Computer Methods in Biomechanics and Biomedical Engineering最新文献_第2页

Depression EEG classification based on multi-scale convolutional transformer network. 基于多尺度卷积变压器网络的凹陷脑电分类。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-08 DOI: 10.1080/10255842.2025.2525975

Wan Chen, Yanping Cai, Aihua Li, Ke Jiang, Qisheng Yang, Xiao Zhong, Wei Zhang

{"title":"Depression EEG classification based on multi-scale convolutional transformer network.","authors":"Wan Chen, Yanping Cai, Aihua Li, Ke Jiang, Qisheng Yang, Xiao Zhong, Wei Zhang","doi":"10.1080/10255842.2025.2525975","DOIUrl":"https://doi.org/10.1080/10255842.2025.2525975","url":null,"abstract":"Depression electroencephalograph (EEG) classification based on machine learning is helpful for the auxiliary diagnosis of major depression disorder (MDD). Multi-channel EEG has abundant spatial information because EEG electrodes are distributed in different brain regions. However, existing methods arrange EEG features as feature vectors, which destroys the spatial structure of the features and may affect the model's performance. To improve the accuracy of MDD classification, we propose a novel EEG classification method for depression based on the brain topographic map and multi-scale convolutional transformer network (MCTNet). First, the power spectral density (PSD) features are extracted from EEG, and the one-dimensional feature vectors are converted into high-dimensional brain topographic maps according to the location information of EEG channels. Then, a multi-scale convolution with three parallel branches is designed to convert the brain topographic map into a deep feature map representation. Finally, image segmentation (IS) and the transformer encoder (TE) are used to learn the local and global features of the feature map, and the feature is input into the fully connected layer for classification. In addition, a joint loss function based on cross-entropy and center loss (CL) is designed to enable MCTNet to extract features with larger inter-class and smaller intra-class distances. Complete experimental verification is carried out on an open dataset. The accuracy, sensitivity and specificity of MCTNet are 97.24%, 97.20%, and 97.46%, respectively. The results show that the proposed method can achieve high-precision depression EEG classification and is superior to the state-of-the-art models.","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1-14"},"PeriodicalIF":1.7,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144585537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Four-gene-based risk score model from peripheral blood: enhancing diagnosis, prognosis, and immunotherapy response assessment in patients with lung adenocarcinoma. 基于外周血的四基因风险评分模型：增强肺腺癌患者的诊断、预后和免疫治疗反应评估

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-08 DOI: 10.1080/10255842.2025.2529518

Xiaohua Li, Guoxia Fu, Shijun Liao, Yu Wu, Lei Lei, Lian Liu, Yi Liao

引用次数: 0

Lateral connection convolutional neural networks for obstructive sleep apnea hypopnea classification. 侧连接卷积神经网络在阻塞性睡眠呼吸暂停低通气分类中的应用。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-06 DOI: 10.1080/10255842.2025.2524478

Junming Zhang, Yushuai Wang, Ruxian Yao, Jinfeng Gao, Haitao Wu

{"title":"Lateral connection convolutional neural networks for obstructive sleep apnea hypopnea classification.","authors":"Junming Zhang, Yushuai Wang, Ruxian Yao, Jinfeng Gao, Haitao Wu","doi":"10.1080/10255842.2025.2524478","DOIUrl":"https://doi.org/10.1080/10255842.2025.2524478","url":null,"abstract":"Despite the successful operation of convolutional neural networks (CNN) with obstructive sleep apnea hypopnea (OSAHS) classification, the interpretability of these models is poor. The limited capacity to understand models hinders the comprehension of end-users, including sleep specialists. At the same time, these models need labeled data; however, this is a time-consuming, labor-intensive, and costly process. Furthermore, the presence of lateral connections plays a crucial role in the field of visual neurobiology. However, up until now, there has been a lack of research on CNN that incorporate lateral connections. In light of this, we introduce a novel CNN architecture called the lateral connection CNN (LCCNN), which integrates the semantic arrangement of neurons to classify OSAHS. The LCCNN consists of several layers, including a convolution layer for extracting local features, a lateral connection layer for detecting salient wave features, a competition layer for updating filters in an unsupervised manner, and a pooling layer. The competition layer ensures that adjacent filters in each convolution layer have similar weight distribution, thus realizing the semantic arrangement of neurons in the LCCNN. We evaluate the performance of the proposed model using the University College Dublin database (UCD) and the Physionet Challenge database (PCD). The results show that the proposed model achieves high total accuracies of 97.3% (with a kappa coefficient of 0.9) on UCD and 95.6% (with a kappa coefficient of 0.83) on PCD. This work can serve as a foundation for future research on unsupervised deep learning models.","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1-13"},"PeriodicalIF":1.7,"publicationDate":"2025-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144568041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Limited effect of load reduction by changing the ski characteristics on the anterior cruciate ligament in the slip-catch injury mechanism in alpine skiing. 在高山滑雪滑抓损伤机制中，通过改变滑雪特性减少负荷对前交叉韧带的有限影响。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-05 DOI: 10.1080/10255842.2025.2527390

Shinsuke Yoshioka, Yusuke Ishige, Masahiro Harada

{"title":"Limited effect of load reduction by changing the ski characteristics on the anterior cruciate ligament in the slip-catch injury mechanism in alpine skiing.","authors":"Shinsuke Yoshioka, Yusuke Ishige, Masahiro Harada","doi":"10.1080/10255842.2025.2527390","DOIUrl":"https://doi.org/10.1080/10255842.2025.2527390","url":null,"abstract":"In competitive alpine skiers, anterior cruciate ligament (ACL) injury is the most common and severe injury, and the slip-catch mechanism is one of the main injury mechanisms. Much effort has been made to prevent injuries by limiting the aggressive characteristics of the ski. However, there is no clear evidence on the effectiveness of equipment regulations for ski competitions aimed at reducing injury rates. Therefore, this study aimed to clarify the relationship between ski aggressiveness and load on the ACL in the slip-catch mechanism. Forward dynamic simulations were conducted incorporating the kinematics of the actual skiing motions measured in the experiment. The actual skiing motion was measured under four different conditions with inertial sensors, which differed in ski type, course settings, and skier's level. The ski parameters used in the simulation were obtained by measuring the skis used in the experiment. The snow and body inertia parameters were obtained from previous studies. The sensitivities of ski characteristics to the load on the knee joint and ACL were generally low. The only significant sensitivity to the ACL force was the tail length; however, the load reduction effect was small. It is important to recognize that there is a severe limitation to the prevention of ACL injuries by limiting the ski aggressiveness. The results of this study indicate that improving the skier's motion (avoiding the knee extended position, and making the pressure on the skis more forward) and tactics (not catching the snow surface) are more effective measures for preventing ACL injury.","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1-16"},"PeriodicalIF":1.7,"publicationDate":"2025-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144568042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Construction of a novel prognostic model for pancreatic adenocarcinoma to predict prognosis and guide immunotherapy. 建立新的胰腺腺癌预后模型预测预后并指导免疫治疗。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-04 DOI: 10.1080/10255842.2025.2525979

Chaoqian Zhu, Peng Peng, Yuanguang Liu, Yichao Zhao, Ran Cheng, Yang Liu, Jun Yin

{"title":"Construction of a novel prognostic model for pancreatic adenocarcinoma to predict prognosis and guide immunotherapy.","authors":"Chaoqian Zhu, Peng Peng, Yuanguang Liu, Yichao Zhao, Ran Cheng, Yang Liu, Jun Yin","doi":"10.1080/10255842.2025.2525979","DOIUrl":"https://doi.org/10.1080/10255842.2025.2525979","url":null,"abstract":"Pancreatic adenocarcinoma (PAAD) remains one of the most lethal malignant tumors, with poor prognosis and limited treatment options. This study aims to explore the role of butyrate metabolism-related genes (BMRGs) in PAAD to improve diagnostic and prognostic strategies. The study analyzed PAAD based on transcriptomic and clinical data obtained from the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) databases. Through the construction of protein-protein interaction (PPI) networks and LASSO Cox regression, characteristic genes were selected to develop a risk model related to butyrate metabolism (BMRS). This model effectively divided patients into high BMRS and low BMRS groups. Kaplan-Meier (K-M) analysis showed a significant difference in overall survival rates between the two groups. ROC curves and nomograms including clinical features and BMRS demonstrated strong predictive capabilities. Functional enrichment analysis (including Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG)) revealed key pathways, such as pancreatic secretion and immune-related processes. Additionally, the two BMRS groups showed different immune cell infiltration patterns, and several potential therapeutic drugs were determined through drug sensitivity prediction. Co-expression network analysis further revealed 20 genes related to biological processes such as keratinization and nucleosome assembly. In summary, this study highlights the clinical significance of BMRGs in PAAD and provides new insights into risk stratification and potential targets for personalized treatment.","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1-18"},"PeriodicalIF":1.7,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144561865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mental workload recognition from EEG signals via semi-supervised autoencoders. 基于半监督自编码器的脑电信号精神负荷识别。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-04 DOI: 10.1080/10255842.2025.2523310

Qi Liu, Xu Jiang, Huanjie Wang, Jingjing Chen

引用次数: 0

A multi-objective optimization of degradable polymer vascular stents. 可降解聚合物血管支架的多目标优化。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-02 DOI: 10.1080/10255842.2025.2524477

Mingkai Liang, Ruiqi Zhang, Yuanming Gao, Li Shen, Lingsen You, Wentao Feng, Junbo Ge, Yubo Fan

引用次数: 0

Poroelastic modelling of brain tissue swelling and decompressive craniectomy treatment in ischaemic stroke. 缺血性脑卒中脑组织肿胀和减压开颅术治疗的透气弹性模型。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-01 Epub Date: 2024-03-10 DOI: 10.1080/10255842.2024.2326972

Aina Najwa Nadzri, Nik Abdullah Nik Mohamed, Stephen J Payne, Mohd Jamil Mohamed Mokhtarudin

{"title":"Poroelastic modelling of brain tissue swelling and decompressive craniectomy treatment in ischaemic stroke.","authors":"Aina Najwa Nadzri, Nik Abdullah Nik Mohamed, Stephen J Payne, Mohd Jamil Mohamed Mokhtarudin","doi":"10.1080/10255842.2024.2326972","DOIUrl":"10.1080/10255842.2024.2326972","url":null,"abstract":"Brain oedema or tissue swelling that develops after ischaemic stroke can cause detrimental effects, including brain herniation and increased intracranial pressure (ICP). These effects can be reduced by performing a decompressive craniectomy (DC) operation, in which a portion of the skull is removed to allow swollen brain tissue to expand outside the skull. In this study, a poroelastic model is used to investigate the effect of brain ischaemic infarct size and location on the severity of brain tissue swelling. Furthermore, the model will also be used to evaluate the effectiveness of DC surgery as a treatment for brain tissue swelling after ischaemia. The poroelastic model consists of two equations: one describing the elasticity of the brain tissue and the other describing the changes in the interstitial tissue pressure. The model is applied on an idealized brain geometry, and it is found that infarcts with radius larger than approximately 14 mm and located near the lateral ventricle produce worse brain midline shift, measured through lateral ventricle compression. Furthermore, the model is also able to show the positive effect of DC treatment in reducing the brain midline shift by allowing part of the brain tissue to expand through the skull opening. However, the model does not show a decrease in the interstitial pressure during DC treatment. Further improvement and validation could enhance the capability of the proposed poroelastic model in predicting the occurrence of brain tissue swelling and DC treatment post ischaemia.","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1489-1499"},"PeriodicalIF":1.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140094995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Finite element modeling of the free boundary effect on gyroid additively manufactured samples. 陀螺仪加成制造样品自由边界效应的有限元建模。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-01 Epub Date: 2024-03-12 DOI: 10.1080/10255842.2024.2326929

Elizabeth Mathey, Amanda Heimbrook, R D Carpenter, Cambre N Kelly, Ken Gall

{"title":"Finite element modeling of the free boundary effect on gyroid additively manufactured samples.","authors":"Elizabeth Mathey, Amanda Heimbrook, R D Carpenter, Cambre N Kelly, Ken Gall","doi":"10.1080/10255842.2024.2326929","DOIUrl":"10.1080/10255842.2024.2326929","url":null,"abstract":"There is a significant need for models that can capture the mechanical behavior of complex porous lattice architectures produced by 3D printing. The free boundary effect is an experimentally observed behavior of lattice architectures including the gyroid triply periodic minimal surface where the number of unit cell repeats has been shown to influence the mechanical performance of the lattice. The purpose of this study is to use finite element modeling to investigate how architecture porosity, unit cell size, and sample size dictate mechanical behavior. Samples with varying porosity and increasing number of unit cells (relative to sample size) were modeled under an axial compressive load to determine the effective modulus. The finite element model captured the free boundary effect and captured experimental trends in the structure's modulus. The findings of this study show that samples with higher porosity are more susceptible to the impact of the free boundary effect and in some samples, the modulus can be 20% smaller in samples with smaller numbers of unit cell repeats within a given sample boundary. The outcomes from this study provide a deeper understanding of the gyroid structure and the implications of design choices including porosity, unit cell size, and overall sample size.","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1477-1488"},"PeriodicalIF":1.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140102842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A framework for studying oxygen and nitric oxide transport in unstable flow through a patient-based abdominal aortic aneurysm model. 通过基于患者的腹主动脉瘤模型研究不稳定血流中氧和一氧化氮运输的框架。

IF 1.7 4区医学

Computer Methods in Biomechanics and Biomedical Engineering Pub Date : 2025-07-01 Epub Date: 2025-06-02 DOI: 10.1080/10255842.2025.2510363

Robert A Peattie, Sudharsan Madhavan, Brian Fix, Robert J Fisher, Simone Melchionna, Erica Cherry Kemmerling

{"title":"A framework for studying oxygen and nitric oxide transport in unstable flow through a patient-based abdominal aortic aneurysm model.","authors":"Robert A Peattie, Sudharsan Madhavan, Brian Fix, Robert J Fisher, Simone Melchionna, Erica Cherry Kemmerling","doi":"10.1080/10255842.2025.2510363","DOIUrl":"10.1080/10255842.2025.2510363","url":null,"abstract":"Abdominal Aortic Aneurysm (AAA) is a potentially life-threatening permanent, localized dilation in the abdominal aorta wall. Previous studies have suggested that the presence of a layer of intraluminal thrombus (ILT), which is found adhering to the wall inner surface in 80-90% of all AAAs, is associated with a significant decrease in the oxygen (O2) level within the wall. However, although turbulence normally has a major influence on solute transport, its effect on this decrease has not yet been investigated. In the present study, a computational technique for evaluating wall O2 and NO concentration distributions in a patient-based model with separate lumen, thrombus, and wall layers is developed. Flow in this model was evaluated by Direct Numerical Simulation, using pathophysiologically realistic flow and transport conditions accounting for instability and turbulence development. Concentration distributions were determined by solution of advection-diffusion-reaction equations appropriate to each layer. Normalized O2 concentration at the wall inner surface decreased as ILT thickness increased up to 0.4 cm but then plateaued at ∼0.7 (normalized). Contrary to expectations, turbulence had minimal impact on transport, which was consistent with calculation of an effective Damkohler number for the AAA, indicating that solute levels were governed by reaction-limited rather than transport-limited dynamics. Since NO production was driven by shear stress at the lumen-wall interface, NO was absent in ILT-covered regions, creating spatial disparities in wall NO concentration between thrombus-covered and clear regions of the wall surface. The results suggest that ILT induces wall hypoxia and impairs NO-mediated vascular homeostasis.","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1500-1519"},"PeriodicalIF":1.7,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0