Bioengineering最新文献

筛选
英文 中文
Biosensor-Integrated Tibial Components in Total Knee Arthroplasty: A Narrative Review of Innovations, Challenges, and Translational Frontiers. 全膝关节置换术中生物传感器集成胫骨组件:创新,挑战和翻译前沿的叙述回顾。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-17 DOI: 10.3390/bioengineering12090988
Ahmed Nadeem-Tariq, Christopher J Fang, Jeffrey Lucas Hii, Karen Nelson
{"title":"Biosensor-Integrated Tibial Components in Total Knee Arthroplasty: A Narrative Review of Innovations, Challenges, and Translational Frontiers.","authors":"Ahmed Nadeem-Tariq, Christopher J Fang, Jeffrey Lucas Hii, Karen Nelson","doi":"10.3390/bioengineering12090988","DOIUrl":"10.3390/bioengineering12090988","url":null,"abstract":"<p><strong>Background: </strong>The incorporation of biosensors into orthopedic implants, particularly tibial components in total knee arthroplasty (TKA), marks a new era in personalized joint replacement. These smart systems aim to provide real-time physiological and mechanical data, enabling dynamic postoperative monitoring and enhanced surgical precision.</p><p><strong>Objective: </strong>This narrative review synthesizes the current landscape of electrochemical biosensor-embedded tibial implants in TKA, exploring technical mechanisms, clinical applications, challenges, and future directions for translation into clinical practice.</p><p><strong>Methods: </strong>A comprehensive literature review was conducted across PubMed and Google Scholar. Articles were thematically categorized into technology design, integration strategies, preclinical and clinical evidence, regulatory frameworks, ethical considerations, and strategic recommendations. Findings were synthesized narratively and organized to support forward-looking system design.</p><p><strong>Results: </strong>Smart tibial implants have demonstrated feasibility in both bench and early clinical settings. Key advances include pressure-sensing intraoperative tools, inertial measurement units for remote gait tracking, and chemical biosensors for infection surveillance. However, the field remains limited by biological encapsulation, signal degradation, regulatory uncertainty, and data privacy challenges. Interdisciplinary design, standardized testing, translational funding, and ethical oversight are essential to scaling these innovations.</p><p><strong>Conclusions: </strong>Biosensor-enabled tibial components represent a promising convergence of orthopedics, electronics, and data science. By addressing the technological, biological, regulatory, and ethical gaps outlined herein, this field can transition from prototype to widespread clinical reality-offering new precision in arthroplasty care.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467652/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Linking a Deep Learning Model for Concussion Classification with Reorganization of Large-Scale Brain Networks in Female Youth. 将女性青少年脑震荡分类的深度学习模型与大规模脑网络重组联系起来。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-17 DOI: 10.3390/bioengineering12090986
Julianne McLeod, Karun Thanjavur, Sahar Sattari, Arif Babul, D T Hristopulos, Naznin Virji-Babul
{"title":"Linking a Deep Learning Model for Concussion Classification with Reorganization of Large-Scale Brain Networks in Female Youth.","authors":"Julianne McLeod, Karun Thanjavur, Sahar Sattari, Arif Babul, D T Hristopulos, Naznin Virji-Babul","doi":"10.3390/bioengineering12090986","DOIUrl":"10.3390/bioengineering12090986","url":null,"abstract":"<p><p>Concussion, or mild traumatic brain injury, is a significant public health challenge, with females experiencing high rates and prolonged symptoms. Reliable and objective tools for early diagnosis are critically needed, particularly in pediatric populations, where subjective symptom reporting can be inconsistent and neurodevelopmental factors may influence presentation. Five minutes of resting-state (RS) EEG data were collected from non-concussed and concussed females between 15 and 24 years of age. We first applied a deep learning approach to classify concussion directly from raw, RS electroencephalography (EEG) data. A long short-term memory (LSTM) recurrent neural network trained on the raw data achieved 84.2% accuracy and an ensemble median area under the receiver operating characteristic curve (AUC) of 0.904. To complement these results, we examined causal connectivity at the source level using information flow rate to explore potential network-level changes associated with concussion. Effective connectivity in the non-concussed cohort was characterized by a symmetric pattern along the central-parietal midline; in contrast, the concussed group showed a more posterior and left-lateralized pattern. These spatial distribution changes were accompanied by significantly higher connection magnitudes in the concussed group (<i>p</i> < 0.001). While these connectivity changes may not directly drive classification, they provide evidence of large-scale brain reorganization following concussion. Together, our results suggest that deep learning models can detect concussion with high accuracy, while connectivity analyses may offer complementary mechanistic insights. Future work with larger datasets is necessary to refine the model specificity, explore subgroup differences related to hormone cycle changes and symptoms, and incorporate data across different sports.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467992/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An Innovative Interactive Narrative Persona (INP) Approach for Virtual Reality-Based Dementia Tour Design (VDT) in Rehabilitation Contexts. 一种基于虚拟现实的康复背景下痴呆之旅设计(VDT)的创新互动叙事角色(INP)方法。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-17 DOI: 10.3390/bioengineering12090987
Yuk Ming Tang, Suet Yi Tse, Hoi Sze Chan, Ho Tung Yip, Hei Tung Cheung, Mohammed Woyeso Geda
{"title":"An Innovative Interactive Narrative Persona (INP) Approach for Virtual Reality-Based Dementia Tour Design (VDT) in Rehabilitation Contexts.","authors":"Yuk Ming Tang, Suet Yi Tse, Hoi Sze Chan, Ho Tung Yip, Hei Tung Cheung, Mohammed Woyeso Geda","doi":"10.3390/bioengineering12090987","DOIUrl":"10.3390/bioengineering12090987","url":null,"abstract":"<p><p>The rising prevalence of dementia has raised significant public concern globally. However, the level of understanding and assistance concerning people with dementia remains limited. This study investigates the impact of virtual reality (VR) on enhancing public awareness and empathy toward dementia. We developed a Virtual Dementia Tour (VDT) designed to simulate the cognitive and sensory impairments associated with dementia while incorporating interactive decision-making elements. A total of 80 adults aged 18 years or older, residing in Hong Kong and with no personal or close family history of dementia or caregiving experience, were recruited for the study. Quantitative data were analyzed using paired and independent samples <i>t</i>-tests to assess the changes in the Dementia Attitudes Scale (DAS) scores before and after the intervention. The results indicate that the baseline awareness and understanding of dementia were low in both groups. However, participants who experienced the VDT showed significantly greater improvements in knowledge and empathy compared to the control group. The findings suggest that VR interventions can effectively promote dementia awareness, reduce stigma, and contribute to the development of dementia-friendly societies. This study contributes to the growing body of evidence supporting the use of VR as an innovative tool for advancing social awareness and empathy in public health education.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12466994/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Development of the Direct Deuteration Method for Amino Acids and Characterization of Deuterated Tryptophan. 氨基酸直接氘化法的发展及氘化色氨酸的表征。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-16 DOI: 10.3390/bioengineering12090981
Chie Shibazaki, Haruki Sugiyama, Misaki Ueda, Takayuki Oku, Motoyasu Adachi, Zoë Fisher, Kazuhiro Akutsu-Suyama
{"title":"Development of the Direct Deuteration Method for Amino Acids and Characterization of Deuterated Tryptophan.","authors":"Chie Shibazaki, Haruki Sugiyama, Misaki Ueda, Takayuki Oku, Motoyasu Adachi, Zoë Fisher, Kazuhiro Akutsu-Suyama","doi":"10.3390/bioengineering12090981","DOIUrl":"10.3390/bioengineering12090981","url":null,"abstract":"<p><p>Proteins and peptides are vital biomolecules, and deuterated amino acids are increasingly applied in areas such as drug discovery, metabolic tracing, and neutron scattering studies. In this study, we performed deuteration on all 20 proteinogenic amino acids, including their side chains, and established efficient methods for 13 amino acids. Using a Pt/C-catalyzed hydrogen-deuterium exchange reaction, the reaction parameters were optimized to achieve the selective and stable incorporation of deuterium. In addition, the resulting deuterated compounds, focusing on tryptophan, were characterized in order to assess their physicochemical properties. Because the deuteration reaction caused significant racemization of amino acids, deuterated D/L-tryptophan was isolated using a chiral separation method. Deuterated tryptophan characterization studies confirmed that the photostability was markedly enhanced by deuteration, whereas the acid stability showed no clear isotopic effect. The X-ray crystal structure analyses revealed minimal changes upon the hydrogen-to-deuterium substitution. These results provide a robust platform for the supply of deuterated amino acids, facilitating their application in drug development, structural analysis, and creation of advanced functional biomaterials.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467387/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ocular Biometry and Refractive Prediction in Short Eyes: A Comparison of Two Swept-Source Optical Coherence Tomography-Based Biometers. 眼生物测量和近视屈光预测:两种扫描源光学相干层析生物计的比较。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-16 DOI: 10.3390/bioengineering12090983
Jiyun Seong, Sang Beom Han
{"title":"Ocular Biometry and Refractive Prediction in Short Eyes: A Comparison of Two Swept-Source Optical Coherence Tomography-Based Biometers.","authors":"Jiyun Seong, Sang Beom Han","doi":"10.3390/bioengineering12090983","DOIUrl":"10.3390/bioengineering12090983","url":null,"abstract":"<p><p><b><i>Purpose:</i></b> To compare the performance of two swept-source optical coherence tomography-based biometers in the measurement of ocular biometry and the prediction of postoperative refractive errors in eyes with short axial length (AL). <b><i>Methods:</i></b> A total of 48 eyes from 29 patients with AL ≤ 22 mm were included. AL, anterior chamber depth (ACD), keratometry (K), and lens thickness (LT) measured using the IOLMaster<sup>®</sup> 700 and ARGOS<sup>®</sup> before cataract surgery were compared. The refractive error prediction accuracy of the two devices was also compared. <b><i>Results:</i></b> This study included four men (7 eyes) and 25 women (41 eyes), with an average age of 70.7 ± 8.1 years (mean ± SD; range, 47-82 years). The two devices demonstrated good agreement in measurements of ocular biometry with high intraclass correlation coefficients (AL = 0.975; ACD = 0.957; K = 0.988; LT = 0.994). However, AL and ACD were significantly shorter when measured with the IOLMaster<sup>®</sup> 700 compared to the ARGOS<sup>®</sup> (<i>p</i> < 0.001 for both). There was no significant difference in mean absolute prediction errors between the two devices (<i>p</i> = 0.423). The IOLMaster<sup>®</sup> 700 showed a significantly lower mean prediction error than the ARGOS<sup>®</sup> (+0.12 ± 0.39 diopters vs. +0.20 ± 0.39 diopters, <i>p</i> = 0.006), although the difference was of limited clinical relevance. There were no significant differences in the percentages of eyes within ± 0.50 D (77.1% vs. 75.0%, <i>p</i> = 0.811) and ± 1.00 D (100% vs. 97.9%, <i>p</i> = 0.315) of the predicted refractive error. <b><i>Conclusions:</i></b> Although IOLMaster<sup>®</sup> 700 and ARGOS<sup>®</sup> showed good agreements in eyes with short AL, significant differences were observed in the measurements of AL and ACD. Both devices demonstrated good efficacy and comparable performance in predicting postoperative refractive errors.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467928/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The Influence of Reaming Velocity During Preparation of the Femoral Canal-An In Vitro Analysis of Two Straight Femoral Revision Stems with a Fluted Tapered Design. 股骨管预备过程中扩孔速度的影响——两种带凹槽锥形设计的直股翻修管的体外分析。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-16 DOI: 10.3390/bioengineering12090984
Oliver E Bischel, Jörn B Seeger, Matthias K Jung, Stefan Dörfler, Arnold J Höppchen, Alexander Jahnke, Eike Jakubowitz
{"title":"The Influence of Reaming Velocity During Preparation of the Femoral Canal-An In Vitro Analysis of Two Straight Femoral Revision Stems with a Fluted Tapered Design.","authors":"Oliver E Bischel, Jörn B Seeger, Matthias K Jung, Stefan Dörfler, Arnold J Höppchen, Alexander Jahnke, Eike Jakubowitz","doi":"10.3390/bioengineering12090984","DOIUrl":"10.3390/bioengineering12090984","url":null,"abstract":"<p><p><i>Background:</i> The use of tapered fluted revision stems has been shown to be reliable and safe. Primary stability is mandatory for a long-lasting fixation between bone and a prosthesis. Nevertheless, aseptic loosening due to insufficient primary stability occurs and may be related to technically improper preparation of the femoral canal. Instructions of manufacturers are heterogeneous regarding preparation of implant beds. <i>Questions/Purposes:</i> Does speed or the design of the reamer influence the accuracy of the implant bed and, consecutively, primary stability? <i>Materials and Methods:</i> A test foam with an elastic moduli and pressure resistance similar to that of cancellous bone was used. The medullary canal was prepared with the use of reamers of two different straight and tapered femoral revision devices. Three different rotational speeds were used for preparation. After preparation, primary stability was measured and fixating characteristics were derived. <i>Results:</i> Sufficient primary stability was achievable by all three preparation methods but fixating characteristics were different. Significantly higher micro-motions were detected near the tip of the prosthesis compared to those at all more proximal measuring points. Reaming with high velocity resulted in significantly higher micro-motions compared to that with mid- or low-speed burring. <i>Conclusions:</i> Different preparation methods may be one explanation for the range of reported survivorship data of the two devices with aseptic loosening as the end point. The precision of the implant bed and fixating characteristics were best after reaming with lower velocity. Superior but not significantly better fixation characteristics were achieved with the monobloc stem compared to those with the modular device.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467323/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Anterior Mandibular Displacement in Growing Rats Enhances Growth-A 3D Analysis. 生长大鼠下颌前移位促进生长- a三维分析。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-16 DOI: 10.3390/bioengineering12090982
Efstratios Ferdianakis, Ioannis Lyros, Demetrios Halazonetis, Georgios Kanavakis, Paula Perlea, Zafeiroula Yfanti, Konstantina-Eleni Alexiou, Dafni Doukaki, Apostolos I Tsolakis
{"title":"Anterior Mandibular Displacement in Growing Rats Enhances Growth-A 3D Analysis.","authors":"Efstratios Ferdianakis, Ioannis Lyros, Demetrios Halazonetis, Georgios Kanavakis, Paula Perlea, Zafeiroula Yfanti, Konstantina-Eleni Alexiou, Dafni Doukaki, Apostolos I Tsolakis","doi":"10.3390/bioengineering12090982","DOIUrl":"10.3390/bioengineering12090982","url":null,"abstract":"<p><p>One of the most common malocclusions encountered in everyday practice by orthodontists is skeletal Class II malocclusion, namely a protrusion of the maxilla, a retrusion of the mandible or a combination of both. To correct it, many clinicians use functional devices that guide the mandible into a more forward position. This stimulates bone growth, correcting the skeletal discrepancy. Controversy exists as to whether these appliances accelerate the growth rate, helping the mandible reach its final size earlier, or whether the growth of the mandible is observed as a positive response to the stimuli. This study examined whether the protrusion of the mandible in rats accelerates the growth rate or increases the overall growth of the mandible in the long run. Relapse was also assessed by removing the appliance prior to the end of the experiment. Seventy-two four-week-old Wistar rats were used. The treatment group, which consisted of 36 rats, had a device fitted on their upper incisors that led to a protrusion of their mandible. The device, a bite-jumping appliance, consisted of an iron-cast inclined plane and was fitted for 24 h a day, inducing a 3.5 mm anterior protrusion and 3 mm inferior displacement of the mandible. The control group consisted of 36 rats that were fed the same soft diet as the treatment group. Both groups were divided into three subgroups. The first was sacrificed 30 days after the onset of the experiment, the second at 60 days, and the last subgroup had the appliance removed for 30 days and was sacrificed 90 days after the onset of the experiment. At the beginning of the experiment, as well as at each time interval prior to the sacrifice of the animals, the appliances were removed, and cone beam-computed tomography was performed on every animal. Linear measurements were made on each 3D scan, measuring the growth of the mandible. Measurements of mandibular growth were higher compared to the control group. For instance, Gonion-Menton was 1.18 mm higher on month 2 compared to month 1 in the control group, whereas the same measurement marked a 1.82 mm difference in the experimental group. Condylion-Menton on the same intervals marked a 0.84 mm difference in the control, whereas a 1.35 mm difference was noted in the experimental group. Given the results, true mandibular growth is achieved using functional appliances for Class II malocclusion correction in rats.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12466957/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Revisiting the Mechanical Work-Energy Framework in Dynamic Biomechanical Systems. 再论动态生物力学系统中的机械功-能框架。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-15 DOI: 10.3390/bioengineering12090977
Donglu Shi
{"title":"Revisiting the Mechanical Work-Energy Framework in Dynamic Biomechanical Systems.","authors":"Donglu Shi","doi":"10.3390/bioengineering12090977","DOIUrl":"10.3390/bioengineering12090977","url":null,"abstract":"<p><p>The classical definition of mechanical work, W = F × D, assumes that work depends solely on force magnitude and displacement, independent of loading rate. However, biological tissues exhibit inherent rate sensitivity-muscles demonstrate velocity-dependent force generation governed by Hill's force-velocity relationship, while connective tissues and joints show load-rate-dependent stiffness and injury thresholds. These rate effects profoundly influence mechanical work, energy dissipation, and functional outcomes. In this work, we revisit the work-energy framework within biomechanics and biomaterials contexts, combining theoretical models, simulations, and a proposed rate-matched nano-bio indentation experiment to quantify how loading rate modulates energy partitioning between recoverable elastic storage and irreversible viscous dissipation. Our analyses span muscle contraction, viscoelastic tissue mechanics, and nanoparticle-membrane interactions, revealing that rapid loading markedly increases viscous dissipation and total mechanical work, even when peak force and displacement remain constant. We demonstrate that classical quasi-static formulations underestimate energy costs and tissue stresses by neglecting temporal dynamics and nonlinear material responses. Our multi-physics experimental-simulation platform bridges this gap, enabling controlled investigation of rate-dependent biomechanical phenomena at the nano-bio interface. These insights inform biomaterials design by emphasizing rate-matching viscoelastic properties to native tissues and guide experimental biomechanics toward capturing full dynamic histories. This unified framework advances understanding of rate-dependent mechanical work, improving predictive modeling, optimizing therapeutic delivery, and enhancing design in sports science, orthopedics, rehabilitation, and nanomedicine.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467073/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
PHSP-Net: Personalized Habitat-Aware Deep Learning for Multi-Center Glioblastoma Survival Prediction Using Multiparametric MRI. php - net:使用多参数MRI进行多中心胶质母细胞瘤生存预测的个性化栖息地感知深度学习。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-15 DOI: 10.3390/bioengineering12090978
Tianci Liu, Yao Zheng, Chengwei Chen, Jie Wei, Dong Huang, Yuefei Feng, Yang Liu
{"title":"PHSP-Net: Personalized Habitat-Aware Deep Learning for Multi-Center Glioblastoma Survival Prediction Using Multiparametric MRI.","authors":"Tianci Liu, Yao Zheng, Chengwei Chen, Jie Wei, Dong Huang, Yuefei Feng, Yang Liu","doi":"10.3390/bioengineering12090978","DOIUrl":"10.3390/bioengineering12090978","url":null,"abstract":"<p><strong>Background: </strong>Glioblastoma (GBM) is a highly aggressive and heterogeneous primary malignancy of the central nervous system, with a median overall survival (OS) of approximately 15 months. Achieving accurate and generalizable OS prediction across multi-center settings is essential for clinical application.</p><p><strong>Methods: </strong>We propose a Personalized Habitat-aware Survival Prediction Network (PHSP-Net) that integrates multiparametric MRI with an adaptive habitat partitioning strategy. The network combines deep convolutional feature extraction and interpretable visualization modules to perform patient-specific subregional segmentation and survival prediction. A total of 1084 patients with histologically confirmed WHO grade IV GBM from four centers (UPENN-GBM, UCSF-PDGM, LUMIERE and TCGA-GBM) were included. PHSP-Net was compared with conventional radiomics, habitat imaging models and ResNet10, with independent validation on two external cohorts.</p><p><strong>Results: </strong>PHSP-Net achieved an AUROC of 0.795 (95% CI: 0.731-0.852) in the internal validation set, and 0.707 and 0.726 in the LUMIERE and TCGA-GBM external test sets, respectively-outperforming both comparison models. Kaplan-Meier analysis revealed significant OS differences between predicted high- and low-risk groups (log-rank <i>p</i> < 0.05). Visualization analysis indicated that necrotic-region habitats were key prognostic indicators.</p><p><strong>Conclusions: </strong>PHSP-Net demonstrates high predictive accuracy, robust cross-center generalization and improved interpretability in multi-center GBM cohorts. By enabling personalized habitat visualization, it offers a promising non-invasive tool for prognostic assessment and individualized clinical decision making in GBM.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467337/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
From Anatomy to Genomics Using a Multi-Task Deep Learning Approach for Comprehensive Glioma Profiling. 从解剖学到基因组学,使用多任务深度学习方法进行全面的胶质瘤分析。
IF 3.7 3区 医学
Bioengineering Pub Date : 2025-09-15 DOI: 10.3390/bioengineering12090979
Akmalbek Abdusalomov, Sabina Umirzakova, Obidjon Bekmirzaev, Adilbek Dauletov, Abror Buriboev, Alpamis Kutlimuratov, Akhram Nishanov, Rashid Nasimov, Ryumduck Oh
{"title":"From Anatomy to Genomics Using a Multi-Task Deep Learning Approach for Comprehensive Glioma Profiling.","authors":"Akmalbek Abdusalomov, Sabina Umirzakova, Obidjon Bekmirzaev, Adilbek Dauletov, Abror Buriboev, Alpamis Kutlimuratov, Akhram Nishanov, Rashid Nasimov, Ryumduck Oh","doi":"10.3390/bioengineering12090979","DOIUrl":"10.3390/bioengineering12090979","url":null,"abstract":"<p><strong>Background: </strong>Gliomas are among the most complex and lethal primary brain tumors, necessitating precise evaluation of both anatomical subregions and molecular alterations for effective clinical management.</p><p><strong>Methods: </strong>To find a solution to the disconnected nature of current bioimage analysis pipelines, where anatomical segmentation based on MRI and molecular biomarker prediction are done as separate tasks, we use here Molecular-Genomic and Multi-Task (MGMT-Net), a one deep learning scheme that carries out the task of the multi-modal MRI data without any conversion. MGMT-Net incorporates a novel Cross-Modality Attention Fusion (CMAF) module that dynamically integrates diverse imaging sequences and pairs them with a hybrid Transformer-Convolutional Neural Network (CNN) encoder to capture both global context and local anatomical detail. This architecture supports dual-task decoders, enabling concurrent voxel-wise tumor delineation and subject-level classification of key genomic markers, including the IDH gene mutation, the 1p/19q co-deletion, and the TERT gene promoter mutation.</p><p><strong>Results: </strong>Extensive validation on the Brain Tumor Segmentation (BraTS 2024) dataset and the combined Cancer Genome Atlas/Erasmus Glioma Database (TCGA/EGD) datasets demonstrated high segmentation accuracy and robust biomarker classification performance, with strong generalizability across external institutional cohorts. Ablation studies further confirmed the importance of each architectural component in achieving overall robustness.</p><p><strong>Conclusions: </strong>MGMT-Net presents a scalable and clinically relevant solution that bridges radiological imaging and genomic insights, potentially reducing diagnostic latency and enhancing precision in neuro-oncology decision-making. By integrating spatial and genetic analysis within a single model, this work represents a significant step toward comprehensive, AI-driven glioma assessment.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 9","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12467930/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145172734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信