Bioengineering

12 pages, 505 KiB

Open AccessArticle

Assessment of Possibility of Using Ultrasound Imaging in Treatment of Stress Urinary Incontinence in Women—Preliminary Study

by Gabriela Kołodyńska, Maciej Zalewski, Aleksandra Piątek, Anna Mucha, Krystyna Rożek-Piechura and Waldemar Andrzejewski

Bioengineering 2025, 12(6), 633; https://doi.org/10.3390/bioengineering12060633 - 10 Jun 2025

Abstract

The number of people suffering from urinary incontinence increases every year. Along this trend, the knowledge of society increases regarding the various methods available for treating this ailment. Both patients and researchers are constantly looking for new treatments for urinary incontinence. One of [...] Read more.

The number of people suffering from urinary incontinence increases every year. Along this trend, the knowledge of society increases regarding the various methods available for treating this ailment. Both patients and researchers are constantly looking for new treatments for urinary incontinence. One of the new solutions is sonofeedback of the pelvic floor muscles, which may help to strengthen them and thus reduce the problem. The aim of this study was to evaluate the effectiveness of sonofeedback and transvaginal electrostimulation in increasing the bioelectrical activity of pelvic floor muscles in postmenopausal women with stress urinary incontinence. Sixty women with stress urinary incontinence were enrolled in the study. The patients were divided into two groups: A, where sonofeedback was used, and B, where electrostimulation of the pelvic floor muscles was performed with biofeedback training. In patients, the resting bioelectrical activity of the pelvic floor muscles was assessed using an electromyograph. The assessment of the resting bioelectrical activity of the pelvic floor muscles was performed before the therapy, after the 5th training, and after the therapy. It was observed that after the end of the therapy, the average bioelectrical potential increased by 1.1 µV compared with the baseline in group A. It can be suggested that the sonofeedback method is comparatively effective in reducing symptoms that are associated with urinary incontinence as an electrostimulation method with biofeedback training. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

2 pages, 122 KiB

Open AccessEditorial

Advances in Wearable Technologies for the In-Field Assessment of Biomechanical Risk

by Micaela Porta and Massimiliano Pau

Bioengineering 2025, 12(6), 632; https://doi.org/10.3390/bioengineering12060632 - 10 Jun 2025

Abstract

The exceptional improvements that have characterized the technology of wearable devices for biomedical applications in recent decades have made it possible for researchers and practitioners to provide advanced solutions for the assessment of biomechanical and physiological variables in the present day, exploiting miniaturized, [...] Read more.

The exceptional improvements that have characterized the technology of wearable devices for biomedical applications in recent decades have made it possible for researchers and practitioners to provide advanced solutions for the assessment of biomechanical and physiological variables in the present day, exploiting miniaturized, lightweight, and low-power-consumption devices at affordable costs [...] Full article

(This article belongs to the Special Issue Advances in Wearable Technologies for ”In-Field” Assessment of Biomechanical Risk)

25 pages, 887 KiB

Open AccessReview

Large Language Models in Healthcare and Medical Applications: A Review

by Subhankar Maity and Manob Jyoti Saikia

Bioengineering 2025, 12(6), 631; https://doi.org/10.3390/bioengineering12060631 - 10 Jun 2025

Abstract

This paper provides a systematic and in-depth examination of large language models (LLMs) in the healthcare domain, addressing their significant potential to transform medical practice through advanced natural language processing capabilities. Current implementations demonstrate LLMs’ promising applications across clinical decision support, medical education, [...] Read more.

This paper provides a systematic and in-depth examination of large language models (LLMs) in the healthcare domain, addressing their significant potential to transform medical practice through advanced natural language processing capabilities. Current implementations demonstrate LLMs’ promising applications across clinical decision support, medical education, diagnostics, and patient care, while highlighting critical challenges in privacy, ethical deployment, and factual accuracy that require resolution for responsible integration into healthcare systems. This paper provides a comprehensive understanding of the background of healthcare LLMs, the evolution and architectural foundation, and the multimodal capabilities. Key methodological aspects—such as domain-specific data acquisition, large-scale pre-training, supervised fine-tuning, prompt engineering, and in-context learning—are explored in the context of healthcare use cases. The paper highlights the trends and categorizes prominent application areas in medicine. Additionally, it critically examines the prevailing technical and social challenges of healthcare LLMs, including issues of model bias, interpretability, ethics, governance, fairness, equity, data privacy, and regulatory compliance. The survey concludes with an outlook on emerging research directions and strategic recommendations for the development and deployment of healthcare LLMs. Full article

(This article belongs to the Special Issue Transforming Healthcare with Large Language Models: Innovations, Challenges, and Future Directions)

► Show Figures

Figure 1

20 pages, 4196 KiB

Open AccessArticle

Active and Inactive Tuberculosis Classification Using Convolutional Neural Networks with MLP-Mixer

by Beanbonyka Rim, Hyeonung Jang, Hongchang Lee and Wangsu Jeon

Bioengineering 2025, 12(6), 630; https://doi.org/10.3390/bioengineering12060630 - 9 Jun 2025

Abstract

Early detection of tuberculosis plays a critical role in effective treatment management. Like active tuberculosis, early identification of inactive forms such as latent or healed tuberculosis is essential to prevent future reactivation. In this study, we developed a deep-learning-based binary classification model to [...] Read more.

Early detection of tuberculosis plays a critical role in effective treatment management. Like active tuberculosis, early identification of inactive forms such as latent or healed tuberculosis is essential to prevent future reactivation. In this study, we developed a deep-learning-based binary classification model to distinguish between active and inactive tuberculosis cases. Our model architecture incorporated an EfficientNet backbone with an MLP-Mixer classification head and was fine-tuned on a dataset annotated by Cheonan Soonchunhyang Hospital. To enhance predictive performance, we applied transfer learning using weights pre-trained on the JFT-300M dataset via the Noisy Student training method. Unlike conventional models, our approach achieved competitive results, with an accuracy of 96.3%, a sensitivity of 95.9%, and a specificity of 96.6% on the test set. These promising outcomes suggest that our model could serve as a valuable asset to support clinical decision-making and streamline early screening workflows for latent tuberculosis. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

18 pages, 6411 KiB

Open AccessArticle

LL-MAROCO: A Large Language Model-Assisted Robotic System for Oral and Craniomaxillofacial Osteotomy

by Lai Jiang, Liangjing Shao, Jinyang Wu, Xiaofeng Xu, Xinrong Chen and Shilei Zhang

Bioengineering 2025, 12(6), 629; https://doi.org/10.3390/bioengineering12060629 - 9 Jun 2025

Abstract

Oral and craniomaxillofacial bone deformities necessitate treatment through osteotomy. Robot-assisted osteotomy appears promising in oral and craniomaxillofacial surgery, but it lacks sufficient intelligence and comprehensive integration of navigation tracking with surgical planning. This study aims to develop an intelligent surgical robot, based on [...] Read more.

Oral and craniomaxillofacial bone deformities necessitate treatment through osteotomy. Robot-assisted osteotomy appears promising in oral and craniomaxillofacial surgery, but it lacks sufficient intelligence and comprehensive integration of navigation tracking with surgical planning. This study aims to develop an intelligent surgical robot, based on the large language model ChatGPT-4, to enable autonomous planning for oral and craniomaxillofacial osteotomies. An autonomous surgical planning system driven by ChatGPT-4 was developed. Surgical plans were autonomously generated based on expert-defined prompts and surgical objectives. A deep learning framework was employed to match navigation-generated visual data with textual planning outputs. The generated plans were subsequently converted into executable instructions for robotic surgery. System precision, execution accuracy, and usability were experimentally validated through common osteotomies. An anonymous Likert scale assessed operational efficiency. The proposed system achieved a trajectory planning accuracy of 0.24 mm and an average robotic execution accuracy of 1.46 mm. The completion rates for two representative procedures, Le Fort I osteotomy and genioplasty, were 87% and 92%, respectively. Survey results confirmed process feasibility. The integration of a large language model with surgical robot advances intelligent, precise, and safe oral and craniomaxillofacial osteotomy procedures. Full article

(This article belongs to the Special Issue Diagnostic Biomedical Image and Processing with Artificial Intelligence and Deep Learning)

► Show Figures

Figure 1

25 pages, 2109 KiB

Open AccessReview

Spiking Neural Networks for Multimodal Neuroimaging: A Comprehensive Review of Current Trends and the NeuCube Brain-Inspired Architecture

by Omar Garcia-Palencia, Justin Fernandez, Vickie Shim, Nicola Kirilov Kasabov, Alan Wang and the Alzheimer’s Disease Neuroimaging Initiative

Bioengineering 2025, 12(6), 628; https://doi.org/10.3390/bioengineering12060628 - 9 Jun 2025

Abstract

Artificial intelligence (AI) is revolutionising neuroimaging by enabling automated analysis, predictive analytics, and the discovery of biomarkers for neurological disorders. However, traditional artificial neural networks (ANNs) face challenges in processing spatiotemporal neuroimaging data due to their limited temporal memory and high computational demands. [...] Read more.

Artificial intelligence (AI) is revolutionising neuroimaging by enabling automated analysis, predictive analytics, and the discovery of biomarkers for neurological disorders. However, traditional artificial neural networks (ANNs) face challenges in processing spatiotemporal neuroimaging data due to their limited temporal memory and high computational demands. Spiking neural networks (SNNs), inspired by the brain’s biological processes, offer a promising alternative. SNNs use discrete spikes for event-driven communication, making them energy-efficient and well suited for the real-time processing of dynamic brain data. Among SNN architectures, NeuCube stands out as a powerful framework for analysing spatiotemporal neuroimaging data. It employs a 3D brain-like structure to model neural activity, enabling personalised modelling, disease classification, and biomarker discovery. This paper explores the advantages of SNNs and NeuCube for multimodal neuroimaging analysis, including their ability to handle complex spatiotemporal patterns, adapt to evolving data, and provide interpretable insights. We discuss applications in disease diagnosis, brain–computer interfaces, and predictive modelling, as well as challenges such as training complexity, data encoding, and hardware limitations. Finally, we highlight future directions, including hybrid ANN-SNN models, neuromorphic hardware, and personalised medicine. Our contributions in this work are as follows: (i) we give a comprehensive review of an SNN applied to neuroimaging analysis; (ii) we present current software and hardware platforms, which have been studied in neuroscience; (iii) we provide a detailed comparison of performance and timing of SNN software simulators with a curated ADNI and other datasets; (iv) we provide a roadmap to select a hardware/software platform based on specific cases; and (v) finally, we highlight a project where NeuCube has been successfully used in neuroscience. The paper concludes with discussions of challenges and future perspectives. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

16 pages, 2946 KiB

Open AccessArticle

Functionally Isolated Sarcoplasmic Reticulum in Cardiomyocytes: Experimental and Mathematical Models

by Diogo C. Soriano, Rosana A. Bassani and José W. M. Bassani

Bioengineering 2025, 12(6), 627; https://doi.org/10.3390/bioengineering12060627 - 9 Jun 2025

Abstract

The interaction among the various Ca²⁺ transporters complicates the assessment of isolated systems in an intact cell. This article proposes the functionally isolated SR model (FISRM), a hybrid (experimental and mathematical) approach to study Ca²⁺ cycling between the cytosol and the [...] Read more.

The interaction among the various Ca²⁺ transporters complicates the assessment of isolated systems in an intact cell. This article proposes the functionally isolated SR model (FISRM), a hybrid (experimental and mathematical) approach to study Ca²⁺ cycling between the cytosol and the sarcoplasmic reticulum (SR), the main source of Ca²⁺ for contraction in mammalian cardiomyocytes. In FISRM, the main transmembrane Ca²⁺ transport pathways are eliminated by using a Na⁺, Ca²⁺-free extracellular medium, and SR Ca²⁺ release is elicited by a train of brief caffeine pulses. Two compounds that exert opposite effects on the SR Ca²⁺ uptake were characterized by this approach in isolated rat ventricular cardiomyocytes. The experimental FISRM was simulated with a simple mathematical model of Ca²⁺ fluxes across the SR membrane, based on a previous model adapted to the present conditions. To a fair extent, the theoretical model could reproduce the experimental results, and confirm the main assumption of the experimental model: that the only relevant Ca²⁺ fluxes occur across the SR membrane. Thus, the FISRM seems to be a valuable framework to investigate the SR Ca²⁺ transport in intact cardiomyocytes under physiological and pathophysiological conditions, and to test therapeutic approaches targeting SR proteins. Full article

(This article belongs to the Special Issue Computational Models in Cardiovascular System)

► Show Figures

Figure 1

16 pages, 523 KiB

Open AccessArticle

Optimizing MRI Scheduling in High-Complexity Hospitals: A Digital Twin and Reinforcement Learning Approach

by Fabián Silva-Aravena, Jenny Morales, Manoj Jayabalan and Paula Sáez

Bioengineering 2025, 12(6), 626; https://doi.org/10.3390/bioengineering12060626 - 9 Jun 2025

Abstract

Magnetic Resonance Imaging (MRI) services in high-complexity hospitals often suffer from operational inefficiencies, including suboptimal MRI machine utilization, prolonged patient waiting times, and inequitable service delivery across clinical priority levels. Addressing these challenges requires intelligent scheduling strategies capable of dynamically managing patient waitlists [...] Read more.

Magnetic Resonance Imaging (MRI) services in high-complexity hospitals often suffer from operational inefficiencies, including suboptimal MRI machine utilization, prolonged patient waiting times, and inequitable service delivery across clinical priority levels. Addressing these challenges requires intelligent scheduling strategies capable of dynamically managing patient waitlists based on clinical urgency while optimizing resource allocation. In this study, we propose a novel framework that integrates a digital twin (DT) of the MRI operational environment with a reinforcement learning (RL) agent trained via Deep Q-Networks (DQN). The digital twin simulates realistic hospital dynamics using parameters extracted from a MRI publicly available dataset, modeling patient arrivals, examination durations, MRI machine reliability, and clinical priority stratifications. Our strategy learns policies that maximize MRI machine utilization, minimize average waiting times, and ensure fairness by prioritizing urgent cases in the patient waitlist. Our approach outperforms traditional baselines, achieving a 14.5% increase in MRI machine utilization, a 44.8% reduction in average patient waiting time, and substantial improvements in priority-weighted fairness compared to First-Come-First-Served (FCFS) and static priority heuristics. Our strategy is designed to support hospital deployment, offering scalability, adaptability to dynamic operational conditions, and seamless integration with existing healthcare information systems. By advancing the use of digital twins and reinforcement learning in healthcare operations, our work provides a promising pathway toward optimizing MRI services, improving patient satisfaction, and enhancing clinical outcomes in complex hospital environments. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

23 pages, 3223 KiB

Open AccessArticle

Colony Binary Classification Based on Persistent Homology Feature Extraction and Improved EfficientNet

by Zumin Wang, Ke Yang, Jie Tang, Jun Gao, Yuhao Zhang, Wei Xu and Chun-Ming Huang

Bioengineering 2025, 12(6), 625; https://doi.org/10.3390/bioengineering12060625 - 9 Jun 2025

Abstract

Classifying newly formed colonies is instrumental in uncovering sources of infection and enabling precision medicine, holding significant clinical value. However, due to the ambiguous features of early-stage colony images in culture dishes, conventional computer vision (CV) classification algorithms are often ineffective. To achieve [...] Read more.

Classifying newly formed colonies is instrumental in uncovering sources of infection and enabling precision medicine, holding significant clinical value. However, due to the ambiguous features of early-stage colony images in culture dishes, conventional computer vision (CV) classification algorithms are often ineffective. To achieve accurate and efficient colony classification, this paper proposes a high-precision method based on Persistent Homology (PH) and an improved EfficientNet. Specifically, (1) a PH feature extraction algorithm is applied to Candida albicans (CA) and Staphylococcus epidermidis (SE) colonies cultured for 18 h in Petri dishes to capture their topological information. (2) The Mobile Inverted Bottleneck Convolution (MBConv) module in EfficientNet is modified, enhancing the attention mechanism to better handle local small targets. (3) A novel self-attention mechanism named the Spatial and Contextual Transformer (SCoT), which is introduced to process information at multiple scales, increasing the resolution in orthogonal directions of the image and the aggregation capability of feature maps. The proposed approach achieves a high accuracy of 98.64%, a 10.29% improvement over the original classification model. The research findings indicate that this method can effectively classify colonies with high efficiency. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Graphical abstract

25 pages, 5547 KiB

Open AccessArticle

Enhanced Aerosol Containment Performance of a Negative Pressure Hood with an Aerodynamic Cap Design: Multi-Method Validation Using CFD, PAO Particles, and Microbial Testing

by Seungcheol Ko, Kisub Sung, Min Jae Oh, Yoonjic Kim, Min Ji Kim, Jung Woo Lee, Yoo Seok Park, Yong Hyun Kim, Ju Young Hong and Joon Sang Lee

Bioengineering 2025, 12(6), 624; https://doi.org/10.3390/bioengineering12060624 - 9 Jun 2025

Abstract

Healthcare providers performing aerosol-generating procedures (AGPs) face significant infection risks, emphasizing the critical need for effective aerosol containment systems. In this study, we developed and validated a negative pressure chamber enhanced with an innovative aerodynamic cap structure designed to optimize aerosol containment. Initially, [...] Read more.

Healthcare providers performing aerosol-generating procedures (AGPs) face significant infection risks, emphasizing the critical need for effective aerosol containment systems. In this study, we developed and validated a negative pressure chamber enhanced with an innovative aerodynamic cap structure designed to optimize aerosol containment. Initially, computational fluid dynamics (CFD) simulations were performed to evaluate multiple structural improvement ideas, including air curtains, bidirectional suction, and aerodynamic cap structures. Among these, the aerodynamic cap was selected due to its superior predicted containment performance, practical feasibility, and cost-effectiveness. The CFD analyses employed realistic transient boundary conditions, precise turbulence modeling using the shear stress transport (SST) k–ω model, and detailed droplet evaporation dynamics under realistic humidity conditions. A full-scale prototype incorporating the selected aerodynamic cap was fabricated and evaluated using physical polyalphaolefin (PAO) particle leakage tests and biological aerosol validation with aerosolized Bacillus subtilis. For the physical leakage tests, the chamber opening was divided into nine sections, and the aerosol dispersion was tested in three distinct directions: ceiling-directed, toward the suction hole, and opposite the suction hole. These tests demonstrated significantly stabilized airflow and substantial reductions in aerosol leakage, consistently maintaining containment levels below the critical threshold of 0.3%, especially under transient coughing conditions. The biological aerosol experiments, conducted in a simulated emergency department environment, involved aerosolizing bacteria continuously for one hour. The results confirmed the effectiveness of the aerodynamic cap structure in achieving at least a one millionth (10⁻⁶) reduction in the aerosolized bacterial leakage compared to the control conditions. These findings highlight the importance and effectiveness of advanced CFD modeling methodologies in accurately predicting aerosol dispersion and improving containment strategies. Although further studies assessing the structural durability, long-term operational ease, and effectiveness against pathogenic microorganisms are required, the aerodynamic cap structure presents a promising, clinically practical infection control solution for widespread implementation during aerosol-generating medical procedures. Full article

(This article belongs to the Special Issue Pathology–Therapeutics–Medicine of Vascular and Respiratory Diseases: Recent Progress Using CFD and AI)

► Show Figures

Figure 1

19 pages, 840 KiB

Open AccessArticle

A Dual-Feature Framework for Enhanced Diagnosis of Myeloproliferative Neoplasm Subtypes Using Artificial Intelligence

by Amna Bamaqa, N. S. Labeeb, Eman M. El-Gendy, Hani M. Ibrahim, Mohamed Farsi, Hossam Magdy Balaha, Mahmoud Badawy and Mostafa A. Elhosseini

Bioengineering 2025, 12(6), 623; https://doi.org/10.3390/bioengineering12060623 - 7 Jun 2025

Viewed by 188

Abstract

Myeloproliferative neoplasms, particularly the Philadelphia chromosome-negative (Ph-negative) subtypes such as essential thrombocythemia, polycythemia vera, and primary myelofibrosis, present diagnostic challenges due to overlapping morphological features and clinical heterogeneity. Traditional diagnostic approaches, including imaging and histopathological analysis, are often limited by interobserver variability, delayed [...] Read more.

Myeloproliferative neoplasms, particularly the Philadelphia chromosome-negative (Ph-negative) subtypes such as essential thrombocythemia, polycythemia vera, and primary myelofibrosis, present diagnostic challenges due to overlapping morphological features and clinical heterogeneity. Traditional diagnostic approaches, including imaging and histopathological analysis, are often limited by interobserver variability, delayed diagnosis, and subjective interpretations. To address these limitations, we propose a novel framework that integrates handcrafted and automatic feature extraction techniques for improved classification of Ph-negative myeloproliferative neoplasms. Handcrafted features capture interpretable morphological and textural characteristics. In contrast, automatic features utilize deep learning models to identify complex patterns in histopathological images. The extracted features were used to train machine learning models, with hyperparameter optimization performed using Optuna. Our framework achieved high performance across multiple metrics, including precision, recall, F1 score, accuracy, specificity, and weighted average. The concatenated probabilities, which combine both feature types, demonstrated the highest mean weighted average of 0.9969, surpassing the individual performances of handcrafted (0.9765) and embedded features (0.9686). Statistical analysis confirmed the robustness and reliability of the results. However, challenges remain in assuming normal distributions for certain feature types. This study highlights the potential of combining domain-specific knowledge with data-driven approaches to enhance diagnostic accuracy and support clinical decision-making. Full article

(This article belongs to the Special Issue Deciphering Medicine: The Role of Explainable Artificial Intelligence in Healthcare Innovations, 2nd Edition)

► Show Figures

Figure 1

30 pages, 4325 KiB

Open AccessArticle

Discovery of Novel Natural Inhibitors of H5N1 Neuraminidase Using Integrated Molecular Modeling and ADMET Prediction

by Afaf Zekri, Mebarka Ouassaf, Shafi Ullah Khan, Kannan R. R. Rengasamy and Bader Y. Alhatlani

Bioengineering 2025, 12(6), 622; https://doi.org/10.3390/bioengineering12060622 - 7 Jun 2025

Viewed by 219

Abstract

The avian influenza virus, particularly the highly pathogenic H5N1 subtype, represents a significant public health threat due to its interspecies transmission potential and growing resistance to current antiviral therapies. To address this, the identification of novel and effective neuraminidase (NA) inhibitors is critical. [...] Read more.

The avian influenza virus, particularly the highly pathogenic H5N1 subtype, represents a significant public health threat due to its interspecies transmission potential and growing resistance to current antiviral therapies. To address this, the identification of novel and effective neuraminidase (NA) inhibitors is critical. In this study, an integrated in silico strategy was employed, beginning with the generation of an energy-optimized pharmacophore model (e-pharmacophore, ADDN) based on the reference inhibitor Zanamivir. A virtual screening of 47,781 natural compounds from the PubChem database was performed, followed by molecular docking validated through an enrichment assay. Promising hits were further evaluated via ADMET predictions, density functional theory (DFT) calculations to assess chemical reactivity, and molecular dynamics (MD) simulations to examine the stability of the ligand–protein complexes. Three lead compounds (C1: CID 102209473, C2: CID 85692821, and C3: CID 45379525) demonstrated strong binding affinity toward NA. Their ADMET profiles predicted favorable bioavailability and low toxicity. The DFT analyses indicated suitable chemical reactivity, particularly for C2 and C3. The MD simulations confirmed the structural stability of all three ligand–NA complexes, supported by robust and complementary intermolecular interactions. In contrast, Zanamivir exhibited limited hydrophobic interactions, compromising its binding stability within the active site. These findings offer a rational foundation for further experimental validation and the development of next-generation NA inhibitors derived from natural sources. Full article

(This article belongs to the Section Biochemical Engineering)

► Show Figures

Figure 1

20 pages, 368 KiB

Open AccessArticle

Sensory–Cognitive Profiles in Children with ADHD: Exploring Perceptual–Motor, Auditory, and Oculomotor Function

by Danjela Ibrahimi, Marcos Aviles, Rafael Rojas-Galván and Juvenal Rodríguez Reséndiz

Bioengineering 2025, 12(6), 621; https://doi.org/10.3390/bioengineering12060621 - 7 Jun 2025

Viewed by 343

Abstract

Objective: This observational cross-sectional study aimed to comprehensively evaluate sensory–cognitive performance in children diagnosed with Attention-Deficit/Hyperactivity Disorder (ADHD), with a focus on auditory processing, visual–perceptual abilities, visual–motor integration, and oculomotor function. The study further examined how hyperactivity, age, and gender may influence these [...] Read more.

Objective: This observational cross-sectional study aimed to comprehensively evaluate sensory–cognitive performance in children diagnosed with Attention-Deficit/Hyperactivity Disorder (ADHD), with a focus on auditory processing, visual–perceptual abilities, visual–motor integration, and oculomotor function. The study further examined how hyperactivity, age, and gender may influence these domains. Methods: A total of 70 non-medicated children with clinically diagnosed ADHD (mean age =

9.1 \pm 2.4

years; 67.1% male), all with normal visual acuity, were assessed using four standardized instruments: the Test of Auditory Processing Skills, Third Edition (TAPS-3), the Test of Visual Perceptual Skills, Fourth Edition (TVPS-4), the Beery–Buktenica Developmental Test of Visual–Motor Integration, Sixth Edition (VMI-6), and the Developmental Eye Movement (DEM) Test. Statistical analyses included one sample and independent samples t-tests, one-way ANOVA, and Pearson correlation coefficients. Results: Participants demonstrated significantly above-average performance in auditory processing (TAPS-3:

μ = 108.4

,

s t d = 7.8

), average visual–perceptual abilities (TVPS-4:

μ = 100.9

,

s t d = 7.2

), slightly below-average visual–motor integration (VMI-6:

μ = 97.1

,

s t d = 9.0

), and marked deficits in oculomotor efficiency (DEM ratio:

μ = 87.3

,

s t d = 18.1

). Statistically significant differences were observed across these domains (t-values ranging from 2.9 to 7.2,

p < 0.01

). Children with hyperactive-impulsive presentations exhibited lower horizontal DEM scores (

μ = 73.4

,

s t d = 12.3

) compared to inattentive counterparts (

μ = 82.9

,

s t d = 16.2

;

p = 0.009

). Age and sex influenced specific subtest scores, with boys and children aged 8–9 years achieving higher outcomes in word memory (

p = 0.042

) and visual discrimination (

p = 0.034

), respectively. Moderate correlations were identified between auditory and visual–perceptual skills (

r = 0.32

,

p = 0.007

), and between visual–perceptual and oculomotor performance (

r = 0.25

,

p = 0.035

). Conclusions: The findings from this sample reveal a distinct sensory–cognitive profile in children with ADHD, characterized by relatively preserved auditory processing and pronounced oculomotor deficits. These results underscore the value of a multimodal assessment protocol that includes oculomotor and visual efficiency evaluations. The conclusions pertain specifically to the cohort studied and should not be generalized to all populations with ADHD without further validation. Full article

(This article belongs to the Special Issue Adaptive Neurostimulation: Innovative Strategies for Stimulation)

► Show Figures

Figure 1

16 pages, 2032 KiB

Open AccessArticle

Auto-Segmentation and Auto-Planning in Automated Radiotherapy for Prostate Cancer

by Sijuan Huang, Jingheng Wu, Xi Lin, Guangyu Wang, Ting Song, Li Chen, Lecheng Jia, Qian Cao, Ruiqi Liu, Yang Liu, Xin Yang, Xiaoyan Huang and Liru He

Bioengineering 2025, 12(6), 620; https://doi.org/10.3390/bioengineering12060620 - 6 Jun 2025

Viewed by 201

Abstract

Objective: The objective of this study was to develop and assess the clinical feasibility of auto-segmentation and auto-planning methodologies for automated radiotherapy in prostate cancer. Methods: A total of 166 patients were used to train a 3D Unet model for segmentation of [...] Read more.

Objective: The objective of this study was to develop and assess the clinical feasibility of auto-segmentation and auto-planning methodologies for automated radiotherapy in prostate cancer. Methods: A total of 166 patients were used to train a 3D Unet model for segmentation of the gross tumor volume (GTV), clinical tumor volume (CTV), nodal CTV (CTVnd), and organs at risk (OARs). Performance was assessed by the Dice similarity coefficient (DSC), the Recall, Precision, Volume Ratio (VR), the 95% Hausdorff distance (HD95%), and the volumetric revision degree (VRD). An auto-planning network based on a 3D Unet was trained on 77 treatment plans derived from the 166 patients. Dosimetric differences and clinical acceptability of the auto-plans were studied. The effect of OAR editing on dosimetry was also evaluated. Results: On an independent set of 50 cases, the auto-segmentation process took 1 min 20 s per case. The DSCs for GTV, CTV, and CTVnd were 0.87, 0.88, and 0.82, respectively, with VRDs ranging from 0.09 to 0.14. The segmentation of OARs demonstrated high accuracy (DSC ≥ 0.83, Recall/Precision ≈ 1.0). The auto-planning process required 1–3 optimization iterations for 50%, 40%, and 10% of cases, respectively, and exhibited significant better conformity (p ≤ 0.01) and OAR sparing (p ≤ 0.03) while maintaining comparable target coverage. Only 6.7% of auto-plans were deemed unacceptable compared to 20% of manual plans, with 75% of auto-plans considered superior. Notably, the editing of OARs had no significant impact on doses. Conclusions: The accuracy of auto-segmentation is comparable to that of manual segmentation, and the auto-planning offers equivalent or better OAR protection, meeting the requirements of online automated radiotherapy and facilitating its clinical application. Full article

(This article belongs to the Special Issue Novel Imaging Techniques in Radiotherapy)

► Show Figures

Figure 1

15 pages, 2154 KiB

Open AccessArticle

Static and Dynamic Changes in Local Brain Connectivity in Unilateral Sudden Sensorineural Hearing Loss

by Junchao Zeng, Jing Li, Bo Liu, Qun Yu, Ziqiao Lei, Fan Yang, Mingyue Ding and Wenliang Fan

Bioengineering 2025, 12(6), 619; https://doi.org/10.3390/bioengineering12060619 - 5 Jun 2025

Viewed by 301

Abstract

Unilateral sudden sensorineural hearing loss (SSHL) presents substantial clinical challenges owing to its abrupt onset and multifactorial, poorly understood etiology. This study investigates the static and dynamic changes in local brain connectivity using regional homogeneity (ReHo) analyses in 102 SSHL patients and 73 [...] Read more.

Unilateral sudden sensorineural hearing loss (SSHL) presents substantial clinical challenges owing to its abrupt onset and multifactorial, poorly understood etiology. This study investigates the static and dynamic changes in local brain connectivity using regional homogeneity (ReHo) analyses in 102 SSHL patients and 73 healthy controls. A static ReHo analysis reveals pronounced disruptions in local synchronization within motor and cognitive-related brain regions in SSHL patients compared to controls. A dynamic ReHo analysis uncovers increased temporal variability, particularly in frontal regions, indicating potential adaptive neural plasticity to auditory deficits through enhanced neural plasticity. The correlation analyses further associate these neural changes with clinical parameters, highlighting the significant positive correlations between static ReHo in the left precentral gyrus and tinnitus severity (R = 0.39, p < 0.001), as well as the negative correlations between dynamic ReHo in the middle frontal gyrus and the duration of hearing loss (R = −0.35, p < 0.001). These findings underscore the complex interplay between static neural dysregulation and dynamic adaptive mechanisms in the pathophysiology of SSHL. Emphasizing dynamic metrics, our study provides a novel temporal perspective on how the brain reorganizes in response to acute sensory loss. Full article

(This article belongs to the Special Issue Biomedical Imaging and Data Analytics for Disease Diagnosis and Treatment, 2nd Edition)

► Show Figures

Figure 1

16 pages, 5703 KiB

Open AccessArticle

Biomechanical Analysis and Clinical Study of Augmented Versus Conventional Endoscopic Orbital Decompression for Dysthyroid Optic Neuropathy

by Pengsen Wu, Yiheng Wu, Jing Rao, Shenglan Yang, Hongyi Yao, Qingjiang Liu, Yuqing Wu, Shengli Mi and Guiqin Liu

Bioengineering 2025, 12(6), 618; https://doi.org/10.3390/bioengineering12060618 - 5 Jun 2025

Viewed by 194

Abstract

Dysthyroid optic neuropathy (DON) represents a severe ocular complication in thyroid eye disease (TED) that can lead to vision loss. Although surgical decompression is a well-established treatment modality, the optimal decompression area remains controversial in orbital decompression surgery. Purpose: This study aims to [...] Read more.

Dysthyroid optic neuropathy (DON) represents a severe ocular complication in thyroid eye disease (TED) that can lead to vision loss. Although surgical decompression is a well-established treatment modality, the optimal decompression area remains controversial in orbital decompression surgery. Purpose: This study aims to develop and validate a finite element analysis (FEA) model of DON to compare the biomechanical behavior between patients undergoing conventional or augmented orbital decompression surgery, with potential clinical implications for surgical planning. Methods: FEA models were established using magnetic resonance imaging data from patients with myopathic TED. Pre-disease, preoperative, and postoperative FEA models were developed for both the conventional orbital decompression group and the augmented group, in which the posteromedial floor and the orbital process of the palatine bone were additionally removed to analyze the stress distribution and displacement of the optic nerve, eyeball, and orbital wall. A retrospective analysis was performed to validate the biomechanical analysis results. Results: The FEA results reveal that DON patients experience higher stress on the optic nerve, eyeball, and orbital wall than healthy individuals, mainly concentrated at the orbital apex. Postoperatively, the stress on the optic nerve was significantly reduced in both groups. In addition, postoperative stress on the optic nerve was significantly lower in the augmented group than in the conventional group. The clinical results demonstrate that patients in the augmented group experienced significantly faster and more pronounced improvements in visual acuity and visual field. Conclusions: FEA shows that augmented orbital decompression surgery can alleviate stress more effectively, especially for the optic nerve, which was validated by clinical analysis. This developed FEA model of DON may facilitate determining the appropriate surgical procedure for orbital decompression. Full article

(This article belongs to the Special Issue Biomechanics Studies in Ophthalmology)

► Show Figures

Figure 1

11 pages, 2884 KiB

Open AccessSystematic Review

Leukocyte-Rich Platelet-Rich Plasma’s Clinical Effectiveness in Arthroscopic Rotator Cuff Repair: A Meta-Analysis of Randomized Controlled Trials

by Peiyuan Tang, Meihui Huang, Wenfeng Xiao, Ting Wen, Pavel Volotovsky, Mikhail Gerasimenko, Shiyao Chu, Shuguang Liu, Kai Zhang and Yusheng Li

Bioengineering 2025, 12(6), 617; https://doi.org/10.3390/bioengineering12060617 - 5 Jun 2025

Viewed by 253

Abstract

Background: Arthroscopic rotator cuff repair faces high retear risks in multi-tendon injuries due to insufficient biological healing; leukocyte-rich PRP may enhance tendon–bone integration through inflammatory modulation and growth factor release. Methods: Four databases including PubMed, Embase, Cochrane Library, and Web of [...] Read more.

Background: Arthroscopic rotator cuff repair faces high retear risks in multi-tendon injuries due to insufficient biological healing; leukocyte-rich PRP may enhance tendon–bone integration through inflammatory modulation and growth factor release. Methods: Four databases including PubMed, Embase, Cochrane Library, and Web of Science were searched until March 2025. Literature screening, quality evaluation, and data extraction were performed according to inclusion and exclusion criteria. GRADE was used to grade the strength of the evidence and the results. Results: The main finding of this study was that leukocyte-rich platelet-rich plasma combined with arthroscopic surgery for rotator cuff injuries can improve the Constant Score (MD = 1.13, 95% CI: 0.19, 2.07, p = 0.02, I² = 47%), American Shoulder and Elbow Surgeons score (MD = 6.02, 95% CI: 4.67, 7.36, p < 0.01, I² = 0%), and University of California, Los Angeles score (MD = 1.20, 95% CI: 0.34, 2.06, p < 0.01, I² = 0%) of patients with rotator cuff tear after treatment, and reduce the postoperative Visual Analog Scale score (MD = −0.62, 95% CI: −1.16, −0.08, p = 0.02, I² = 83%) of patients. However, there were no statistical differences regarding the Simple Shoulder Test (MD = 0.08, 95% CI: −0.23, 0.39, p = 0.61, I² = 5%). Conclusions: Based on current evidence, the use of LR-PRP in arthroscopic rotator cuff repair could lessen postoperative pain and improve postoperative functional scores in individuals with rotator cuff injuries. Full article

(This article belongs to the Special Issue Advances in Bone Regeneration with Multipotential Stromal Cells and Bioactive Materials)

► Show Figures

Figure 1

21 pages, 1280 KiB

Open AccessReview

A Review of Bioelectrochemical Strategies for Enhanced Polyhydroxyalkanoate Production

by Alejandro Chamizo-Ampudia, Raúl. M. Alonso, Luisa Ariza-Carmona, África Sanchiz and María Isabel San-Martín

Bioengineering 2025, 12(6), 616; https://doi.org/10.3390/bioengineering12060616 - 5 Jun 2025

Viewed by 323

Abstract

The growing demand for sustainable bioplastics has driven research toward more efficient and cost-effective methods of producing polyhydroxyalkanoates (PHAs). Among the emerging strategies, bioelectrochemical technologies have been identified as a promising approach to enhance PHA production by supplying electrons to microorganisms either directly [...] Read more.

The growing demand for sustainable bioplastics has driven research toward more efficient and cost-effective methods of producing polyhydroxyalkanoates (PHAs). Among the emerging strategies, bioelectrochemical technologies have been identified as a promising approach to enhance PHA production by supplying electrons to microorganisms either directly or indirectly. This review provides an overview of recent advancements in bioelectrochemical PHA synthesis, highlighting the advantages of this method, including increased production rates, the ability to utilize a wide range of substrates (including industrial and agricultural waste), and the potential for process integration with existing systems. Various bioelectrochemical systems (BES), electrode materials, and microbial strategies used for PHA biosynthesis are discussed, with a focus on the roles of electrode potentials and microbial electron transfer mechanisms in improving the polymer yield. The integration of BES into PHA production processes has been shown to reduce costs, enhance productivity, and support the use of renewable carbon sources. However, challenges remain, such as optimizing reactor design, scaling up processes, and improving the electron transfer efficiency. This review emphasizes the advancement of bioelectrochemical technologies combined with the use of agro-industrial waste as a carbon source, aiming to maximize the efficiency and sustainability of PHA production for large-scale industrial applications. Full article

(This article belongs to the Special Issue Development of Bioelectrochemical Systems for Environmental Engineering)

► Show Figures

Graphical abstract

13 pages, 1427 KiB

Open AccessArticle

Accelerometry and the Capacity–Performance Gap: Case Series Report in Upper-Extremity Motor Impairment Assessment Post-Stroke

by Estevan M. Nieto, Edaena Lujan, Crystal A. Mendoza, Yazbel Arriaga, Cecilia Fierro, Tan Tran, Lin-Ching Chang, Alvaro N. Gurovich, Peter S. Lum and Shashwati Geed

Bioengineering 2025, 12(6), 615; https://doi.org/10.3390/bioengineering12060615 - 4 Jun 2025

Viewed by 261

Abstract

This case series investigates whether traditional machine learning (ML) and convolutional neural network (CNN) models trained on wrist-worn accelerometry data collected in a laboratory setting can accurately predict real-world functional hand use in individuals with chronic stroke. Participants (N = 4) with neuroimaging-confirmed [...] Read more.

This case series investigates whether traditional machine learning (ML) and convolutional neural network (CNN) models trained on wrist-worn accelerometry data collected in a laboratory setting can accurately predict real-world functional hand use in individuals with chronic stroke. Participants (N = 4) with neuroimaging-confirmed chronic stroke completed matched activity scripts—comprising instrumental and basic activities of daily living—in-lab and at-home. Participants wore ActiGraph CenterPoint Insight watches on the impaired and unimpaired wrists; concurrent video recordings were collected in both environments. Frame-by-frame annotations of the video, guided by the FAABOS scale (functional, non-functional, unknown), served as the ground truth. The results revealed a consistent capacity–performance gap: participants used their impaired hand more in-lab than at-home, with the largest discrepancies in patients with moderate to severe impairment. Random forest ML models trained on in-lab accelerometry accurately classified at-home hand use, with the highest performance in mildly and severely impaired limbs (accuracy = 0.80–0.90) and relatively lower performance (accuracy = 0.62) in moderately impaired limbs. CNN models showed comparable accuracy to random forest classifiers. These pilot findings demonstrate the feasibility of using lab-trained ML models to monitor real-world hand use and identify emerging patterns of learned non-use—enabling timely, targeted interventions to promote recovery in outpatient stroke rehabilitation. Full article

(This article belongs to the Special Issue Advances in Physical Therapy and Rehabilitation)

► Show Figures

Figure 1

23 pages, 14306 KiB

Open AccessArticle

EEG-Driven Arm Movement Decoding: Combining Connectivity and Amplitude Features for Enhanced Brain–Computer Interface Performance

by Hamidreza Darvishi, Ahmadreza Mohammadi, Mohammad Hossein Maghami, Meysam Sadeghi and Mohamad Sawan

Bioengineering 2025, 12(6), 614; https://doi.org/10.3390/bioengineering12060614 - 4 Jun 2025

Viewed by 213

Abstract

Brain–computer interfaces (BCIs) translate electroencephalography (EEG) signals into control commands, offering potential solutions for motor-impaired individuals. While traditional BCI studies often focus solely on amplitude variations or inter-channel connectivity, movement-related brain activity is inherently dynamic, involving interactions across regions and frequency bands. We [...] Read more.

Brain–computer interfaces (BCIs) translate electroencephalography (EEG) signals into control commands, offering potential solutions for motor-impaired individuals. While traditional BCI studies often focus solely on amplitude variations or inter-channel connectivity, movement-related brain activity is inherently dynamic, involving interactions across regions and frequency bands. We propose that combining amplitude-based (filter bank common spatial patterns, FBCSP) and phase-based connectivity features (phase-locking value, PLV) improves decoding accuracy. EEG signals from ten healthy subjects were recorded during arm movements, with electromyography (EMG) as ground truth. After preprocessing (resampling, normalization, bandpass filtering), FBCSP and multi-lag PLV features were fused, and the ReliefF algorithm selected the most informative subset. A feedforward neural network achieved average metrics of: Pearson correlation 0.829 ± 0.077, R-squared value 0.675 ± 0.126, and root mean square error (RMSE) 0.579 ± 0.098 in predicting EMG amplitudes indicative of arm movement angles. Analysis highlighted contributions from both FBCSP and PLV, particularly in the 4–8 Hz and 24–28 Hz bands. This fusion approach, augmented by data-driven feature selection, significantly enhances movement decoding accuracy, advancing robust neuroprosthetic control systems. Full article

► Show Figures

Figure 1

17 pages, 1564 KiB

Open AccessReview

Capsule Endoscopy: Current Trends, Technological Advancements, and Future Perspectives in Gastrointestinal Diagnostics

by Chang-Chao Su, Chu-Kuang Chou, Arvind Mukundan, Riya Karmakar, Binusha Fathima Sanbatcha, Chien-Wei Huang, Wei-Chun Weng and Hsiang-Chen Wang

Bioengineering 2025, 12(6), 613; https://doi.org/10.3390/bioengineering12060613 - 4 Jun 2025

Viewed by 422

Abstract

Capsule endoscopy (CE) has revolutionized gastrointestinal (GI) diagnostics by providing a non-invasive, patient-centered approach to observing the digestive tract. Conceived in 2000 by Gavriel Iddan, CE employs a diminutive, ingestible capsule containing a high-resolution camera, LED lighting, and a power supply. It specializes [...] Read more.

Capsule endoscopy (CE) has revolutionized gastrointestinal (GI) diagnostics by providing a non-invasive, patient-centered approach to observing the digestive tract. Conceived in 2000 by Gavriel Iddan, CE employs a diminutive, ingestible capsule containing a high-resolution camera, LED lighting, and a power supply. It specializes in visualizing the small intestine, a region frequently unreachable by conventional endoscopy. CE helps detect and monitor disorders, such as unexplained gastrointestinal bleeding, Crohn’s disease, and cancer, while presenting a lower procedural risk than conventional endoscopy. Contrary to conventional techniques that necessitate anesthesia, CE reduces patient discomfort and complications. Nonetheless, its constraints, specifically the incapacity to conduct biopsies or therapeutic procedures, have spurred technical advancements. Five primary types of capsule endoscopes have emerged: steerable, magnetic, robotic, tethered, and hybrid. Their performance varies substantially. For example, the image sizes vary from 256 × 256 to 640 × 480 pixels, the fields of view (FOV) range from 140° to 360°, the battery life is between 8 and 15 h, and the frame rates fluctuate from 2 to 35 frames per second, contingent upon motion-adaptive capture. This study addresses a significant gap by methodically evaluating CE platforms, outlining their clinical preparedness, and examining the underexploited potential of artificial intelligence in improving diagnostic precision. Through the examination of technical requirements and clinical integration, we highlight the progress made in overcoming existing CE constraints and outline prospective developments for next-generation GI diagnostics. Full article

(This article belongs to the Special Issue Novel, Low Cost Technologies for Cancer Diagnostics and Therapeutics)

► Show Figures

Figure 1

21 pages, 6702 KiB

Open AccessArticle

Advancing Soft Tissue Reconstruction with a Ready-to-Use Human Adipose Allograft

by Victor Fanniel, Ihab Atawneh, Jonathan Savoie, Michelle Izaguirre-Ramirez, Joanna Marquez, Christopher Khorsandi and Shauna Hill

Bioengineering 2025, 12(6), 612; https://doi.org/10.3390/bioengineering12060612 - 4 Jun 2025

Viewed by 385

Abstract

Soft tissue reconstruction remains a challenge in clinical practice, particularly for restoring substantial volume loss due to surgical resections or contour deformities. Current methods, such as autologous fat transplantation, have limitations, including donor site morbidity and insufficient tissue availability, necessitating an innovative approach. [...] Read more.

Soft tissue reconstruction remains a challenge in clinical practice, particularly for restoring substantial volume loss due to surgical resections or contour deformities. Current methods, such as autologous fat transplantation, have limitations, including donor site morbidity and insufficient tissue availability, necessitating an innovative approach. This study characterizes alloClae, a minimally manipulated human-derived adipose allograft prepared using a detergent-based protocol to reduce DNA content while preserving adipose tissue structure. Proteomic analysis revealed that alloClae retains key native proteins critical for graft integration with the host and stability, with key extracellular matrix (ECM) components, collagens, elastins, and laminin, which are more concentrated as a result of the detergent-based protocol. Biocompatibility of alloClae was assessed in vitro using cytotoxicity and cell viability assays in fibroblast cultures, revealing no adverse effects on cell viability, membrane integrity, or oxidative stress. Additionally, in vitro studies with adipose-derived stem cells (ASCs) demonstrated attachment and differentiation, with lipid droplet accumulation observed by day 14, indicating support for adipogenesis. A 6-month longitudinal study in athymic mice showed stable graft retention, host cell infiltration, and formation of new adipocytes and vasculature within alloClae by 3 months. The findings highlight alloClae’s ability to support host-driven adipogenesis and angiogenesis while maintaining graft stability throughout the study period. It presents a promising alternative to the existing graft materials, offering a clinically translatable solution for soft tissue reconstruction. Full article

(This article belongs to the Special Issue Regenerative Technologies in Plastic and Reconstructive Surgery)

► Show Figures

Graphical abstract

13 pages, 30902 KiB

Open AccessArticle

GCSA-SegFormer: Transformer-Based Segmentation for Liver Tumor Pathological Images

by Jingbin Wen, Sihua Yang, Weiqi Li and Shuqun Cheng

Bioengineering 2025, 12(6), 611; https://doi.org/10.3390/bioengineering12060611 - 4 Jun 2025

Viewed by 278

Abstract

Pathological images are crucial for tumor diagnosis; however, due to their extremely high resolution, pathologists often spend considerable time and effort analyzing them. Moreover, diagnostic outcomes can be significantly influenced by subjective judgment. With the rapid advancement of artificial intelligence technologies, deep learning [...] Read more.

Pathological images are crucial for tumor diagnosis; however, due to their extremely high resolution, pathologists often spend considerable time and effort analyzing them. Moreover, diagnostic outcomes can be significantly influenced by subjective judgment. With the rapid advancement of artificial intelligence technologies, deep learning models offer new possibilities for pathological image diagnostics, enabling pathologists to diagnose more quickly, accurately, and reliably, thereby improving work efficiency. This paper proposes a novel Global Channel Spatial Attention (GCSA) module aimed at enhancing the representational capability of input feature maps. The module combines channel attention, channel shuffling, and spatial attention to capture global dependencies within feature maps. By integrating the GCSA module into the SegFormer architecture, the network, named GCSA-SegFormer, can more accurately capture global information and detailed features in complex scenarios. The proposed network was evaluated on a liver dataset and the publicly available ICIAR 2018 BACH dataset. On the liver dataset, the GCSA-SegFormer achieved a 1.12% increase in MIoU and a 1.15% increase in MPA compared to baseline models. On the BACH dataset, it improved MIoU by 1.26% and MPA by 0.39% compared to baseline models. Additionally, the performance metrics of this network were compared with seven different types of semantic segmentation, showing good results in all comparisons. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medical Image Processing and Segmentation, 2nd Edition)

► Show Figures

Graphical abstract

20 pages, 1726 KiB

Open AccessArticle

Experiences of People with Multiple Sclerosis in Sensor-Based Jump Assessment

by Anne Geßner, Anikó Vágó, Heidi Stölzer-Hutsch, Dirk Schriefer, Maximilian Hartmann, Katrin Trentzsch and Tjalf Ziemssen

Bioengineering 2025, 12(6), 610; https://doi.org/10.3390/bioengineering12060610 - 3 Jun 2025

Viewed by 273

Abstract

(1) Background: When implementing new biomechanical and technology-based assessments, such as the jump assessment in Multiple Sclerosis (MS), into clinical routine, it is important to ensure that they are based on the real needs of patients and to identify and adapt to potential [...] Read more.

(1) Background: When implementing new biomechanical and technology-based assessments, such as the jump assessment in Multiple Sclerosis (MS), into clinical routine, it is important to ensure that they are based on the real needs of patients and to identify and adapt to potential barriers early on. (2) Methods: In the present cross-sectional study, 157 pwMS performed a sensor-based jump assessment on a force plate consisting of three jump tests: 10 s jump test (10SHT), countermovement jumps (CMJ), and single-leg countermovement jumps (SLCMJ). After the jump assessment, the patient experience measures (PREM) were recorded using a paper-based questionnaire on an 11-point scale from 0 (positive) to 10 (negative). (3) Results: PwMS showed an overall positive experience with the sensor-based jump assessment. “Staff support performance”, “acceptance required time”, “usefulness” of the results, and “integration of results in therapy” were the best rated items with a median of 0 (positive). The CMJ was perceived as the easy (p < 0.05) and less exhausting (p < 0.05). PwMS who experienced CMJ as easy, not exhausting, and safe were associated with higher CMJ performance, especially in peak power, flight time, and jump height (r > −0.4). Significant associations were found between PREMs and age, sex, BMI, physical activity, and disability degree. (4) Conclusions: The study findings support the feasibility of jump assessment in clinical practice and highlight the need for patient-centered integration of innovative technologies to optimize precision neuromuscular function evaluation in MS. Full article

(This article belongs to the Special Issue Technological Advances for Gait and Balance Assessment)

► Show Figures

Figure 1

13 pages, 322 KiB

Open AccessArticle

Limited Diagnostic Value of Blood Cultures in Patients with Soft Tissue Infections Transferred to a Quaternary Care Center

by Mira H. Ghneim, Gregory M. Schrank, William Teeter, Brooke Andersen, Anna Brown and Quincy K. Tran

Bioengineering 2025, 12(6), 609; https://doi.org/10.3390/bioengineering12060609 - 3 Jun 2025

Viewed by 292

Abstract

Introduction: Patients with soft tissue infection are often encountered in clinical practice. The mainstay of treatment typically includes antimicrobial therapy, followed by surgical debridement when indicated. Blood cultures are often performed prior to starting the first dose of antibiotics. However, when patients require [...] Read more.

Introduction: Patients with soft tissue infection are often encountered in clinical practice. The mainstay of treatment typically includes antimicrobial therapy, followed by surgical debridement when indicated. Blood cultures are often performed prior to starting the first dose of antibiotics. However, when patients require transfer to tertiary/quaternary-level care for more advanced surgical interventions, blood cultures are often repeated despite patients being on broad-spectrum antibiotics. Our study aims to investigate the utility of blood cultures following transfer to a higher level of care. Methods: This is a retrospective study involving adult patients (≥18 years of age) who were transferred to a quaternary academic center with soft tissue infections between 15 June 2018 and 15 February 2022. Patients with incomplete medical records and/or without blood culture data after arrival were excluded. The primary outcome was the rate of positive blood cultures post-transfer. Descriptive analyses were performed, and comparisons between groups were expressed as absolute differences and 95% CI. Results: We analyzed 303 patients with a mean (+/−SD) age of 54 (14) years, and 199 (66%) were male. Necrotizing soft tissue infections (NSTIs) predominated, 198 patients (65%), with a majority of the NSTIs involving the perineum (112, 37%). The prevalence of positive blood cultures was 20 (7%) for pre-transfer and 14 (5%) for post-transfer. Among post-transfer positive blood cultures, 3 (21%) were coagulase-negative Staphylococcus aureus, with 2 (14%) cases each for the blood culture categories of polymicrobial, methicillin-sensitive Staphylococcus aureus, and Enterococcus faecalis, and 2 (14%) with Candida species. Among 112 patients with NSTIs of the perineum, 2 (14%) patients had positive blood cultures post-transfer, compared with 110 (38%) patients with negative blood cultures (difference 24%, 95% CI −0.40, −0.12, p < 0.001). Conclusions: For patients with soft tissue infection, the prevalence of positive blood culture after arrival at our quaternary care center was low at 5%. Pathogenic cases of positive blood cultures after transfer were polymicrobial, methicillin-sensitive Staphylococcus aureus and Candida species. However, the low number of post-transfer positive blood cultures limits the strength of the inference and should be interpreted cautiously. Further studies are necessary to confirm our observation. Clinicians at tertiary/quaternary care centers should consider the utility of obtaining blood cultures from patients with soft tissue infections transferred from other facilities. Full article

(This article belongs to the Special Issue Surgical Wound Infections and Management)

► Show Figures

Figure 1

22 pages, 2884 KiB

Open AccessReview

Research on Medical Image Segmentation Based on SAM and Its Future Prospects

by Kangxu Fan, Liang Liang, Hao Li, Weijun Situ, Wei Zhao and Ge Li

Bioengineering 2025, 12(6), 608; https://doi.org/10.3390/bioengineering12060608 - 3 Jun 2025

Viewed by 432

Abstract

The rapid advancement of prompt-based models in natural language processing and image generation has revolutionized the field of image segmentation. The introduction of the Segment Anything Model (SAM) has further invigorated this domain with its unprecedented versatility. However, its applicability to medical image [...] Read more.

The rapid advancement of prompt-based models in natural language processing and image generation has revolutionized the field of image segmentation. The introduction of the Segment Anything Model (SAM) has further invigorated this domain with its unprecedented versatility. However, its applicability to medical image segmentation remains uncertain due to significant disparities between natural and medical images, which demand careful consideration. This study comprehensively analyzes recent efforts to adapt SAM for medical image segmentation, including empirical benchmarking and methodological refinements aimed at bridging the gap between SAM’s capabilities and the unique challenges of medical imaging. Furthermore, we explore future directions for SAM in this field. While direct application of SAM to complex, multimodal, and multi-target medical datasets may not yet yield optimal results, insights from these efforts provide crucial guidance for developing foundational models tailored to the intricacies of medical image analysis. Despite existing challenges, SAM holds considerable potential to demonstrate its unique advantages and robust capabilities in medical image segmentation in the near future. Full article

(This article belongs to the Special Issue Advances in Medical 3D Vision: Voxels and Beyond)

► Show Figures

Figure 1

20 pages, 11903 KiB

Open AccessArticle

Regional Brain Aging Disparity Index: Region-Specific Brain Aging State Index for Neurodegenerative Diseases and Chronic Disease Specificity

by Yutong Wu, Shen Sun, Chen Zhang, Xiangge Ma, Xinyu Zhu, Yanxue Li, Lan Lin and Zhenrong Fu

Bioengineering 2025, 12(6), 607; https://doi.org/10.3390/bioengineering12060607 - 3 Jun 2025

Viewed by 308

Abstract

This study proposes a novel brain-region-level aging assessment paradigm based on Shapley value interpretation, aiming to overcome the interpretability limitations of traditional brain age prediction models. Although deep-learning-based brain age prediction models using neuroimaging data have become crucial tools for evaluating abnormal brain [...] Read more.

This study proposes a novel brain-region-level aging assessment paradigm based on Shapley value interpretation, aiming to overcome the interpretability limitations of traditional brain age prediction models. Although deep-learning-based brain age prediction models using neuroimaging data have become crucial tools for evaluating abnormal brain aging, their unidimensional brain age–chronological age discrepancy metric fails to characterize the regional heterogeneity of brain aging. Meanwhile, despite Shapley additive explanations having demonstrated potential for revealing regional heterogeneity, their application in complex deep learning algorithms has been hindered by prohibitive computational complexity. To address this, we innovatively developed a computational framework featuring efficient Shapley value approximation through a novel multi-stage computational strategy that significantly reduces complexity, thereby enabling an interpretable analysis of deep learning models. By establishing a reference system based on standard Shapley values from healthy populations, we constructed an anatomically specific Regional Brain Aging Deviation Index (RBADI) that maintains age-related validity. Experimental validation using UK Biobank data demonstrated that our framework successfully identified the thalamus (THA) and hippocampus (HIP) as core contributors to brain age prediction model decisions, highlighting their close associations with physiological aging. Notably, it revealed significant correlations between the insula (INS) and alcohol consumption, as well as between the inferior frontal gyrus opercular part (IFGoperc) and smoking history. Crucially, the RBADI exhibited superior performance in the tri-class classification of prodromal neurodegenerative diseases (HCs vs. MCI vs. AD: AUC = 0.92; HCs vs. pPD vs. PD: AUC = 0.86). This framework not only enables the practical implementation of Shapley additive explanations in brain age prediction deep learning models but also establishes anatomically interpretable biomarkers. These advancements provide a novel spatial analytical dimension for investigating brain aging mechanisms and demonstrate significant clinical translational value for early neurodegenerative disease screening, ultimately offering a new methodological tool for deciphering the neural mechanisms of aging. Full article

(This article belongs to the Special Issue AI Advancements in Healthcare: Medical Imaging and Sensing Technologies)

► Show Figures

Figure 1

3 pages, 130 KiB

Open AccessEditorial

Advanced 3D Cell Culture Technologies and Formats

by Cornelia Kasper and Dominik Egger

Bioengineering 2025, 12(6), 606; https://doi.org/10.3390/bioengineering12060606 - 3 Jun 2025

Viewed by 214

Abstract

The Special Issue “Advanced 3D Cell Culture Technologies and Formats” presents a collection of original research and review articles that explore recent innovations in three-dimensional (3D) cell culture systems aimed at enhancing the physiological relevance and therapeutic utility of cells and cell-derived products [...] Read more.

The Special Issue “Advanced 3D Cell Culture Technologies and Formats” presents a collection of original research and review articles that explore recent innovations in three-dimensional (3D) cell culture systems aimed at enhancing the physiological relevance and therapeutic utility of cells and cell-derived products and assays [...] Full article

(This article belongs to the Special Issue Advanced 3D Cell Culture Technologies and Formats)

18 pages, 1389 KiB

Open AccessArticle

e-Health Strategy for Surgical Prioritization: A Methodology Based on Digital Twins and Reinforcement Learning

by Fabián Silva-Aravena, Jenny Morales and Manoj Jayabalan

Bioengineering 2025, 12(6), 605; https://doi.org/10.3390/bioengineering12060605 - 2 Jun 2025

Viewed by 426

Abstract

This article presents a methodological framework for elective surgery scheduling based on the integration of patient-specific Digital Twins (DTs) and reinforcement learning (RL). The proposed approach aims to support the future development of an intelligent e-health platform for dynamic, data-driven prioritization of surgical [...] Read more.

This article presents a methodological framework for elective surgery scheduling based on the integration of patient-specific Digital Twins (DTs) and reinforcement learning (RL). The proposed approach aims to support the future development of an intelligent e-health platform for dynamic, data-driven prioritization of surgical patients. We generate prioritization scores by modeling clinical, economic, behavioral, and social variables in real time and optimize access through a reinforcement learning engine designed to maximize long-term system performance. The methodology is designed as a modular, transparent, and interoperable digital decision-support architecture aligned with the goals of organizational transformation and equitable healthcare delivery. To validate its potential, we simulate realistic surgical scheduling scenarios using synthetic patient data. Results demonstrate substantial improvements compared withto traditional strategies, including a 55.1% reduction in average wait time, a 41.9% decrease in clinical risk at surgery, a 16.1% increase in OR utilization, and a significant increase in the prioritization of socially vulnerable patients. These findings highlight the value of the proposed framework as a foundation for future smart healthcare platforms that support transparent, adaptive, and ethically aligned decision-making in surgical scheduling. Full article

(This article belongs to the Section Biosignal Processing)

► Show Figures

Figure 1

14 pages, 440 KiB

Open AccessArticle

Deep-Learning-Based Computer-Aided Grading of Cervical Spinal Stenosis from MR Images: Accuracy and Clinical Alignment

by Zhiling Wang, Xinquan Chen, Bin Liu, Jinjin Hai, Kai Qiao, Zhen Yuan, Lianjun Yang, Bin Yan, Zhihai Su and Hai Lu

Bioengineering 2025, 12(6), 604; https://doi.org/10.3390/bioengineering12060604 - 1 Jun 2025

Viewed by 307

Abstract

Objective: This study aims to apply different deep learning convolutional neural network algorithms to assess the grading of cervical spinal stenosis and to evaluate their consistency with clinician grading results as well as clinical manifestations of patients. Methods: We retrospectively enrolled 954 patients [...] Read more.

Objective: This study aims to apply different deep learning convolutional neural network algorithms to assess the grading of cervical spinal stenosis and to evaluate their consistency with clinician grading results as well as clinical manifestations of patients. Methods: We retrospectively enrolled 954 patients with cervical spine magnetic resonance imaging (MRI) data and medical records from the Fifth Affiliated Hospital of Sun-Yat Sen University. The Kang grading method for sagittal MR images of the cervical spine and the spinal cord compression ratio for horizontal MR images of the cervical spine were adopted for cervical spinal canal stenosis grading. The collected data were randomly divided into training/validation and test sets. The training/validation sets were processed by various image preprocessing and annotation methods, in which deep learning convolutional networks, including classification, target detection, and key point localization models, were applied. The predictive grading of the test set by the model was finally contrasted with the grading results of the clinicians, and correlation analysis was performed with the clinical manifestations of the patients. Result: The EfficientNet_B5 model achieved a five-fold cross-validated accuracy of 79.45% and near-perfect agreement with clinician grading on the test set (κ= 0.848, 0.822), surpassing resident–clinician consistency (κ = 0.732, 0.702). The model-derived compression ratio (0.45 ± 0.07) did not differ significantly from manual measurements (0.46 ± 0.07). Correlation analysis showed moderate associations between model outputs and clinical symptoms: EfficientNet_B5 grades (r = 0.526) were comparable to clinician assessments (r = 0.517, 0.503) and higher than those of residents (r = 0.457, 0.448). Conclusion: CNN models demonstrate strong performance in the objective, consistent, and efficient grading of cervical spinal stenosis severity, offering potential clinical value in automated diagnostic support. Full article

(This article belongs to the Special Issue Artificial Intelligence for Computer-Aided Detection in Biomedical Applications)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Bioengineering, Volume 12, Issue 6 (June 2025) – 77 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI