, thereby validating its high degree of movement flexibility and control precision.

Conclusion: This study achieved high-degree-of-freedom motion control of rat robots without the need for reward-based training, which was previously unattainable.

Significance: This research establishes a crucial foundation and provides valuable technical references for the application of animal robots in fields such as information reconnaissance and wreckage search and rescue operations.

A novel 3D-printed microwave probe operating in the 25-45 GHz frequency range is designed and fabricated for early skin tumor detection using signal processing. Due to the highly lossy nature of the skin, electromagnetic wave penetration is difficult. To overcome this limitation, a multi-section probe design was developed to enhance wave penetration into the skin layer. This design effectively mitigates the effects of high-loss tangents in tissues and compensates for the small size of tumors, aiding in early detection. The probe's performance is validated through simulations and experimental measurements, showing excellent agreement. For imaging evaluation, a phantom model composed of pork skin, measuring 30 mm × 30 mm with a skin thickness of 4 mm, is utilized. A total of 215 scanning points were analyzed, and time-domain reflection waves were extracted, demonstrating the probe's ability to detect variations in tissue properties accurately. These signals were then processed using an entropy-based method. The reconstructed images across various scenarios highlight the effectiveness of the proposed probe in achieving high-resolution microwave imaging, indicating its strong potential for non-invasive, early-stage tumor detection.

Restoring stiffness perception in prosthetic users through non-invasive methods remains a major challenge in haptic feedback research. This study evaluates a wearable vibrotactile stimulation system that conveys object stiffness information through two encoding strategies: Proposed Spatiotemporal Encoding and Circular Encoding, applied to two anatomical locations: upper-arm and forearm. Ten healthy participants completed structured trials of stiffness-discrimination involving vibrotactile cues corresponding to four stiffness categories. The results showed significantly higher classification accuracy (CA) and information transfer (IT) with the Proposed encoding strategy at both sites. The upper-arm-proposed configuration achieved peak performance (CA: 97.75%, IT: 1.84 bit/s), whereas the forearm-circular strategy yielded the lowest (CA: 73.62%, IT: 0.86 bit/s). NASA-TLX scores indicated a significantly lower mental workload for the proposed strategy, with the upper-arm feedback location providing superior perceptual clarity. A supplementary evaluation with a transradial amputee further demonstrated that the proposed encoding strategy remained interpretable, achieving classification accuracies above 85%. The classification accuracies over different conditions followed the same pattern as observed in healthy participants. These findings validate the importance of encoding geometry and stimulation site in designing effective haptic interfaces and support the feasibility of spatially distributed, non-invasive vibrotactile feedback for enhancing tactile perception in prosthetic applications.

Objective: Precise mealtime insulin bolus (MIB) dosing is essential in type 1 diabetes (T1D) to minimize glucose excursions from carbohydrate intake. Traditional MIB formulas, based on glucose concentration at mealtime, are suboptimal and do not exploit real-time data from continuous glucose monitoring (CGM). Existing methods that incorporate CGM data often rely on empirical rules or are developed in-silico, limiting their applicability to real-world conditions. This work investigates a framework combining machine learning (ML) algorithms, digital twins (DTs) and real-world data, to improve the assessment, tuning, and development of MIB dosing algorithms.

Methods: We utilized ReplayBG, a DT for T1D, to: i) evaluate a published linear ML model (Noaro et al.), originally developed in-silico, on real-world data from 30 free-living subjects; ii) recalibrate this model to fit the real-world dataset; and iii) train and test nonlinear gradient-boosting models (XGBoost, LightGBM) developed entirely on real data through DT simulations.

Results: Progressing to DT-enhanced models, we observed improvements in glucose control. The recalibrated linear and nonlinear models increased time-in-range (up to 80.6% with LightGBM vs. 75.6% for Noaro et al.) and reduced time-above-range. Risk metrics reflecting hypo/hyperglycemia also improved.

Conclusions: These findings demonstrate that a DT-based framework grounded in real-world data supports both the refinement and development of bolus calculators, achieving performance gains beyond the original in-silico model.

Significance: DTs allow the use real-world data to develop, validate and extend the domain of validity of new MIB formulas, paving the way to practical applications of ML tailored solutions for T1D.

Objective: Latent diffusion models (LDM) could alleviate data scarcity challenges affecting machine learning development for medical imaging. However, medical LDM strategies typically rely on short-prompt text encoders, nonmedical LDMs, or large data volumes. These strategies can limit performance and scientific accessibility. We propose a novel LDM conditioning approach to address these limitations.

Methods: We propose Class-Conditioned Efficient Large Language model Adapter (CCELLA), a novel dual-head conditioning approach that simultaneously conditions the LDM U-Net with free-text clinical reports and radiology classification. We also propose a data-efficient LDM pipeline centered around CCELLA and a proposed joint loss function. We first evaluate our method on 3D prostate MRI against state-of-the-art. We then augment a downstream classifier model training dataset with synthetic images from our method.

Results: Our method achieves a 3D FID score of 0.025 on a size-limited 3D prostate MRI dataset, significantly outperforming a recent foundation model with FID 0.070. When training a classifier for prostate cancer prediction, adding synthetic images generated by our method during training improves classifier accuracy from 69% to 74% and outperforms classifiers trained on images generated by prior state-of-the-art. Classifier training solely on our method's synthetic images achieved comparable performance to real image training.

Conclusion: We show that our method improved both synthetic image quality and downstream classifier performance using limited data and minimal human annotation.

Significance: The proposed CCELLA-centric pipeline enables radiology report and class-conditioned LDM training for high-quality medical image synthesis given limited data volume and human data annotation, improving LDM performance and scientific accessibility.

Objective: Achieving effective and robust free-living PD severity assessment with wearable intelligence technologies requires a deep understanding of clinically relevant features, representative activities, and machine learning algorithms.

Methods: We designed a unified analytic framework (PDWearML) to optimise wearable ML approaches with simple daily activities for fast assessment of PD severity. It comprises annotation criteria, feature importance analysis, representative activity combination, and PD severity assessment. We conducted a 12-month study, developing a supervised PD wearable dataset containing 100 PD patients and 35 age-matched healthy controls using Huawei smartwatches and Shimmer. PD severity, assessed by trained physicians using the Hoehn and Yahr (H&Y) scale.

Results: The results reveal that through optimising multi-level feature extraction and combining three representative daily activities (WALK, ARISING-FROM-CHAIR, and DRINK), our smartwatch-based machine learning approach can assess PD severity in supervised settings within 2 minutes with an accuracy of up to 84.7%.

Significance: This work holds significant clinical value, offering a potential auxiliary tool for faster, more tailored interventions in PD healthcare. Code is availableat code ocean platform and https://github.com/wang-xulong/PDWearML.

Variable-length time series classification (VTSC) problems are prevalent in healthcare applications, such as heart rate monitoring and electrophysiological recordings, where sequence length varies among patients and events. VTSC is challenging as finite-context models such as Transformers require padding, truncation, or interpolation, leading to distortion in the input data, higher computational costs, and overfitting, while infinite-context models including recurrent neural networks struggle with overcompression and unstable gradients over long sequences. In this paper, we develop a novel VTSC framework based on Stochastic Sparse Sampling (SSS) for seizure onset zone (SOZ) localization, a critical VTSC problem requiring identification of seizure-inducing brain regions from variable-length electrophysiological time series. The proposed framework sparsely samples time series windows to compute local predictions, which are then aggregated and calibrated to form a global prediction. SSS provides post-hoc insights into local signal characteristics related to the SOZ, by visualizing temporally averaged local predictions throughout the signal. We evaluate our method on the Epilepsy intracranial electroencephalography (iEEG) Multicenter Dataset, a heterogeneous collection of iEEG recordings obtained from four independent medical centers. The proposed solution outperforms state-of-the-art (SOTA) baselines across most medical centers, and superior performance on all out-of-distribution (OOD) unseen medical centers.