Biomedical Engineering Letters最新文献

This review article focuses on recent advancements and persistent challenges in artificial vision prostheses designed to restore sight for patients affected by retinal diseases. It comprehensively examines various approaches, including epiretinal, subretinal, and suprachoroidal implants, as well as optic nerve and visual cortex stimulation strategies. The critical role of the retina in visual perception is explored, emphasizing how retinal degeneration affects the transmission of visual information and how artificial devices aim to replicate this function. The review also discusses the technological complexities of artificial retina development, particularly challenges associated with enhancing resolution, minimizing the spread of electrical stimulation, and achieving reliable long-term device functionality within the biological environment. Practical clinical outcomes, such as surgical feasibility, device durability, and biocompatibility, are analyzed in light of these innovations. Furthermore, emerging trends are highlighted, including the adoption of flexible materials, photovoltaic structures, and 3D electrode architectures to improve the performance and longevity of implants. Ultimately, future advancements in artificial vision systems will depend on integrated approaches that combine cutting-edge engineering with a deep understanding of biological systems to achieve meaningful and lasting visual restoration.

China's healthcare infrastructure faces growing population pressure and resource gaps. This review explores how AI applications, regulatory frameworks, and commercialization pathways are reshaping China's healthcare delivery system and global innovation standards. China's AI healthcare market is expected to grow from $900 million in 2020 to $1.59 billion in 2023, and is expected to reach $18.88 billion by 2030, at a Compound Annual Growth Rate (CAGR) of 42.5%. The National Medical Products Administration (NMPA) expects to approve 59 Class III AI devices by 2023, compared with just nine in 2020. Key applications include the widespread use of AI technology in lesion identification; a telemedicine platform serving 13 million users; and AI drug development that shortens the development cycle from 4 to 18 months. Regulatory pillars include the Personal Information Protection Law, which requires explicit consent before processing health data, and NMPA guidelines, which require all AI medical software to undergo three types of review. China's unique combination of centralized health data, policy incentives, and rapid commercialization has created a globally competitive AI medical ecosystem. Continued development requires addressing issues such as algorithm transparency, cross-border data governance, and international regulatory coordination.

The function of our brain is the result of the balanced interplay between billions of neurons forming a network of enormous complexity. However, the neurons themselves are also immensely complex entities, with many specialized macromolecular structures orchestrating signal processing and propagation. The postsynaptic density is an elaborate network of interconnected proteins, a dynamic yet highly organized molecular assembly beneath the dendritic membrane, and plays a pivotal role in learning, memory formation, and the development of a number of cognitive disorders. In this review, we argue that with the recent blooming of AI-assisted computational tools in structural biology, we might be able to get closer to understanding the molecular-level mechanistic aspects of this machinery. Nevertheless, we have to use these methods with caution as they are not yet capable of solving all the questions that arise for such a complex macromolecular system. First, we focus on the unique features of the postsynaptic protein network, highlighting those that pose particular challenges for such a modeling task, and put these in the light of the currently available deep learning-based approaches. We highlight the aspects that need specific attention and the areas where future developments could facilitate the detailed description of neural function at the molecular level.

Recent advances in generative artificial intelligence (AI) have accelerated the development of foundation models-large-scale, pre-trained systems capable of learning across modalities and tasks with minimal supervision. In the radiology domain, where annotated data are limited and heterogeneous, generative AI plays a critical role not only in enabling self-supervised learning and synthetic data generation, but also in addressing core engineering challenges such as scalability, multimodal alignment, and data diversity. This review examines how generative models-ranging from VAEs to diffusion and autoregressive frameworks-serve as both the algorithmic and architectural backbone of medical foundation models. We explore hybrid designs that optimize sample quality, efficiency, and control, alongside representation learning techniques like masked autoencoding and contrastive learning. Further, we describe the design and training strategies of multimodal large language models (MLLMs), which integrate visual, textual, and structured clinical data for applications including report generation, segmentation, and clinical reasoning. Through case studies of models such as Med-CLIP, RetFound, M3D-LaMed, and Med-Gemini, we illustrate how generative AI enables scalable, adaptable, and privacy-conscious AI systems in medicine. Finally, we discuss ongoing challenges-hallucination, generalization, and regulatory constraints-and highlight future directions for engineering trustworthy and deployable medical AI infrastructures.

Image registration involves aligning multiple images within a common coordinate system to determine their geometric transformations. This study aims to improve diagnostic accuracy and efficiency by applying deep learning-based image registration between CT and MR images. Initially, the iterative closest point (ICP) technique was utilized to extract point clouds from CT and MR images and their corresponding segmentation masks. Through ICP-based alignment, the Dice Similarity Coefficient (DSC) for the segmentation mask (specifically, the femur head) improved from 0.29 to 0.91, and the Root Mean Square Error (RMSE) also decreased. However, to achieve more precise registration, a Cycle-GAN-based generative model was employed to synthesize CT (sCT) images from MR images, enabling registration to be performed on modality-unified images. The generated sCT images demonstrated high similarity to actual CT images, as indicated by a PSNR of 20.57 and an NCC of 0.93. Subsequently, registered between the MR images and sCT images yielded to a PSNR of 12.95 and an NCC of 0.62, indicating strong alignment with the CT images. This study addresses the inherent challenges of multi-modality image registration and highlights the effectiveness of utilizing unified synthetic images for improved registration performance. Future research will focus on enhancing data diversity and quality, as well as refining deep learning model architectures to further advance registration accuracy. These advancements are expected to contribute to the development of clinically applicable tools, utilizing improving the precision of medical image analysis and diagnosis.

Purpose: Research into the spinal biomechanics of 3D-printed porous titanium pedicle screws (3DPS) has not yet been undertaken. This study evaluates the structural performance of 3DPS under physiological loading conditions using finite element analysis (FEA) and analyzes the effects of varying porosity levels on their mechanical behavior.

Method: A validated FE model of the lumbar spine was used to simulate one-, two-, and three-level fusion scenarios with 3DPS and transforaminal lumbar interbody fusion (TLIF) cages. Physiological loads, including flexion, extension, lateral bending, and axial rotation, were applied. Peak von Mises stress (PVMS), stress distribution, and structural stability were assessed across the different porosity configurations (0%, 60%, 70%, and 80%).

Result: The PVMS value in the core increases as the porosity increases. the stress distribution of posterior fixations in a 3-level fusion. when the porosity of the porous layer was 80%, the stress was concentrated in the core. At 70% and 80% porosity, where the risk of structural instability exceeded safe thresholds under a conservative safety factor of 3. The 60% porosity demonstrated an optimal balance between mechanical stability and stress distribution.

Conclusion: 3DPS, particularly those with 60% porosity, offer promising potential for enhancing fixation stability. Further studies are needed to confirm their long-term clinical efficacy. The outcomes of this research offer a critical preliminary step for preclinical and clinical evaluations aimed at confirming the mechanical integrity of 3D-printed porous structures.

The Comprehensive in vitro Proarrhythmia Assay (CiPA) initiative positions in silico simulations as essential tools for cardiac safety assessment. While single-cell simulations reveal ionic perturbations, they under-represent tissue-scale conduction, electrotonic coupling, and spatial heterogeneity that shape organ-level arrhythmogenesis. Investigate whether a multiscale classifier that combines a single-cell biomarker (qNet) with an organ-level metric (simulated QT) improves Torsades de Pointes (TdP) risk stratification over either biomarker alone. Twenty-eight CiPA drugs were simulated at 1-4×Cmax. We derived Avg. qNet from single-cell simulations (2,000 IC50-h samples × 4 concentrations) and Avg. QT from 3D tissue simulations (median parameters). Ordinal Logistic Regression (OLR) models were evaluated under split-sample (12/16) and full-set (28) analyses. Avg. qNet outperformed Avg. QT. Adding Avg. QT to Avg. qNet provided no material gain across AUC, ordinal calibration, likelihood ratios (LR±), and error rates, with only a small improvement for identifying high-risk drugs in the full-set analysis. Within this framework and dataset, ECG-derived QT is insufficient as a standalone predictor of tissue-level arrhythmogenicity; Avg. qNet is a robust primary biomarker, and the multiscale (Avg. qNet + Avg. QT) model offers at most incremental benefit. Multiscale gains will likely require ECG features that capture conduction/dispersion and larger, more diverse cohorts.

Supplementary information: The online version contains supplementary material available at 10.1007/s13534-025-00510-7.

Microplastics have become ubiquitous in modern environments, entering the human body through multiple pathways, including air, water, and food. Recent evidence shows that microplastics penetrate deep into the human body and accumulate in tissues. Despite escalating exposure to microplastics and growing concerns about potential toxicity, strategies for microplastic clearance from the body have yet to be explored. This review summarizes current knowledge on exposure pathways, distribution, accumulation mechanisms, and health risks of microplastics and critically evaluates natural clearance mechanisms in human and their limitations. Further, we investigate potential biomedical strategies for microplastic clearance and detoxification and synthesize considerations for clinical translation.

Schizophrenia (SCZ) is a severe and persistent mental health condition that profoundly affects individuals, their families, and broader communities. With rising global incidence and symptoms overlapping with disorders like bipolar illness, many remain unaware of its presence in daily life. Early diagnosis enables timely intervention, improving treatment outcomes and symptom management. Traditional machine learning approaches for schizophrenia detection rely on feature extraction and selection before classification. Deep learning (DL), renowned for modeling complex hierarchical patterns, accelerates the development of precise and objective diagnostic tools. Therefore, this research proposed a novel hybrid deep-learning approach for diagnosing Schizophrenia at an early stage. In this study, we developed an innovative framework employing the Mutation-enhanced Archimedes Optimization (MAO) algorithm to improve EEG preprocessing and signal clarity. Spatial and temporal features from multi-channel EEG data are analyzed through a hybrid deep learning approach, which mainly combines a Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) network. The proposed framework integrated an MAO into the CNN-GRU-MAO model, which enhances the capability to detect schizophrenia. A dual-objective optimization technique bootup detection accuracy and noise reduction, enhancing the overall effectiveness of the model. The experimental results demonstrated excellent performance and outperformed traditional approaches in terms of accuracy, precision, recall, F1-score, and specificity 98.41%, 98.13%, 98.87%, 98.49%, and 97.78% respectively. The MAO technique also evaluates signal integrity, enhancing Signal-to-Noise Ratio (SNR) and Signal-to-Interference Ratio (SIR) while reducing artifact contamination. This study highlights the ability of the MAO method in EEG preprocessing for schizophrenia detection. Integrating a deep learning framework with innovative optimization methods offers a transformative mechanism for improving mental health diagnostics via neurophysiological signal analysis.

The accurate replication of cerebral hemodynamics is essential for advancing neuroimaging techniques and preclinical research. This study presents a novel multi-component dynamic optical phantom designed to model the complex blood flow dynamics of the mouse brain. The phantom incorporates a static base mimicking skull optical properties, a porous medium infused with a blood-mimicking solution to simulate microvascular perfusion, and a directed flow channel representing large vessels such as the sagittal sinus. The phantom structure was characterized using laser speckle contrast imaging (LSCI) to assess its ability to replicate in vivo-like blood flow patterns. The results demonstrate strong quantitative agreement between the phantom and transcranial LSCI measurements of mouse brain hemodynamics. Our key findings highlight the influence of tissue-mimicking perfusion structures and optical attenuation properties on the blood flow index, validating the phantom as a reproducible and physiologically relevant model. This optically tunable and dynamically controllable platform provides a robust tool for calibrating neuroimaging technologies, validating new optical diagnostic techniques, and investigating cerebral blood flow regulation in preclinical studies.