Next Issue
Volume 13, May
Previous Issue
Volume 13, March
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.5
4.4
Journals
Bioengineering
Volume 13
Issue 4
share announcement

Bioengineering, Volume 13, Issue 4 (April 2026) – 111 articles

Cover Story (view full-size image): Continuous blood pressure monitoring in laboratory rabbits is vital for preclinical cardiovascular research, yet common methods require terminal carotid catheterization or expensive implantable telemetry. This study introduces a low-cost, minimally invasive IoT-based system that measures arterial pressure via the central auricular artery using an ESP32 microcontroller, an INA122 amplifier, and a disposable pressure transducer. Digitized signals are wirelessly transmitted to the ThingSpeak cloud platform, where MATLAB-based processing extracts systolic (SBP), diastolic (DBP), and mean arterial pressure (MAP) in real time. A pilot evaluation against the direct method using the BIOPAC MP100 as a reference showed relative errors of 1.60% (MAP), 8.58% (SBP), and 2.43% (DBP). This approach avoids surgical implantation and enables remote monitoring, supporting long-term hemodynamic studies. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
18 pages, 1499 KB  
Article
Toward Personalized Rotator Cuff Physical Therapy Dosage Using a Machine Learning-Based Pilot Study with EMG
by AmirHossein MajidiRad, Iram Azam, Japp Adhikari and Mehrnoosh Damircheli
Bioengineering 2026, 13(4), 483; https://doi.org/10.3390/bioengineering13040483 - 21 Apr 2026
Viewed by 880
Abstract
Rotator cuff injuries are among the most common musculoskeletal conditions that affect shoulder function and can ultimately impact quality of life. While physical therapy is essential in the care of rotator cuff injuries, the ideal dose of therapeutic exercises continues to be a [...] Read more.
Rotator cuff injuries are among the most common musculoskeletal conditions that affect shoulder function and can ultimately impact quality of life. While physical therapy is essential in the care of rotator cuff injuries, the ideal dose of therapeutic exercises continues to be a significant clinical dilemma because of the generalized nature of rehabilitation protocols. This pilot study proposes a machine learning approach to personalize rehabilitation using surface electromyography (sEMG) data collected from eight healthy individuals by testing four key shoulder movements: scaption, internal rotation, external rotation, and external rotation at 90° abduction. In this research, the XGBoost algorithm was used to model muscle activation patterns by achieving a high predictive accuracy (R2 = 0.5325; MSE = 0.0084 μV2). Because sEMG reliably measures superficial muscle activity, a linear programming model was used to divide a 60 min therapy session in a way that increases activation of superficial muscles (such as deltoid and trapezius) while reducing strain on deep muscles (such as supraspinatus and infraspinatus). Three optimization scenarios were tested by reflecting a different clinical goal: prioritizing superficial muscles, minimizing deep muscle strain, or balancing both. Optimized time allocations assigned more time to external rotation at 90° abduction and scaption. This research demonstrates the potential for data-driven methods to transform rotator cuff rehabilitation through personalized and evidence-based treatment plans. The results enhance clinical practice by enabling adaptive rehabilitation planning and show that machine learning can support decision-making in complex muscle activation analysis with strong performance and low latency. Full article
(This article belongs to the Special Issue Advances in Physical Therapy and Rehabilitation, 2nd Edition)
►▼ Show Figures

Figure 1

5 pages, 152 KB  
Editorial
Recent Findings and Developments in Spine Biomechanics
by Christian Liebsch
Bioengineering 2026, 13(4), 482; https://doi.org/10.3390/bioengineering13040482 - 21 Apr 2026
Viewed by 815
Abstract
As the central musculoskeletal element of the human body, the spine simultaneously enables trunk movement, upright posture, and load transfer from the upper to the lower body [...] Full article
(This article belongs to the Special Issue Spine Biomechanics)
1 pages, 127 KB  
Correction
Correction: Patsouris et al. Advances in Innovative Surgical Implant Manufacturing for Hernia Repair and Soft Tissue Reconstruction. Bioengineering 2025, 12, 1182
by Stavros Patsouris, Panagiotis Mallis, Efstathios Michalopoulos, Nefeli Papadopoulou, Michalis Katsimpoulas and Nikolaos Nikiteas
Bioengineering 2026, 13(4), 481; https://doi.org/10.3390/bioengineering13040481 - 21 Apr 2026
Viewed by 410
Abstract
Revisions to Authorship and Affiliation [...] Full article
(This article belongs to the Section Regenerative Engineering)
40 pages, 1792 KB  
Article
An Effective Model-Based Voting Classifier for Diabetes Mellitus Classification
by Diyar Qader Zeebaree, Merdin Shamal Salih, Danial William Odeesho, Dilovan Asaad Zebari, Nechirvan Asaad Zebari, Omar I. Dallal Bashi, Reving Masoud Abdulhakeem and Yahya Ahmed Yahya
Bioengineering 2026, 13(4), 480; https://doi.org/10.3390/bioengineering13040480 - 21 Apr 2026
Cited by 1 | Viewed by 824
Abstract
Diabetes mellitus is a health issue that is rapidly increasing worldwide, and it affects more than 347 million people globally. It is important to note that the disease can be successfully detected in its early stages, enabling physicians to avoid complications and improve [...] Read more.
Diabetes mellitus is a health issue that is rapidly increasing worldwide, and it affects more than 347 million people globally. It is important to note that the disease can be successfully detected in its early stages, enabling physicians to avoid complications and improve patient outcomes. Despite the fact that machine learning (ML) has been extensively used in diabetes classification, the available solutions tend to place little or no emphasis on feature selection and ensembles, which limits prediction accuracy and generalizability. In this study, we introduce a hybrid framework that is based on three feature-selection algorithms, specifically, genetic algorithm (GA), correlation-based feature selection (CFS) and recursive feature elimination (RFE), in single and hybrid forms, and three classifiers, namely, multi-layer perceptron (MLP), support vector machine (SVM) and random forest (RF), to achieve a greater predictive robustness with the aid of soft voting. Experimental findings obtained from a benchmark diabetes dataset indicate that the RFE + CFS + SVM combination achieves the best performance, with an accuracy of 98.0%, sensitivity of 97.43%, specificity of 99.03%, precision of 99.51% and F1-score of 98.72%. These results indicate that the suggested hybrid feature-selection and ensemble learning model can offer a robust and highly effective approach for early-stage diabetes diagnosis, one which clinicians may use to make timely and accurate decisions. Full article
(This article belongs to the Section Biosignal Processing)
►▼ Show Figures

Figure 1

11 pages, 2008 KB  
Brief Report
Nano-Enhanced Optical Delivery of Multi-Characteristic Opsin Gene for Spinal Optogenetic Modulation of Pain
by Darryl Narcisse, Robert Benkowski, Matthew Dwyer and Samarendra Mohanty
Bioengineering 2026, 13(4), 479; https://doi.org/10.3390/bioengineering13040479 - 20 Apr 2026
Viewed by 617
Abstract
Optogenetic modulation employs light-sensitive proteins known as opsins to regulate cellular activity. A unique therapeutic application of this technique involves modulating pain perception by selectively targeting neural pathways within the spinal cord. Multi-Characteristic Opsin (MCO) represents an innovative optogenetic actuator capable of activation [...] Read more.
Optogenetic modulation employs light-sensitive proteins known as opsins to regulate cellular activity. A unique therapeutic application of this technique involves modulating pain perception by selectively targeting neural pathways within the spinal cord. Multi-Characteristic Opsin (MCO) represents an innovative optogenetic actuator capable of activation across a broad spectrum of light wavelengths, exhibiting a slow depolarizing phase that resembles natural photoreceptors. This study examines the current advancements in spinal optogenetic modulation utilizing MCO for pain management. Due to its high sensitivity, MCO facilitates minimally invasive, remotely controlled optogenetic modulation of spinal neurons. This approach enables the regulation of extensive spatial regions, provided the MCO channel receives sufficient light intensity to surpass the activation threshold. Nano-enhanced optical delivery (NOD) successfully transfected spinal neurons with the GAD67-MCO2-mCherry construct, as confirmed by membrane-localized mCherry fluorescence with DAPI-labeled nuclei. Using this platform, 5 Hz spinal optogenetic stimulation produced a significant reduction in formalin-evoked pain behaviors, demonstrating frequency-specific modulation of spinal pain circuits. Neither 2 Hz nor 10 Hz stimulation yielded comparable analgesic effects, underscoring the importance of precise stimulation parameters. The therapeutic impact also depended on transfection efficiency: reducing the fGNR–plasmid concentration diminished MCO expression and weakened the analgesic response. Together, these results show that effective spinal optogenetic pain modulation requires both optimal stimulation frequency and robust gene delivery. Full article
(This article belongs to the Section Nanobiotechnology and Biofabrication)
►▼ Show Figures

Figure 1

25 pages, 3544 KB  
Review
Bioengineering Pancreatic Organoids and iPSC-Derived β-Cells for Diabetes: Materials, Devices, and Translational Challenges
by Abdullah Jabri, Mohamed Alsharif, Bader Taftafa, Tasnim Abbad, Dania Sibai, Abdulaziz Mhannayeh, Abdulrahman Elsalti, Islam M. Saadeldin, Jahan Salma, Tanveer Ahmad Mir and Ahmed Yaqinuddin
Bioengineering 2026, 13(4), 478; https://doi.org/10.3390/bioengineering13040478 - 18 Apr 2026
Viewed by 1019
Abstract
Diabetes mellitus is primarily caused by the loss or malfunction of insulin-producing β-cells, and although current therapies improve glycemic control, they do not restore physiologic insulin secretion. Advances in stem cell biology and organoid engineering have led to the development of pancreatic organoids [...] Read more.
Diabetes mellitus is primarily caused by the loss or malfunction of insulin-producing β-cells, and although current therapies improve glycemic control, they do not restore physiologic insulin secretion. Advances in stem cell biology and organoid engineering have led to the development of pancreatic organoids and induced pluripotent stem cell (iPSC)-derived β-cells as promising platforms for disease modeling, drug testing, and regenerative medicine. Pancreatic organoids generated from ductal, acinar, or progenitor populations can recapitulate key anatomical and functional features of native pancreatic tissue, enabling studies of development, injury, and regeneration. In parallel, improvements in iPSC differentiation protocols have produced β-like cells capable of insulin secretion in response to glucose, although achieving full functional maturity remains a challenge. Bioengineering strategies, including biomaterial scaffolds, microfluidic platforms, endothelial co-culture systems, three-dimensional bioprinting, and CRISPR-based genome editing, have enhanced the stability, vascular compatibility, and functional performance of both organoid and iPSC-derived systems. Despite these advances, variability in differentiation efficiency, limited β-cell maturity, and poor long-term survival continue to hinder clinical translation. Together, pancreatic organoids and iPSC-derived β-cells represent complementary platforms that advance fundamental research and support the development of β-cell replacement therapies, with ongoing integration of bioengineering approaches expected to accelerate progress toward reproducible, scalable, and clinically relevant β-cell regeneration. Full article
(This article belongs to the Section Regenerative Engineering)
►▼ Show Figures

Figure 1

16 pages, 4741 KB  
Article
Robust Non-Invasive Cardiac Index Prediction via Feature Integration and Data-Augmented Neural Networks
by Chih-Hao Chang, Mei-Ling Chan, Yu-Hung Fang, Po-Lin Huang, Tsung-Yi Chen, Tsun-Kuang Chi, I Elizabeth Cha, Tzong-Rong Ger, Kuo-Chen Li, Shih-Lun Chen, Liang-Hung Wang, Jia-Ching Wang and Patricia Angela R. Abu
Bioengineering 2026, 13(4), 477; https://doi.org/10.3390/bioengineering13040477 - 18 Apr 2026
Viewed by 635
Abstract
Concurrent with the rising consumption of ultra-processed, high-calorie diets and the decline in physical activity, obesity and related cardiovascular conditions among young adults have continued to increase, becoming an important global public health concern. This study integrates non-invasive Internet of Things (IoT) sensing [...] Read more.
Concurrent with the rising consumption of ultra-processed, high-calorie diets and the decline in physical activity, obesity and related cardiovascular conditions among young adults have continued to increase, becoming an important global public health concern. This study integrates non-invasive Internet of Things (IoT) sensing devices, including the TERUMO ES-P2000 blood pressure monitor (Terumo Corp., Tokyo, Japan) and the PhysioFlow PF07 Enduro cardiac hemodynamic analyzer (Manatec Biomedical, Poissy, France), with an artificial neural network (ANN) for cardiac index (CI) prediction. Through appropriate data preprocessing and model training strategies, the generalization ability and stability of the proposed CI prediction model were significantly enhanced. Experimental results demonstrate that, when using three physiological parameters as input, the ANN achieved a classification accuracy of 97.78%, substantially outperforming traditional approaches. Even under two-parameter input conditions, the model maintained strong predictive performance. These findings confirm the effectiveness and practical potential of the proposed framework for real-time, non-invasive CI assessment. Moreover, this research has received rigorous assessment and approval from the Institutional Review Board (IRB) under application number 202501987B0. Full article
(This article belongs to the Special Issue Artificial Intelligence Revolution in Biomedical Image and Signal Processing: Innovations and Applications)
►▼ Show Figures

Figure 1

50 pages, 11144 KB  
Review
Photoacoustic Imaging for Women’s Gynecological Health: Advances and Clinical Prospects
by Panangattukara Prabhakaran Praveen Kumar, Dong-Kwon Lim and Taeho Kim
Bioengineering 2026, 13(4), 476; https://doi.org/10.3390/bioengineering13040476 - 18 Apr 2026
Viewed by 1159
Abstract
Photoacoustic imaging (PAI) is an emerging hybrid biomedical imaging modality that combines the high molecular contrast of optical excitation with the deep tissue penetration of ultrasound detection. This review presents recent advances in PAI-based techniques for the detection and characterization of gynecological diseases [...] Read more.
Photoacoustic imaging (PAI) is an emerging hybrid biomedical imaging modality that combines the high molecular contrast of optical excitation with the deep tissue penetration of ultrasound detection. This review presents recent advances in PAI-based techniques for the detection and characterization of gynecological diseases in women, with particular focus on endometriosis and uterine-related disorders. We summarize the application of PAI across preclinical and translational studies, highlighting progress in photoacoustic microscopy, spectroscopic photoacoustic imaging, and endoscopic and probe-based implementations for non-invasive, high-resolution tissue evaluation. The role of functional and contrast-enhanced PAI approaches is discussed, emphasizing their ability to enhance diagnostic sensitivity, enable longitudinal monitoring, and provide detailed information on vascular, biochemical, and structural tissue characteristics. Furthermore, the expanding applications of PAI in assessing uterine, cervical, and ovarian pathologies, including tumor detection and tissue remodeling, are reviewed. Finally, current challenges, limitations, and future directions toward clinical translation are addressed. Collectively, this review underscores the potential of photoacoustic imaging as a powerful, non-invasive platform for early diagnosis, disease monitoring, and improved management of women’s health conditions. Full article
(This article belongs to the Section Biomedical Engineering and Biomaterials)
►▼ Show Figures

Graphical abstract

18 pages, 611 KB  
Article
Clinically Robust Deep Learning for Contrast-Enhanced Mammography: Multicenter Evaluation Across Convolutional Neural Network Architectures
by Roberta Fusco, Vincenza Granata, Paolo Vallone, Teresa Petrosino, Maria Daniela Iasevoli, Roberta Galdiero, Mauro Mattace Raso, Davide Pupo, Filippo Tovecci, Annamaria Porto, Gerardo Ferrara, Modesta Longobucco, Giulia Capuano, Roberto Morcavallo, Caterina Todisco, Fabiana Antenucci, Mario Sansone, Mimma Castaldo, Daniele La Forgia and Antonella Petrillo
Bioengineering 2026, 13(4), 475; https://doi.org/10.3390/bioengineering13040475 - 17 Apr 2026
Viewed by 612
Abstract
Background: This study investigates the impact of anatomically constrained preprocessing and deep learning architecture selection on benign versus malignant breast lesion classification in contrast-enhanced mammography (CEM), with the goal of improving robustness and clinical reliability across heterogeneous data sources. Methods: In this retrospective [...] Read more.
Background: This study investigates the impact of anatomically constrained preprocessing and deep learning architecture selection on benign versus malignant breast lesion classification in contrast-enhanced mammography (CEM), with the goal of improving robustness and clinical reliability across heterogeneous data sources. Methods: In this retrospective multicenter study, CEM images from 300 patients (314 lesions) were combined with 1003 publicly available CEM images, yielding a total of 1120 breast cases. Automatic breast segmentation was performed using the LIBRA framework to generate breast-mask images. Eleven deep learning models, including classical convolutional neural networks, attention-based networks, hybrid convolutional neural networks (CNNs), Transformer architectures, and mammography-specific models, were trained and evaluated using both original DICOM images and breast-mask inputs. Performance was assessed using accuracy, balanced accuracy, sensitivity, specificity, AUROC, and AUPRC on cross-validation and independent test sets. Hyperparameter optimization was conducted for the best-performing architecture. Results: Models trained on breast-mask images consistently outperformed those trained on original DICOM images across all architectures and metrics, with AUROC improvements ranging from +0.06 to +0.21. Among all models, ResNet50 trained on breast-mask images achieved the best performance (AUROC = 0.931; AUPRC = 0.933; balanced accuracy = 0.834), further improved after optimization (balanced accuracy = 0.886; sensitivity = 0.842; specificity = 0.930). Classical CNN architectures demonstrated performance comparable to or exceeding that of more complex hybrid CNN–Transformer models when anatomically focused preprocessing and rigorous optimization were applied. Conclusions: Anatomically constrained preprocessing through breast-mask segmentation substantially enhances deep learning performance and stability in CEM-based breast lesion classification. These findings indicate that input representation quality and training optimization are critical determinants of clinically relevant performance, often outweighing architectural complexity, and may support more reliable AI-assisted decision support in CEM workflows. Full article
(This article belongs to the Special Issue New Sights of Deep Learning and Digital Model in Biomedicine)
►▼ Show Figures

Figure 1

30 pages, 1288 KB  
Article
Efficient and Dynamically Consistent Joint Torque Estimation for Wearable Neurotechnology via Knowledge Distillation
by Shu Xu, Zheng Chang, Zenghui Ding, Xianjun Yang, Tao Wang and Dezhang Xu
Bioengineering 2026, 13(4), 474; https://doi.org/10.3390/bioengineering13040474 - 17 Apr 2026
Viewed by 524
Abstract
Wearable neurotechnology depends critically on continuous movement monitoring to characterize motor impairment and recovery in real-world settings. While joint torque serves as a clinically essential kinetic marker, estimating it directly on-device from inertial signals remains challenging due to stringent computational, memory, and energy [...] Read more.
Wearable neurotechnology depends critically on continuous movement monitoring to characterize motor impairment and recovery in real-world settings. While joint torque serves as a clinically essential kinetic marker, estimating it directly on-device from inertial signals remains challenging due to stringent computational, memory, and energy constraints. Lightweight pipelines typically omit computationally expensive time–frequency processing; however, this omission degrades the observability of dynamics encoded in 1D IMU signals and diminishes the effectiveness of standard knowledge distillation strategies. To enable reliable on-device torque inference, we propose a Physically Guided Dual-Consistency Knowledge Distillation (PDC-KD) framework that explicitly integrates biomechanical priors into the learning process through two collaborative pathways: parameter-manifold alignment and physics-guided compensation. The student network receives guidance through Fisher-information-weighted parameter transfer, ensuring robust knowledge distillation despite significant model capacity mismatch. Furthermore, the framework incorporates a physics-guided regularization term that enforces dynamically consistent torque trajectories via a numerically stable Cholesky-parameterized constraint. Experiments demonstrate that the student model preserves teacher-level predictive accuracy while operating within the stringent resource constraints of edge devices (achieving a 98% parameter reduction, ∼2× faster inference, and ∼1 ms latency). Moreover, the proposed method yields torque estimates with enhanced dynamical consistency, providing an efficient biosignal-processing solution for wearable neurotechnology platforms demanding real-time movement analytics. Full article
(This article belongs to the Special Issue Wearable Devices for Neurotechnology)
►▼ Show Figures

Figure 1

19 pages, 679 KB  
Review
Biomechanical Factors and Prevention Strategies for Sports-Related Muscle Injuries: A Narrative Review
by Catalin Ionite, Lucian Indrei, Andrei Gheorghiță, Bogdan Caba, Marius Turnea, Irina Duduca, Cezar Mucileanu, Iustina Condurache and Mariana Rotariu
Bioengineering 2026, 13(4), 473; https://doi.org/10.3390/bioengineering13040473 - 17 Apr 2026
Viewed by 1680
Abstract
Sports-related muscle injuries represent a major challenge in both recreational and professional sports, accounting for a substantial proportion of time-loss injuries and frequently leading to recurrent episodes. The aim of this narrative review was to analyze the biomechanical and neuromuscular mechanisms involved in [...] Read more.
Sports-related muscle injuries represent a major challenge in both recreational and professional sports, accounting for a substantial proportion of time-loss injuries and frequently leading to recurrent episodes. The aim of this narrative review was to analyze the biomechanical and neuromuscular mechanisms involved in the occurrence of muscle injuries and to synthesize evidence-based prevention strategies reported in the scientific literature. The literature search was conducted in the Web of Science database using the keyword “muscle injury prevention”, focusing on studies published between 2010 and 2025. The analyzed literature indicates that muscle injuries are strongly associated with eccentric contractions at long muscle lengths, neuromuscular fatigue, strength imbalances, impaired lumbopelvic stability, and inadequate load management. Preventive strategies based on biomechanical principles, particularly eccentric strength training, neuromuscular training programs, and core stability exercises, have demonstrated consistent effectiveness in reducing injury incidence and recurrence rates across multiple sports disciplines. In addition, emerging technological approaches, including wearable sensors and machine learning models, show promising potential for injury risk prediction and individualized prevention strategies. Full article
(This article belongs to the Special Issue Orthopedic and Trauma Biomechanics)
►▼ Show Figures

Figure 1

14 pages, 2594 KB  
Article
The Influence of Non-Thermal Plasma Treatment on Osseointegration of Endosteal Implants Presenting Decompressing Vertical Chambers
by Shray Mehra, Hana Shah, Sara E. Munkwitz, Nicholas J. Iglesias, Tina Joshua, Kashyap K. Tadisina, Natalia Fullerton, Vasudev Vivekanand Nayak, Lukasz Witek and Paulo G. Coelho
Bioengineering 2026, 13(4), 472; https://doi.org/10.3390/bioengineering13040472 - 17 Apr 2026
Viewed by 498
Abstract
Current evidence suggests that achieving the desired level of osseointegration necessitates a hierarchical approach to implant design. This is particularly relevant for osseointegration around implant systems such as those presenting vertical decompression chambers and acid-etched surfaces which could further be augmented by non-thermal [...] Read more.
Current evidence suggests that achieving the desired level of osseointegration necessitates a hierarchical approach to implant design. This is particularly relevant for osseointegration around implant systems such as those presenting vertical decompression chambers and acid-etched surfaces which could further be augmented by non-thermal plasma (NTP) treatment. Three implant systems were compared in this study: (i) ND (GM Helix Acqua Implant; Neodent®, Curitiba, PR, Brazil—hybrid, acid-etched thread design treated with isotonic sodium chloride solution), (ii) Sin (Epikut Plus; S.I.N. Implant System, São Paulo, Brazil—V-shaped, acid-etched thread design treated with nano-hydroxyapatite), and (iii) Mp (Maestro; Implacil De Bortoli, São Paulo, Brazil—buttress, acid-etched thread design with decompressing vertical chambers). The ND and Sin implants were used directly as supplied by the manufacturer. For the Mp implants, the manufacturer-supplied surface was subjected to supplemental acid etching with 37% hydrochloric acid followed by Argon-based NTP treatment administered with a pulsed plasma generator prior to implantation into the iliac crest of n = 12 adult female sheep. Histomorphometric analysis was conducted at 3- and 12-week post-implantation (n = 6 sheep per time point) to assess bone-to-implant contact (BIC) and bone area fraction occupancy (BAFO). After 3 weeks in vivo, the healing chambers of all implant groups consisted predominantly of newly forming woven bone. By 12 weeks, bone maturation was observed, with the presence of remodeling sites and some areas of well-organized lamellar structures occupying the healing chambers. At both 3 and 12 weeks, the Mp implants demonstrated significantly higher BAFO values relative to ND (p = 0.015 and p = 0.008, respectively). The combination of vertical healing chambers, acid etching, and NTP treatment promoted early vascular infiltration and sustained bone deposition. Full article
(This article belongs to the Section Biomedical Engineering and Biomaterials)
►▼ Show Figures

Figure 1

16 pages, 4004 KB  
Article
Automated Aortic Quantification Based on Artificial Intelligence: Validation Using Contrast-Enhanced and Non-Contrast CT Scans from the Same Session
by Jia-Sheng Hong, Yun-Hsuan Tzeng, Kuan-Ting Wu, Shih-Yu Huang, Ting-Wei Wang, Guan-Yu Li, Chun-Yi Lin, Ho-Ren Liu, Hai-Neng Fu, Yung-Tsai Lee, Wei-Hsian Yin and Yu-Te Wu
Bioengineering 2026, 13(4), 471; https://doi.org/10.3390/bioengineering13040471 - 17 Apr 2026
Viewed by 583
Abstract
Early detection of aortic dilatation is clinically important for preventing progression to serious aortic disease and enabling timely intervention. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. [...] Read more.
Early detection of aortic dilatation is clinically important for preventing progression to serious aortic disease and enabling timely intervention. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired contrast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensitivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based workflow enables highly sensitive automated aortic quantification in both contrast-enhanced and non-contrast CT scans, supporting broader clinical applicability across different imaging conditions. Full article
(This article belongs to the Special Issue Artificial Intelligence Revolution in Biomedical Image and Signal Processing: Innovations and Applications)
►▼ Show Figures

Figure 1

14 pages, 937 KB  
Review
Insight into Kidney Function and Microstructure Through Renal MRI—Review of the Literature
by Marcin Majos, Artur Klepaczko and Ilona Kurnatowska
Bioengineering 2026, 13(4), 470; https://doi.org/10.3390/bioengineering13040470 - 17 Apr 2026
Cited by 1 | Viewed by 651
Abstract
Chronic kidney disease (CKD) represents a growing medical, diagnostic and social challenge, and it is estimated to effect 8.5–9.8% of the global population and requires expensive modes of treatment, such as hemodialysis or renal transplants. Currently, a diagnosis of CKD is set based [...] Read more.
Chronic kidney disease (CKD) represents a growing medical, diagnostic and social challenge, and it is estimated to effect 8.5–9.8% of the global population and requires expensive modes of treatment, such as hemodialysis or renal transplants. Currently, a diagnosis of CKD is set based on the level of creatinine in the blood, which is the gold standard of renal function diagnostics. Unfortunately, decrease in GFR is secondary to damage of the kidney parenchyma and indicates that the best time to start more aggressive treatment has already passed. Therefore, several non-invasive methods have been proposed for predicting increased risk of CKD progression; however, in most of the cases kidney biopsy is essential. Currently, the greatest hopes for a method that can confirm CKD are associated with the development of MRI, the most tissue-specific imaging method, and it is already proven to be capable to detect inflammatory and edematous changes, fibrosis, as well as perfusion and oxygenation disturbances. Therefore, in our manuscript we decided to present up-to-date knowledge about kidney MRI from a clinical point of view. Full article
(This article belongs to the Special Issue Diagnostic Imaging and Radiation Therapy in Biomedical Engineering)
►▼ Show Figures

Figure 1

23 pages, 5658 KB  
Article
Evaluation of the Effectiveness of a Novel Wireless Energy-Transmitting Implantable Diaphragm Pacemaker in Anesthetized Pigs
by Xiaoyu Gu, Wei Zhong, Zhihao Mao, Yan Shi and Yixuan Wang
Bioengineering 2026, 13(4), 469; https://doi.org/10.3390/bioengineering13040469 - 16 Apr 2026
Viewed by 609
Abstract
Objectives: This study aimed to demonstrate the feasibility of a novel wireless energy-transmitting implantable diaphragm pacemaker for restoring respiratory ventilation. Methods: The diaphragm pacing (DP) system was designed based on the principle of electromagnetic resonance coupling. The safety of device implantation was analyzed [...] Read more.
Objectives: This study aimed to demonstrate the feasibility of a novel wireless energy-transmitting implantable diaphragm pacemaker for restoring respiratory ventilation. Methods: The diaphragm pacing (DP) system was designed based on the principle of electromagnetic resonance coupling. The safety of device implantation was analyzed through finite-element simulations of multi-field coupling between electromagnetic heating and biological tissue. In vitro testing with coils embedded in pork demonstrated the system output characteristics. This device was used in miniature Bama pigs that underwent deep anesthesia and respiratory arrest (N = 8). Respiratory airflow, diaphragmatic displacement, and blood gases were used to evaluate the effectiveness of the designed DP system. Results: Thermal effect simulation results show that the temperature rise of the surrounding tissue does not exceed 2 °C during 1 h of transmission power (0.5–1.3 W) operation of the receiver. In vitro tests with two receivers embedded in pork showed that the DP system can effectively output stimulation waveforms over a certain transmission distance (5–35 mm). The stimulation waveform output by the receiver is consistent with the parameters set by the external controller. In phrenic nerve electrical stimulation experiments, the peak respiratory airflow and tidal volume remained stable over 50 consecutive respiratory cycles. The tidal volume (108.63 mL) and diaphragmatic displacement (0.883–2.15 cm) in a pig induced by DP demonstrate the effectiveness of respiratory ventilation. The arterial blood gas analysis results and temperature rise experiment during implantation further confirmed the effectiveness and safety of the ventilation. Conclusions: The implantable diaphragmatic pacemaker developed in this study exhibits good thermal safety, stable output, and effective respiratory ventilation. A control group with commercial diaphragmatic pacemakers and data from chronic implantation experiments are needed to further evaluate its effectiveness. Full article
(This article belongs to the Special Issue Advances in Neural Interface Techniques and Applications)
►▼ Show Figures

Figure 1

19 pages, 1983 KB  
Article
Using Large Language Models to Generate Dietary Feedback Similar to Human Experts in Weight Management: Experiments on Real-World Scenario Data
by Ruixin Dai, Liping Cui, Kun Hu, Jiye An and Ning Deng
Bioengineering 2026, 13(4), 468; https://doi.org/10.3390/bioengineering13040468 - 16 Apr 2026
Viewed by 905
Abstract
Providing dietary feedback is important for promoting healthy behaviors in weight management, but the rapid development of obesity and the shortage of medical nutrition human resources have limited this health service. The rise of large language models (LLMs) offers the possibility of using [...] Read more.
Providing dietary feedback is important for promoting healthy behaviors in weight management, but the rapid development of obesity and the shortage of medical nutrition human resources have limited this health service. The rise of large language models (LLMs) offers the possibility of using artificial intelligence (AI) to simulate the behavior of human dietitians. However, existing studies have only explored LLM performance when generating answers to common nutrition-related questions; the use of LLMs to generate situation-adapted dietary feedback in practical weight management scenarios still needs further research. In this study, we collected dietary records and dietary feedback from primary dietitians through an mHealth weight management application. We conducted topic modeling to generalize how dietitians deliver nutrition guidance in real-world dietary feedback scenarios. Combining the in-context learning capability of LLMs with real-world data, we proposed a synthetic data generation approach (HDI-SDG) and trained an LLM for dietary feedback with the synthetic data (LLMDF-EXP). Experiments on automatic and manual evaluation of LLMDF-EXP and an LLM trained directly with the real-world data as well as generalized LLMs illustrated that LLMDF-EXP performed most similarly to human experts. Notably, there were no significant differences from human experts in terms of professionalism (p-value = 0.510) and usefulness (p-value = 0.498). The study highlights that integrating LLMs with real-world data in health management processes can enhance the situational adaptability of LLMs in practical health management environment applications. Full article
(This article belongs to the Special Issue Advances in Intelligent Health Management and Rehabilitation Technology: Integrating Large Language Models and AI Solutions)
►▼ Show Figures

Figure 1

15 pages, 3786 KB  
Article
A Flexible Copper Electrode Array for High-Density Surface Electromyography
by Chaoxin Li, Chenghong Lu, Jiuqiang Li and Kai Guo
Bioengineering 2026, 13(4), 467; https://doi.org/10.3390/bioengineering13040467 - 16 Apr 2026
Viewed by 599
Abstract
Precise monitoring of forearm muscle groups is crucial for decoding motor intentions in human–machine interfaces (HMIs) and rehabilitation. However, traditional surface electromyography (sEMG) electrodes face significant challenges in densely packed muscle regions with large skin deformations, leading to severe signal crosstalk and unstable [...] Read more.
Precise monitoring of forearm muscle groups is crucial for decoding motor intentions in human–machine interfaces (HMIs) and rehabilitation. However, traditional surface electromyography (sEMG) electrodes face significant challenges in densely packed muscle regions with large skin deformations, leading to severe signal crosstalk and unstable contact. Here, we report a flexible, low-cost 16-channel copper electrode array system designed for the high-density monitoring of multiple forearm muscle activities. Through a facile fabrication process, rigid copper is transformed into a conformable sensing interface. The optimized serpentine interconnects endow the array with excellent stretchability and effectively isolate motion-induced stress, ensuring high-quality signal acquisition under complex deformations. The high-density 2 × 8 array enables the spatiotemporal mapping of distributed flexor and extensor muscle groups. Integrated with a customized wireless data acquisition system, the array successfully demonstrates real-time, multi-channel sEMG monitoring of various hand movements (e.g., fist clenching, wrist flexion/extension), clearly revealing specific muscle activation patterns. This low-cost, high-performance flexible sensor array provides a highly promising tool for complex gesture decoding, electromyographic imaging, and next-generation wearable HMIs. Full article
(This article belongs to the Special Issue Intelligent Medical Robots: Human–Machine Interaction and Medical Innovations)
►▼ Show Figures

Figure 1

24 pages, 30745 KB  
Review
Vision–Language Models in Medical Imaging for Cancer Diagnosis: A Bibliometric Review
by Musa Adamu Wakili, Aminu Bashir Suleiman, Kaloma Usman Majikumna, Harisu Abdullahi Shehu, Huseyin Kusetogullari and Md. Haidar Sharif
Bioengineering 2026, 13(4), 466; https://doi.org/10.3390/bioengineering13040466 - 16 Apr 2026
Viewed by 1304
Abstract
The demand for advanced detection methods and accurate staging remains a global challenge in cancer diagnosis. Even though traditional deep learning models in medical imaging achieve high precision, they suffer from limited explainability and multimodal reasoning due to their black-box nature, thereby limiting [...] Read more.
The demand for advanced detection methods and accurate staging remains a global challenge in cancer diagnosis. Even though traditional deep learning models in medical imaging achieve high precision, they suffer from limited explainability and multimodal reasoning due to their black-box nature, thereby limiting their clinical applicability. To address this gap, recent research has increasingly explored multimodal approaches that integrate visual and textual clinical data to enhance diagnostic accuracy and interpretability. This study presents a bibliometric analysis of 408 publications from 2021 to 2025, collected from Web of Science and Scopus, using VOSviewer and R-Bibliometrix to map citation networks, co-authorship, and keyword co-occurrences. The results reveal a rapid growth from 1 publication in 2021 to 269 in 2025, with significant contributions from leading countries and institutions. Thematic analysis indicates a shift from conventional convolutional approaches toward transformer-based and self-supervised methods, alongside increasing attention to multimodal learning in cancer imaging tasks such as breast, lung, and brain cancer analysis. Overall, this study provides a structured overview of the evolving research landscape, highlighting key trends, emerging themes, and research gaps to inform future developments in multimodal artificial intelligence for cancer diagnosis. Full article
(This article belongs to the Special Issue AI and Machine Learning in Medical Image Processing: Innovations and Applications)
►▼ Show Figures

Figure 1

16 pages, 2188 KB  
Article
Biomineralization of Glucose Oxidase from Aspergillus niger in ZIF-zni for Enhanced Biocatalytic Performance
by Marija Stanišić, Milica Crnoglavac Popović, Nikola Knežević, Marko Radenković, Branimir Bajac, Olivera Prodanović and Radivoje Prodanović
Bioengineering 2026, 13(4), 465; https://doi.org/10.3390/bioengineering13040465 - 16 Apr 2026
Viewed by 646
Abstract
Biomineralization has recently emerged as a highly effective strategy for enzyme immobilization. Zeolitic imidazolate frameworks (ZIFs), a subclass of metal–organic frameworks (MOFs), are particularly attractive carriers due to their structural tunability and chemical stability. While ZIF-8 has been extensively studied, its denser and [...] Read more.
Biomineralization has recently emerged as a highly effective strategy for enzyme immobilization. Zeolitic imidazolate frameworks (ZIFs), a subclass of metal–organic frameworks (MOFs), are particularly attractive carriers due to their structural tunability and chemical stability. While ZIF-8 has been extensively studied, its denser and thermodynamically more stable analog ZIF-zni has received far less attention. In this work, we report the biomineralization of glucose oxidase (GOx) from Aspergillus niger within the ZIF-zni framework and systematically investigate the influence of zinc and imidazole (Im) concentration on immobilization performance. The optimized biocomposite, obtained at 10 mM Zn2+ and a Zn:Im ratio of 1:10, exhibited a specific activity of 2051 IU g−1, which is more than twice the activity obtained for GOx@ZIF-8 in our previous study (874 IU g−1). Furthermore, the GOx@ZIF-zni biocomposite demonstrated remarkable resistance to sodium dodecyl sulfate (SDS) and retained up to 50% of its activity after incubation at 65 °C for one hour. These results demonstrate that ZIF-zni is a highly promising carrier for enzyme immobilization and suggest that framework topology and synthesis conditions play a crucial role in determining the catalytic performance and stability of enzyme@MOF biocomposites. Full article
(This article belongs to the Special Issue Development of Biocatalytic Processes and Green Energy Technologies)
►▼ Show Figures

Figure 1

32 pages, 15173 KB  
Article
Effects of Purkinje Fiber Conduction Block on Cardiac Pump Function: Computational Modeling Study
by Sandra P. Hager, Vahid Ziaei-Rad, Jenny S. Choy, Mengjun Wang, Ghassan S. Kassab and Lik Chuan Lee
Bioengineering 2026, 13(4), 464; https://doi.org/10.3390/bioengineering13040464 - 15 Apr 2026
Viewed by 746
Abstract
Cardiac and hemodynamic conditions such as myocardial infarct, cardiomyopathy, hypertension, and aortic valve disease can impair conduction within the Purkinje fiber network and compromise left ventricular (LV) pump function. We developed a computational framework that couples electrical propagation in a structurally organized Purkinje [...] Read more.
Cardiac and hemodynamic conditions such as myocardial infarct, cardiomyopathy, hypertension, and aortic valve disease can impair conduction within the Purkinje fiber network and compromise left ventricular (LV) pump function. We developed a computational framework that couples electrical propagation in a structurally organized Purkinje fiber network with LV electromechanics to analyze the impact of conduction abnormalities on cardiac performance. A baseline simulation reproduced physiological activation patterns and pump indices consistent with healthy human data. Conduction block was then introduced at different locations within the Purkinje fiber network. LV pump function was strongly dependent on block location: left bundle branch block (LBBB) produced the largest reduction in ejection fraction (EF) (59% to 46%) and peak pressure (119 to 97 mmHg), whereas left anterior fascicle block caused smaller functional changes. Across simulations, myocardial activation delay and systolic dyssynchrony index (SDI) exhibited a nonlinear relationship with EF and myocardial strain. A threshold behavior was identified at a simulated LV activation duration of approximately 240 ms and an SDI of 8.4%, beyond which EF and strain decreased by about 5% relative to baseline. These findings provide a mechanistic framework to investigate how Purkinje fiber network conduction abnormalities influence LV pump dysfunction. Full article
(This article belongs to the Special Issue Preclinical Models in Cardiovascular Disease Research)
►▼ Show Figures

Figure 1

34 pages, 3125 KB  
Article
Optimized Signal Acquisition and Advanced AI for Robust 1D EMG Classification: A Comparative Study of Machine Learning, Deep Learning, and Reinforcement Learning
by Anagha Shinde, Virendra Shete and Ninad Mehendale
Bioengineering 2026, 13(4), 463; https://doi.org/10.3390/bioengineering13040463 - 15 Apr 2026
Viewed by 895
Abstract
Electromyography (EMG) signals are critical for prosthetic control, rehabilitation, and human–machine interaction, yet their classification remains challenging due to noise, non-stationarity, and inter-subject variability. This study presents a comprehensive comparative analysis of machine learning (ML), deep learning (DL), and reinforcement learning (RL) approaches [...] Read more.
Electromyography (EMG) signals are critical for prosthetic control, rehabilitation, and human–machine interaction, yet their classification remains challenging due to noise, non-stationarity, and inter-subject variability. This study presents a comprehensive comparative analysis of machine learning (ML), deep learning (DL), and reinforcement learning (RL) approaches for 1D EMG signal classification, with a systematic evaluation of signal acquisition parameters. Using both synthetic and real-world EMG datasets, we demonstrate that 8–10 bit quantization and a 2000 Hz sampling rate provide optimal signal fidelity while maintaining data efficiency. Among the evaluated models, ensemble methods (Gradient Boosting, Voting Ensemble) and advanced DL architectures (LSTM, Transformer) achieved superior performance on real EMG data, with accuracies reaching 100% and 96.3%, respectively. Notably, reinforcement learning agents (Deep Q-Networks) demonstrated 100% accuracy on multiclass synthetic data, revealing their potential for learning complex bio-signal representations. Our findings establish that meticulous optimization of preprocessing pipelines, combined with robust AI models, significantly enhances EMG classification accuracy. This work provides empirical guidance for selecting optimal acquisition parameters and AI architectures for practical EMG analysis systems, with direct implications for prosthetic control and rehabilitation technologies. Full article
(This article belongs to the Section Biosignal Processing)
►▼ Show Figures

Graphical abstract

13 pages, 2161 KB  
Article
Characterization of Multilayer Structure-Graded Dental Zirconias
by Ragai-Edward Matta, Renan Belli, Katrin Hurle, Arulraj Sangarapillai, Oleksandr Sednyev, Manfred Wichmann and Lara Berger
Bioengineering 2026, 13(4), 462; https://doi.org/10.3390/bioengineering13040462 - 14 Apr 2026
Viewed by 704
Abstract
Multilayer zirconias have recently been introduced as dental biomaterials to combine improved translucency with sufficient mechanical reliability by implementing yttria-driven gradients in phase composition. Such materials can be considered functionally graded ceramics, where local phase stabilization influences strength and crack resistance. However, manufacturer-specific [...] Read more.
Multilayer zirconias have recently been introduced as dental biomaterials to combine improved translucency with sufficient mechanical reliability by implementing yttria-driven gradients in phase composition. Such materials can be considered functionally graded ceramics, where local phase stabilization influences strength and crack resistance. However, manufacturer-specific gradient profiles and their structure–property relationships remain insufficiently characterized. This study investigated two commercially available multilayer zirconias with distinct gradient concepts: IPS e.max® ZirCAD Prime (continuous gradient) and KATANA™ Zirconia YML (stepwise gradient). Ten equidistant sections along the blank height were analyzed using quantitative X-ray diffraction and Rietveld refinement to quantify zirconia phase fractions and estimate local Y2O3 content. Mechanical behavior was evaluated by biaxial flexural strength testing (ball-on-three-balls method) and fracture toughness testing using the chevron-notched beam technique. Both materials exhibited pronounced yttria- and phase-dependent gradients consistent with their reported layer designs. Regions with increased yttria content showed higher t″ fractions and reduced fracture toughness and strength, whereas deeper regions displayed increased mechanical performance associated with higher fractions of transformable tetragonal phase. These findings emphasize that multilayer zirconias exhibit spatially dependent mechanical properties, which should be considered in biomaterial selection and restoration design, particularly when balancing aesthetic demands and fracture resistance. Full article
(This article belongs to the Special Issue Advanced Dental Materials for Restorative Dentistry)
►▼ Show Figures

Graphical abstract

23 pages, 1399 KB  
Review
Bibliometric Analysis of Artificial Intelligence in Pediatric Radiology and Medical Imaging: A Focus on Deep Learning Applications
by Ahmad Tijjani Garba, Aminu Bashir Suleiman, Wenze Du, Ahmed Ibrahim Mahmud, Harisu Abdullahi Shehu, Huseyin Kusetogullari and Md. Haidar Sharif
Bioengineering 2026, 13(4), 461; https://doi.org/10.3390/bioengineering13040461 - 14 Apr 2026
Cited by 1 | Viewed by 937
Abstract
This study presents the first dedicated bibliometric analysis of artificial intelligence (AI) and deep learning applications in pediatric radiology and medical imaging, mapping the intellectual structure of a rapidly evolving field. A total of 2688 articles and conference proceedings published between 2005 and [...] Read more.
This study presents the first dedicated bibliometric analysis of artificial intelligence (AI) and deep learning applications in pediatric radiology and medical imaging, mapping the intellectual structure of a rapidly evolving field. A total of 2688 articles and conference proceedings published between 2005 and 2025 were retrieved from the Web of Science Core Collection and analyzed using Bibliometrix R and VOSviewer. The findings reveal exponential growth in publications, from 7 papers in 2005 to 559 in 2025, with journal articles dominating the corpus (85.9%). The most-cited contributions, led by Kermany et al. (2018) with 2886 citations, are predominantly technical feasibility studies rather than clinical outcome trials, indicating a field that has advanced methodologically but remains in early stages of clinical translation. Thematic mapping identifies convolutional neural networks, pneumonia, and transfer learning as Motor Themes representing methodological maturity in chest imaging, while neuroimaging and image segmentation clusters occupy Niche Themes, reflecting insular development with limited cross-field connectivity. Geographic analysis reveals concentrated co-authorship along US–China and US–Europe corridors, with African, Latin American, and Southeast Asian institutions largely absent from knowledge production networks. Eight of the ten most productive affiliations are North American, highlighting structural inequities that risk producing AI tools optimized for high-resource settings rather than the global pediatric population. This analysis provides an empirical foundation for reorienting the field toward clinical validation, geographic inclusion, and methodological integration across isolated research communities. Full article
(This article belongs to the Special Issue AI and Machine Learning in Medical Image Processing: Innovations and Applications)
►▼ Show Figures

Figure 1

13 pages, 2014 KB  
Article
In Vitro Experimental Study of Biofiligree® Osteosynthesis in Calcaneus Fracture Fixation
by António Ramos, Olga Noronha, Orlando Simões, José Noronha and José Simões
Bioengineering 2026, 13(4), 460; https://doi.org/10.3390/bioengineering13040460 - 14 Apr 2026
Viewed by 553
Abstract
Surgical fixation techniques for bone fracture healing are well established and effective; however, opportunities remain to improve both functional outcomes and the patient experience. The Biofiligree® concept integrates medicine, engineering, and design by reimagining conventional osteosynthesis plates as both therapeutic and aesthetic [...] Read more.
Surgical fixation techniques for bone fracture healing are well established and effective; however, opportunities remain to improve both functional outcomes and the patient experience. The Biofiligree® concept integrates medicine, engineering, and design by reimagining conventional osteosynthesis plates as both therapeutic and aesthetic devices. Inspired by traditional Portuguese filigree, these plates allow patient participation through personalized geometries, patterns, or engravings and may later be transformed into wearable jewellery after removal, preserving them as symbolic artefacts of recovery. This study introduces and biomechanically evaluates a novel calcaneal fixation plate incorporating the biofiligree geometry concept. A biofiligree plate was designed for calcaneus fracture fixation and manufactured in stainless steel 306L. Experimental testing was conducted on synthetic composite calcaneus bone models to simulate anatomical conditions and compare the new design with a standard commercial plate. The biofiligree plate, 2 mm thick, was fixed using five screws and two percutaneous screws positioned at 45° to compress the fracture line. Results demonstrated comparable biomechanical performance between both systems, with similar strain distributions and fracture stabilization. The biofiligree plate showed stresses around 430 MPa and fracture displacement below 0.7 mm. Fixation stiffness values were 1445 N/mm for intact calcaneus, 1065 N/mm for the commercial plate, and 725 N/mm for the biofiligree plate, indicating adequate support for bone healing. Full article
(This article belongs to the Special Issue Application of Bioengineering to Orthopedics)
►▼ Show Figures

Graphical abstract

17 pages, 3800 KB  
Article
Ureteral Orifice Detection in Ureteroscopic Images Based on Large-Kernel Convolutional Neural Networks and Attention-Based Feature Fusion
by Liang Li, Chen-Yi Jiang, Xing-Jie Wang, Yuan-Jun Wang and Jian Zhuo
Bioengineering 2026, 13(4), 459; https://doi.org/10.3390/bioengineering13040459 - 14 Apr 2026
Viewed by 526
Abstract
Objective: To enhance the information modeling capacity of large-kernel convolutional neural networks and to build a ureteral orifice detection framework for ureteroscopic imaging. Methods: A retrospective dataset of ureteroscopic images from 222 patients was collected. The patients were randomly divided into [...] Read more.
Objective: To enhance the information modeling capacity of large-kernel convolutional neural networks and to build a ureteral orifice detection framework for ureteroscopic imaging. Methods: A retrospective dataset of ureteroscopic images from 222 patients was collected. The patients were randomly divided into training and testing sets at a ratio of 7:3. Initially, video files were converted into image frames, and feature-relevant images were manually labeled by physicians. Subsequently, a ConvNeXt-based backbone augmented with squeeze-and-excitation (SE) modules was employed to extract diverse deep features. SCConv modules were incorporated across stages to strengthen the network’s feature extraction performance. Lastly, enhanced spatial excitation attention mechanisms were cascaded to achieve superior feature fusion and detection accuracy. Comparative experiments were conducted against baseline models, including ConvNeXt, assessing accuracy, computational overhead, and inference latency. Results: On a test set of 491 ureteroscopic images, all models achieved mAP@50 values above 0.75, whereas the proposed network achieved 0.890, markedly exceeding baseline performance. The model operated at 20 ms per frame, achieving a frame rate of 50 FPS. Conclusions: We developed an improved deep learning framework based on large-kernel convolutional networks for real-time ureteral orifice detection in endoscopic scenarios. This system achieves a favorable balance between detection accuracy and real-time efficiency. The method demonstrates significant potential as a training and feedback tool for residents and junior urologists in clinical environments. Full article
(This article belongs to the Special Issue Multimodal Generative AI for Health Monitoring and Bioengineering Applications)
►▼ Show Figures

Figure 1

11 pages, 245 KB  
Opinion
Prospects and Limitations of Bioprinting in Studying Human Cells’ Responses to Extreme Environments
by Taieba Tuba Rahman, Zhijian Pei, Hongmin Qin and Hamid R. Parsaei
Bioengineering 2026, 13(4), 458; https://doi.org/10.3390/bioengineering13040458 - 14 Apr 2026
Viewed by 671
Abstract
Understanding human’s responses to extreme environments holds significant importance for space exploration, deep-sea research, and environmental adaptation. Traditionally, human subjects were used to study humans’ responses to extreme environments. The main limitations of this approach include the inability to independently investigate specific cellular [...] Read more.
Understanding human’s responses to extreme environments holds significant importance for space exploration, deep-sea research, and environmental adaptation. Traditionally, human subjects were used to study humans’ responses to extreme environments. The main limitations of this approach include the inability to independently investigate specific cellular mechanisms, ethical and safety constraints, limited experimental controllability, and inter-individual variability that complicates mechanistic interpretation. Another approach is to study humans’ responses at the cellular level using 2D culture. This approach often exhibits limited reproducibility due to its inability to recapitulate physiologically relevant microenvironments. Bioprinting can enable studies on human’s responses at the cellular level and within 3D environments. One way is to study human cells’ responses to localized and transient extreme environments created during printing. Another way is to expose 3D printed samples (embedded with human cells) to extreme environments. However, the literature does not contain comprehensive review papers to discuss the prospects and limitations of bioprinting for investigating human cells’ responses to extreme environments. This review paper aims to fill this gap in the literature. It begins with a brief description of the effects of extreme environments on human health and summarizes reported studies on cells’ responses to extreme environments. Afterward, it discusses the prospects and limitations of the two ways of using bioprinting to investigate cells’ responses to extreme environments. Finally, it concludes with identifying knowledge gaps and proposing research directions in the application of bioprinting to study human cells’ responses to extreme environments. Full article
(This article belongs to the Special Issue Biofabrication of Biologically Realistic Constructs: Needs, Challenges, and Opportunities)
16 pages, 1470 KB  
Article
Physics-Guided Deep Learning for Interpretable Biomedical Image Reconstruction and Pattern Recognition in Diagnostic Frameworks
by Akeel Qadir, Saad Arif, Prajoona Valsalan and Osama Khan
Bioengineering 2026, 13(4), 457; https://doi.org/10.3390/bioengineering13040457 - 13 Apr 2026
Viewed by 834
Abstract
This study introduces a physics-guided deep learning architecture designed for the simulation, reconstruction, and pattern recognition of biomedical images. By explicitly integrating physical priors into the learning model, the framework addresses the black-box nature of traditional artificial intelligence (AI). It provides an explainable [...] Read more.
This study introduces a physics-guided deep learning architecture designed for the simulation, reconstruction, and pattern recognition of biomedical images. By explicitly integrating physical priors into the learning model, the framework addresses the black-box nature of traditional artificial intelligence (AI). It provides an explainable AI pathway that enhances diagnostic accuracy, robustness, and clinical interpretation. The proposed framework was evaluated through systematic simulation studies. It involved complex geometric configurations, multimodal physical fields, and noise-corrupted synthetic three-dimensional brain volumes. Quantitative analysis demonstrates consistent improvements in reconstruction fidelity, with the peak signal-to-noise ratio (PSNR) reaching 47 dB and the structural similarity index exceeding 0.90 across all scenarios. Notably, at moderate noise levels (0.05), the framework maintains a PSNR greater than 32 dB, ensuring structural integrity essential for computer-aided diagnosis. Volumetric brain experiments further reveal a 38–44% reduction in activation localization errors, highlighting the framework’s utility in functional imaging and disease prognosis. By grounding deep learning in physical constraints, this study provides a transparent and robust solution for automated disease classification and advanced biomedical imaging tasks within clinical decision support systems. Full article
(This article belongs to the Special Issue Recent Advances in Machine Learning and Explainable Artificial Intelligence in Biomedical Data Mining, and Disease Diagnosis Frameworks—2nd Edition)
►▼ Show Figures

Figure 1

20 pages, 4643 KB  
Article
Deep Learning-Assisted Early Detection of Skin Cancer from Dermoscopic Images in Underserved Clinical Settings
by Anchal Kumari, Punam Rattan, Anand Kumar Shukla, Sita Rani, Aman Kataria, Hong Min and Taeho Kim
Bioengineering 2026, 13(4), 456; https://doi.org/10.3390/bioengineering13040456 - 13 Apr 2026
Cited by 1 | Viewed by 983
Abstract
Skin cancer is caused by aberrant cells that proliferate uncontrollably after unrepaired DNA damage results in mutations in the epidermis. The majority of skin cancer is caused by high UV exposure from the sun, tanning beds, or sunlamps. Due to sociocultural hurdles, limited [...] Read more.
Skin cancer is caused by aberrant cells that proliferate uncontrollably after unrepaired DNA damage results in mutations in the epidermis. The majority of skin cancer is caused by high UV exposure from the sun, tanning beds, or sunlamps. Due to sociocultural hurdles, limited access to specialized dermatological care, and low public knowledge, many nations, including India, have higher mortality rates and late-stage presentations. The unequal distribution of specialized dermatological treatments, particularly in rural and underdeveloped areas, makes detection and treatment more difficult. For skin cancer, one of the most prevalent malignancies with a high death rate, early detection is crucial. This study gathered 1200 dermoscopic images from two clinics in Himachal Pradesh in order to solve these problems. In order to automatically classify dermoscopic clinical images into melanoma and non-melanoma skin cancer categories, this study compares VGG16 with ResNet-50. Preprocessing, lesion segmentation, and classification are all part of the suggested approach. A collection of 1200 dermoscopic images with clinical annotations was used to improve the models. ResNet-50 outperformed VGG16 in tests, with 93% accuracy and 96% AUC-ROC as opposed to 89% and 94%, respectively. These results emphasize how crucial model selection and preprocessing are to diagnostic performance. Ensemble methods, multi-class classification, explainability integration, and clinical validation will be investigated in order to facilitate the implementation of AI-assisted dermatological diagnostic tools. Full article
(This article belongs to the Special Issue Artificial Intelligence for Computer-Aided Detection in Biomedical Applications, 2nd Edition)
►▼ Show Figures

Figure 1

24 pages, 3453 KB  
Article
Role of Platelet-Rich Plasma Injection in Anterior Cruciate Ligament Reconstruction: A Meta-Analysis of Randomized Controlled Trials
by Ahmed Abdirahman Ibrahim, Michael Opoku, Abakar Mahamat Abdramane, Mingqing Fang, Xu Liu, Abdulraheem Mustapha, Yusheng Li, Wenfeng Xiao, Kai Zhang and Shuguang Liu
Bioengineering 2026, 13(4), 455; https://doi.org/10.3390/bioengineering13040455 - 13 Apr 2026
Viewed by 901
Abstract
Purpose: To critically evaluate the role or effect of platelet-rich plasma (PRP) in anterior cruciate ligament (ACL) reconstruction in terms of clinical and radiological outcomes. Method: We conducted a systematic search of PubMed, Embase, the Cochrane Library, and Web of Science to identify [...] Read more.
Purpose: To critically evaluate the role or effect of platelet-rich plasma (PRP) in anterior cruciate ligament (ACL) reconstruction in terms of clinical and radiological outcomes. Method: We conducted a systematic search of PubMed, Embase, the Cochrane Library, and Web of Science to identify relevant studies. Clinical outcomes included the Visual Analogue Scale (VAS), International Knee Documentation Committee (IKDC) subjective and objective evaluations, Lysholm score, Tegner score, anterior knee laxity, Knee Injury and Osteoarthritis Outcome Score (KOOS), Kujala score, Victorian Institute of Sport Assessment (VISA) scale, proprioception, isokinetic strength, and physical examination tests (anterior drawer, Lachman, and pivot-shift tests). Radiological outcomes encompassed measures obtained via magnetic resonance imaging (MRI), computed tomography (CT), X-ray, and ultrasound. Statistical significance was defined as a p value < 0.05, and all analyses were performed using R software (version 4.1.3). Results: A total of 23 studies, including 19 randomized controlled trials, met the inclusion criteria, encompassing 1072 patients overall. The meta-analysis showed significant differences between PRP group and non-PRP group with regard to VAS score at 6- and 12-month follow-up, Lysholm score at 6-month follow-up, and Tegner score at 6-month follow-up. Meta-regression showed that the two group differences in VAS score changed significantly with follow-up time (p < 0.01). In terms of radiological findings, about half of the assessments favored PRP to facilitate the graft maturation and integration at 6-month follow-up. Conclusions: PRP application in ACL reconstruction compared with non-PRP, may produce short-term but not long-term clinical outcomes such as VAS score, Lysholm score and Tegner score. While some short-term statistical differences exist, their magnitude and durability do not yet justify routine clinical adoption of PRP in ACL reconstruction. Larger samples and higher-quality studies are needed to support our results and further explore the advantages of PRP in other aspects. Level of evidence: Level II. Full article
(This article belongs to the Section Regenerative Engineering)
►▼ Show Figures

Figure 1

26 pages, 3302 KB  
Article
Comparison of Controller Logics for Automating Vasopressor Administration Using a Hardware-in-Loop Test Platform
by Michael D. Lopez, Jonathan Marrero Bermudez, David Berard, Lawrence Holland, Austin J. Ruiz, Jose M. Gonzalez, Sofia I. Hernandez Torres and Eric J. Snider
Bioengineering 2026, 13(4), 454; https://doi.org/10.3390/bioengineering13040454 - 13 Apr 2026
Viewed by 580
Abstract
Hemorrhagic shock remains one of the leading causes of preventable death for both civilian and military trauma. Fluid resuscitation is the primary treatment but requires constant monitoring, particularly for volume non-responsive patients susceptible to fluid overload, pulmonary edema, and other life-threatening conditions. To [...] Read more.
Hemorrhagic shock remains one of the leading causes of preventable death for both civilian and military trauma. Fluid resuscitation is the primary treatment but requires constant monitoring, particularly for volume non-responsive patients susceptible to fluid overload, pulmonary edema, and other life-threatening conditions. To overcome fluid non-responsiveness, vasoactive drugs or vasopressors can be necessary adjuvants to fluid therapy but require tedious titrations that can be difficult to manage during mass-casualty situations. This study developed and evaluated automated closed-loop vasopressor controllers for hemorrhage scenarios. Ten physiological closed-loop controller (PCLC) configurations with different underlying functionalities were tuned to be either more aggressive or conservative to reach the target mean arterial pressure. A hardware-in-loop test platform with fluid-pressure responsiveness, derived from animal data, tested each controller across three different starting pressure scenarios. The platform successfully differentiated controller designs based on performance metrics. While some configurations overshot the target and others could not reach the target pressure, strong-performing PCLCs consistently reached and maintained the target quickly. Three candidate PCLCs outperformed the rest and will be evaluated across wider scenarios to develop a robust controller design. This work accelerates PCLC-driven vasopressor administration development, providing a necessary fluid resuscitation adjuvant for precise hemodynamic management in hemorrhagic trauma. Full article
(This article belongs to the Section Biomedical Engineering and Biomaterials)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-111
Previous Issue
Next Issue
Back to TopTop