生物医学工程学杂志最新文献

Due to its irregular shape and varying contour, pancreas segmentation is a recognized challenge in medical image segmentation. Convolutional neural network (CNN) and Transformer-based networks perform well but have limitations: CNN have constrained receptive fields, and Transformer underutilize image features. This work proposes an improved pancreas segmentation method by combining CNN and Transformer. Point-wise separable convolution was introduced in a stage-wise encoder to extract more features with fewer parameters. A densely connected ensemble decoder enabled multi-scale feature fusion, addressing the structural constraints of skip connections. Consistency terms and contrastive loss were integrated into deep supervision to ensure model accuracy. Extensive experiments on the Changhai and National Institute of Health (NIH) pancreas datasets achieved the highest Dice similarity coefficient (DSC) values of 76.32% and 86.78%, with superiority in other metrics. Ablation studies validated each component's contributions to performance and parameter reduction. Results demonstrate that the proposed loss function smooths training and optimizes performance. Overall, the method outperforms other advanced methods, enhances pancreas segmentation performance, supports physician diagnosis, and provides a reliable reference for future research.

Deep learning method can be used to automatically analyze electrocardiogram (ECG) data and rapidly implement arrhythmia classification, which provides significant clinical value for the early screening of arrhythmias. How to select arrhythmia features effectively under limited abnormal sample supervision is an urgent issue to address. This paper proposed an arrhythmia classification algorithm based on an adaptive multi-feature fusion network. The algorithm extracted RR interval features from ECG signals, employed one-dimensional convolutional neural network (1D-CNN) to extract time-domain deep features, employed Mel frequency cepstral coefficients (MFCC) and two-dimensional convolutional neural network (2D-CNN) to extract frequency-domain deep features. The features were fused using adaptive weighting strategy for arrhythmia classification. The paper used the arrhythmia database jointly developed by the Massachusetts Institute of Technology and Beth Israel Hospital (MIT-BIH) and evaluated the algorithm under the inter-patient paradigm. Experimental results demonstrated that the proposed algorithm achieved an average precision of 75.2%, an average recall of 70.1% and an average F ₁-score of 71.3%, demonstrating high classification accuracy and being able to provide algorithmic support for arrhythmia classification in wearable devices.

Blood biochemical indicators are an important basis for the diagnosis and treatment by doctors. The performance of related instruments, the qualification of operators, the storage method and time of blood samples and other factors will affect the accuracy of test results. However, it is difficult to meet the clinical needs of rapid detection and early screening of diseases with currently available methods. Point-of-care testing (POCT) is a new diagnostic technology with the characteristics of instant, portability, accuracy and efficiency. Microfluidic chips can provide an ideal experimental reaction platform for POCT. This paper summarizes the existing detection methods for common biochemical indicators such as blood glucose, lactic acid, uric acid, dopamine and cholesterol, and focuses on the application status of POCT based on microfluidic technology in blood biochemistry. It also summarizes the advantages and challenges of existing methods and prospects for development. The purpose of this paper is to provide relevant basis for breaking through the technical barriers of microfluidic and POCT product development in China.

As a relatively novel technique for drug delivery, the needle-free injection technique is characterized by transporting the drug liquid to the designated subcutaneous position through a high-speed micro-jet. Although this technique has been applied in many fields, the research on its drug dispersion mechanism and injection performance is insufficient. The presented study aims to identify critical parameters during the injection process and describe their influence on the injection effect. The injection completion rate and performance of a needle-free injector under various operating conditions were compared based on mouse experiments. The results show that the nozzle diameter imposes a more significant influence on jet characteristics than other injection parameters. Moreover, the injection completion rate increases with the nozzle diameter. The nozzle diameters of 0.14 mm and 0.25 mm correspond to injection completion rates of 89.7% and 95.8%, respectively. Furthermore, by analyzing the rate of blood glucose change in the tested mice, it is found that insulin administration through the needle-free injection can achieve a drug effect duration longer than 120 min, which is better than that obtained using conventional needle-syringe technique. In summary, the obtained conclusions can provide an important reference for the optimal design and extending application of the air-powered needle-free injector.

Emotion classification and recognition is a crucial area in emotional computing. Physiological signals, such as electroencephalogram (EEG), provide an accurate reflection of emotions and are difficult to disguise. However, emotion recognition still faces challenges in single-modal signal feature extraction and multi-modal signal integration. This study collected EEG, electromyogram (EMG), and electrodermal activity (EDA) signals from participants under three emotional states: happiness, sadness, and fear. A feature-weighted fusion method was applied for integrating the signals, and both support vector machine (SVM) and extreme learning machine (ELM) were used for classification. The results showed that the classification accuracy was highest when the fusion weights were set to EEG 0.7, EMG 0.15, and EDA 0.15, achieving accuracy rates of 80.19% and 82.48% for SVM and ELM, respectively. These rates represented an improvement of 5.81% and 2.95% compared to using EEG alone. This study offers methodological support for emotion classification and recognition using multi-modal physiological signals.

Repeated transcranial magnetic stimulation (rTMS) is one of the commonly used brain stimulation techniques. In order to investigate the effects of rTMS on the excitability of different types of neurons, this study is conducted to investigate the effects of rTMS on the cognitive function of mice and the excitability of hippocampal glutaminergic neurons and gamma-aminobutyric neurons from the perspective of electrophysiology. In this study, mice were randomly divided into glutaminergic control group, glutaminergic magnetic stimulation group, gamma-aminobutyric acid energy control group, and gamma-aminobutyric acid magnetic stimulation group. The four groups of mice were injected with adeno-associated virus to label two types of neurons and were implanted optical fiber. The stimulation groups received 14 days of stimulation and the control groups received 14 days of pseudo-stimulation. The fluorescence intensity of calcium ions in mice was recorded by optical fiber system. Behavioral experiments were conducted to explore the changes of cognitive function in mice. The patch-clamp system was used to detect the changes of neuronal action potential characteristics. The results showed that rTMS significantly improved the cognitive function of mice, increased the amplitude of calcium fluorescence of glutamergic neurons and gamma-aminobutyric neurons in the hippocampus, and enhanced the action potential related indexes of glutamergic neurons and gamma-aminobutyric neurons. The results suggest that rTMS can improve the cognitive ability of mice by enhancing the excitability of hippocampal glutaminergic neurons and gamma-aminobutyric neurons.

The risk prediction of paroxysmal atrial fibrillation (PAF) is a challenge in the field of biomedical engineering. This study integrated the advantages of machine learning feature engineering and end-to-end modeling of deep learning to propose a PAF risk prediction method based on multimodal feature fusion. Additionally, the study utilized four different feature selection methods and Pearson correlation analysis to determine the optimal multimodal feature set, and employed random forest for PAF risk assessment. The proposed method achieved accuracy of (92.3 ± 2.1)% and F1 score of (91.6 ± 2.9)% in a public dataset. In a clinical dataset, it achieved accuracy of (91.4 ± 2.0)% and F1 score of (90.8 ± 2.4)%. The method demonstrates generalization across multi-center datasets and holds promising clinical application prospects.

Collagen contains abundant cell binding motifs, which are conducive to adhesion, migration, and differentiation, maintain cell vitality and promote cell proliferation. However, pure collagen hydrogel has some shortcomings such as poor mechanical properties, poor thermal stability and fast degradation. Numerous studies have shown that the properties of collagen can be improved by combining it with natural polysaccharides such as alginate, chitosan, hyaluronic acid and cellulose. In this paper, the research status and biological application fields of four kinds of composite hydrogels, including collagen-alginate composite hydrogels, collagen-chitosan hydrogels, collagen-hyaluronic acid hydrogels and collagen-cellulose hydrogels, were summarized. The common preparation methods of four kinds of composite hydrogels were introduced, and the future development direction of collagen-based composite hydrogels was prospected.

Deformable image registration plays a crucial role in medical image analysis. Despite various advanced registration models having been proposed, achieving accurate and efficient deformable registration remains challenging. Leveraging the recent outstanding performance of Mamba in computer vision, we introduced a novel model called MCRDP-Net. MCRDP-Net adapted a dual-stream network architecture that combined Mamba blocks and convolutional blocks to simultaneously extract global and local information from fixed and moving images. In the decoding stage, we employed a pyramid network structure to obtain high-resolution deformation fields, achieving efficient and precise registration. The effectiveness of MCRDP-Net was validated on public brain registration datasets, OASIS and IXI. Experimental results demonstrated significant advantages of MCRDP-Net in medical image registration, with DSC, HD95, and ASD reaching 0.815, 8.123, and 0.521 on the OASIS dataset and 0.773, 7.786, and 0.871 on the IXI dataset. In summary, MCRDP-Net demonstrates superior performance in deformable image registration, proving its potential in medical image analysis. It effectively enhances the accuracy and efficiency of registration, providing strong support for subsequent medical research and applications.

Olfactory bulb is a critical component in encoding and processing olfactory signals, characterized by its intricate neural projections and networks dedicated to this function. It has been found that descending neural projections from the olfactory cortex and other advanced brain regions can modulate the excitability of olfactory bulb output neurons in the olfactory bulb, either directly or indirectly, which can further influence olfactory discrimination, learning, and other abilities. In recent years, advancements in optogenetic technology have facilitated extensive application of neuron manipulation for studying neural circuits, thereby greatly accelerating research into olfactory mechanisms. This review summarizes the latest research progress on the regulatory effects of neural projections from the olfactory cortex, basal forebrain, raphe nucleus, and locus coeruleus on olfactory bulb function. Furthermore, the important role that photogenetic technology plays in olfactory mechanism research is evaluated. Finally, the existing problems and future development trends in current research are preliminarily proposed and explained. This review aims to provide new insights into the mechanisms underlying olfactory neural regulation as well as applications of optogenetic technology, which are crucial for advancing the research on olfactory mechanism and the application of optogenetic technology.