Biomedical Physics & Engineering Express最新文献

Continuous and interpretable monitoring of masseter muscle activity is essential for the assessment of sleep bruxism (SB) and temporomandibular dysfunction (TMD). However, existing surface electromyography (sEMG) systems remain constrained by wired power supply, data-privacy concerns, and limited real-time specificity. To address these gaps, this study introduces a self-powered, edge-intelligent monitoring framework that combines poly(vinylidene fluoride) (PVDF)-based piezoelectric patches (BP-Patch) with a dual-branch lightweight neural network, the Depthwise Separable Convolutional Network with Efficient Channel Attention (DSC-AttNet). The network leverages depthwise separable convolution (DSC) to balance computational load and feature resolution, and incorporates an Efficient Channel Attention (ECA) module to enhance the discriminability between lateralised activations. After 8-bit quantisation, DSC-AttNet is deployed on an Arm Cortex-M4 microcontroller (MCU) while occupying only 80.7 KiB Flash and 72.8 KiB RAM, enabling real-time on-device inference across five physiological states (left/right bruxism, left/right chewing, and resting) with 94.75% classification accuracy and 63.6 ms average latency on data from 12 subjects. To support trustworthy AI-driven decision-making, Gradient-weighted Class Activation Mapping (Grad-CAM) and attention-based relevance analysis are employed to identify class-specific activation patterns across both time and frequency domains. These interpretable features further enable the derivation of clinically relevant indices such as nightly bruxism count, episode duration, and the Masseter Symmetry Index (MSI). By integrating bilateral self-powered sensing, resource-efficient edge inference, and quantitative interpretability within a fully on-device framework, this work lays the groundwork for long-term, home-based assessment and privacy-preserving intervention in masseter monitoring.

Leukodystrophies are a group of inherited disorders that predominantly and selectively affect the white matter of the central nervous system. Their overlapping clinical and imaging manifestations make a timely and accurate diagnosis challenging. In this study, brain MRI images from 115 patients with confirmed Leukodystrophy representing five major subtypes were analyzed. The imaging pipeline began with comprehensive pre-processing, which included tilt correction, noise reduction, skull stripping, brain segmentation, intensity normalization, and registration. This process ensured consistency throughout the dataset. Subsequently, two main classification strategies were investigated: (1) five traditional machine learning algorithms trained on four sets of handcrafted features extracted from the white matter and whole-brain regions, and (2) deep learning models using pre-trained convolutional neural networks fine-tuned on 3D MRI volumes. The CNN-based methods consistently outperformed traditional approaches, demonstrating a greater ability to learn complex hierarchical and spatial patterns. The InceptionV3 architecture achieved the highest performance on whole-brain images, with an accuracy of 93.41%, precision of 85.49%, recall of 83.95%, specificity of 95.77%, F1-score of 84.48%, and AUC of 89.86%. These findings indicate that machine learning-based approaches provide a reliable automated tool that can support neurologists in the differential diagnosis of Leukodystrophies, facilitating targeted confirmatory genetic testing and guiding patient management strategies.

Lung cancer remains one of the deadliest forms of cancer worldwide, making early and accurate pulmonary-nodule classification essential for improving patient prognosis. This study presents a robust ensemble-stacking framework that integrates Histogram of Oriented Gradients with advanced radiomic features to distinguish benign from malignant nodules. Experiments were conducted on the publicly available LIDC-IDRI dataset, which comprises of 1,018 thoracic computed tomography scans with expert-annotated nodules. Complementary feature sets capturing both local edge patterns and high-order texture and shape descriptors were extracted. On this feature set, Random Forest, Logistic Regression, and Support Vector Machine served as base learners. Through extensive hyperparameter tuning and class-balanced training, followed by 5-fold cross-validation, the proposed ensemble achieved an accuracy of 93.26%, a sensitivity of 90.76%, and an AUC-ROC of 97.96%, outperforming individual feature-only models and several recent state-of-the-art approaches. Furthermore, feature-importance analysis highlights the importance of morphological descriptors and the complementary value of gradient-based features. These results demonstrate that integrating different imaging biomarkers within an ensemble framework can significantly enhance diagnostic performance. Future work will extend this framework to multi-modal imaging and also to incorporate semi-supervised learning to reduce manual label dependence and improve the overall generalisation.

Pre-extracted lumen information of 3D vessel in medical images can effectively assist doctors in intraoperative navigation and postoperative evaluation, which has important clinical value. The main challenge faced by fully automatic 3D vessel segmentation comes from the imbalanced proportion of the vessels in medical image, which may lead to lost target. In this paper, a fully automatic 3D vessel segmentation method based on small-object-sensitive deep reinforcement learning, is presented. The region of target is firstly detected by the bounding box of a deep reinforcement learning (DRL) network, and then is segmented with a convolutional neural network (CNN). To better detect small vessel object, we have made three improvements to the existing DRL-based detection network: 1) A novel state with random receptive field expansion is applied to provide the agent with necessary information even if part of the target is lost. 2) A Recall-priority reward is presented to provide the most complete region for the next segmentation stage. 3) The dependency of vascular spatial positions between adjacent slices is utilized to correct the errors in detection stage, and the topological integrity of the obtained vascular structure is improved. The proposed method has been extensively validated on a challenging vessel dataset with 100 computed tomography angiography (CTA) scans. The segmentation accuracy of this method is Dice=93.75%, which outperforms the baseline and other automatic 3D vessel segmentation algorithms. This method has advantages in positioning accuracy, segmentation accuracy, and operational efficiency, and can be easily applied to clinical applications.

The recognition of the subject's emotional states is of great significance for achieving humanized services in many scenarios with human-computer interaction. Recently, identification of the emotional states based on electroencephalogram (EEG) has received increasing attention. However, due to the complexity of EEG signals, EEG-based emotion recognition is very challenging. In this research, a novel BrainEmoNet with learning-based framework is proposed to improve the emotion recognition accuracy from the perspective of the asymmetry of human brain functions. The BrainEmoNet consists of frequency-domain feature network (FFN), long-term dependent feature network (LDFN) and spatial characteristic analysis network (SCAN). The parallel FFN and LDFN are suggested to extract the frequency-domain and long-term dependent features of the information in each brain channel, respectively. Meanwhile, based on the working principle of the human brain, the SCAN with channel-spatial attention mechanism is proposed to focus on the high-value information channels with assigning adaptive weights and analyze the spatial characteristics of the frequency-domain and time-domain features. The feature analysis in the time-frequency-spatial perspective can fully explore the emotional information contained in EEG information. Experimental results on multi-modal DEAP dataset presents the competitive performances of the BrainEmoNet over the existing state-of-the-art models. In the subject-dependent experiments, the proposed model achieves identification accuracies of 86.77% and 82.14% in arousal and valence dimensions, respectively, compared to 75.53% and 72.83% in the subject-independent experiments. The proposed BrainEmoNet model in this research can be used as an auxiliary tool for the assessment or monitoring of emotions.

Dosimetric biomarkers, in terms of dosiomics features, play a crucial role in modeling radiotherapy and should be analyze d for their robustness and stability. This study aims to investigate how these dosiomics features will change over variations in treatment planning parameters. Different treatment plans were created by varying such parameters as field number, dose calculation algorithm, dose grid resolution, energy, monitor units, fraction, dose, field size, multileaf collimator, collimator angle, table angle, source-to-surface distance and source-to-axis distance, and wedge for a hypothetical tumor in the CIRS phantom CT scan. Dosiomics features were extracted with different segment sizes. The coefficient of variation (COV) was used to evaluate dosiomics feature changes with consider COV ≤ 5% as robust features. Our findings showed that many of the dosiomics features had significant variations due to changes in treatment parameters. First-order and gray-level co-occurrence matrix (GLCM) features were more stable (COV ≤ 5%) compared to others. Field and wedge changes had the most significant impact on features, while the dose calculation algorithm, dose, and MU changes had the lesser effects. Dosiomics features were vulnerable over changing treatment parameters and should always be reported. The GLCM features set was the most robust. Further studies are needed to identify robust dosiomics features for future biomarker discovery.

Hyperlipidemia detection involves invasive, time-consuming procedures requiring clinical laboratories and blood samples. Often asymptomatic in its early stages, hyperlipidemia significantly increases the risk of cardiovascular diseases. The objective of this study was to investigate whether hyperlipidemia produces detectable changes in pulse wave patterns and to develop a non-invasive, cost-effective diagnostic approach using deep learning techniques applied to finger pulse images. Pulse waves were recorded from 81 hyperlipidemia patients and 65 participants in the control group, with 700 single pulse wave cycles selected from each group. These waveforms were preprocessed and divided into training (70%), validation (15%), and testing (15%) subsets. Custom Convolutional Neural Network (CNN) architectures trained from scratch were developed and evaluated to identify the most effective classification model. After model selection, hyperparameter tuning was applied to enhance predictive performance. In parallel, pre-trained models such as Visual Geometry Group 16 (VGG16) were fine-tuned and optimized. The models were assessed using accuracy, precision, recall, and F1-score. The custom CNN models achieved the highest performance, with the top model reaching approximately 95%-96% for accuracy, precision, recall, and F1-score. The VGG16 models also performed well, with all metrics around 91%. Training and validation curves for both model types indicated strong learning capabilities with minimal overfitting or underfitting, showcasing their potential for generalization to unseen data. Deep learning models effectively differentiated pulse waves between individuals with hyperlipidemia and those in the control group, indicating that hyperlipidemia causes detectable changes in pulse wave patterns. This study could lead to the development of a reliable, efficient, and non-invasive device for hyperlipidemia screening.

The uncontrolled release of pharmaceuticals in traditional drug delivery systems has resulted in the development of innovative drug delivery methods based on nanotechnology and the use of tailored nanocarriers for cancer treatment. This study aimed to develop a targeted drug delivery system and photodynamic therapy (PDT) for enhanced therapeutic efficacy in lung cancer treatment. Upconversion nanoparticles (UCNPs) were synthesised via a Polyol route and surface-modified with polyethylene glycol (PEG) to improve biocompatibility. Further functionalization with folic acid (FA) facilitated targeted delivery to the human lung fibroblast cell line (MRC-5) (normal) and the human lung carcinoma cell line (A549) (lung cancer). The nanoparticles were loaded with paclitaxel (PTX), which inhibits microtubule polymerisation, forming UCNPs-FA-PTX complexes. Transmission Electron Microscopy (TEM) characterisation revealed well-dispersed nanoparticles with an average size of 22.5 ± 8.67 nm. Zeta potential analysis confirmed a shift from +24.5 mV for UCNPs to -14 mV for UCNPs-FA-PTX, indicating successful drug loading and surface modification. Dynamic Light Scattering (DLS) showed a larger particle size for drug-loaded UCNPs, with a mean diameter of 117 nm. Cell viability and apoptosis were evaluated using MTT and Flow cytometry assays. The UCNPs-FA-PTX complex demonstrated a significantly reduced A549 cell viability, with a half-maximal inhibitory concentration (IC 50) of 11.15 μg ml^-1at 72 h, compared to MRC-5 cells (IC 50 =22.8 μg ml^-1), and induced higher apoptosis in cancer cells. The study integrates PDT, using Tetraphenylporphyrin (TPP) as a dye to enhance treatment. Laser treatment (980 nm) enhanced these effects through a synergistic therapeutic approach. In contrast, UCNPs-FA and UCNPs exhibited minimal cytotoxicity, underscoring their biocompatibility.

Sparse-view low-dose computed tomography (LDCT) imaging poses difficulties in preserving image quality while reducing radiation exposure. Recent research has focused extensively on artificial intelligence (AI) to reduce artifacts in LDCT. This paper presents a unique integration based on a conditional generative adversarial network (CGAN) with metaheuristic optimization to improve the reconstruction of sparse-view computed tomography (CT) images. A Pix2Pix CGAN-based model was integrated with Particle Swarm Optimization (PSO), Differential Evolution (DE), and Cuckoo Search (CS) to improve essential hyperparameters, such as learning rate and beta values. The LDCT-P and LUNA16 datasets were used, producing seven levels of sparse-view CT images (10, 16, 32, 64, 128, 256, and 512 views) for assessment. The findings indicated a substantial improvement in image quality with an increase in the number of view projections. Pix2Pix + PSO demonstrated superior performance, with the Structural Similarity Index metric (SSIM) rising from 0.900 (10 views) to 0.972 (512 views) for abdominal CT and from 0.801 to 0.971 for lung CT, respectively. The results underscore the capability of the Pix2Pix model integrated with metaheuristic optimization to enhance sparse-view CT reconstruction. This method adeptly reconciles computing economy with image integrity, enabling improved LDCT imaging applications in clinical settings.

Nanosecond pulsed electric fields (nsPEFs) have emerged as a promising modality for cancer treatment by inducing targeted immune responses. Inin vitrostudies, commercial cuvettes with narrow 1-mm gaps are typically employed to deliver high-intensity electric fields to biological samples. However, the inherently high conductivity of the biological sample results in extremely low impedance-often only a few Ohms. Under kilovolt-level pulses, this low impedance can induce current surges of hundreds of amperes, posing risks to pulse generation equipment. This issue is further amplified in high cell-density environments. To overcome these challenges, a novel cuvette design featuring a pair of grid-patterned electrodes has been developed to enhance load impedance while preserving electric field uniformity. Numerical simulations confirm that the proposed structure improves impedance characteristics without compromising the homogeneity of the electric field. Experimental validation has been conducted using 3D-printed cuvettes based on the current-voltage measurement method, indicating a strong correlation with simulations. This proposed grid-patterned cuvette provides a reliable platform for nsPEF delivery inin vitrobiomedical research.