Medical & Biological Engineering & Computing最新文献_第4页

Study on the regulatory effect of magnetic vestibular stimulation on visually induced motion sickness. 前庭磁刺激对视动病调节作用的研究。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-04 DOI: 10.1007/s11517-026-03666-1

Yuehua Geng, Xinlei Li, Yongjian Li, Xiang Zhai, Guizhi Xu

{"title":"Study on the regulatory effect of magnetic vestibular stimulation on visually induced motion sickness.","authors":"Yuehua Geng, Xinlei Li, Yongjian Li, Xiang Zhai, Guizhi Xu","doi":"10.1007/s11517-026-03666-1","DOIUrl":"https://doi.org/10.1007/s11517-026-03666-1","url":null,"abstract":"Visually induced motion sickness (VIMS) is a common adverse effect of virtual reality (VR). Magnetic vestibular stimulation (MVS) may modulate vestibular function, but its effect on VIMS remains unclear. This study examined whether different MVS intensities were associated with changes in VIMS symptoms and resting-state EEG network characteristics in healthy participants exposed to VR. Twenty healthy young adults completed five repeated-measures sessions: normal/non-VR, VR-only, and VR combined with MVS at 90%, 100%, and 110% of individual resting motor threshold (rMT). VIMS symptoms were assessed using the Simulator Sickness Questionnaire (SSQ) before and after each session. Resting-state EEG was recorded after each session, and brain functional network parameters were calculated across frequency bands. SSQ total and subscale scores differed significantly across sessions. Compared with VR alone, the 110% rMT condition showed a more favorable SSQ symptom profile, whereas 90% rMT MVS was associated with symptom aggravation. EEG network analysis showed exploratory session-related differences across multiple frequency bands, with the 110% rMT condition generally showing a pattern closer to baseline. In this study, higher-intensity MVS was associated with reduced VIMS symptoms, whereas lower-intensity MVS may worsen symptoms. These findings should be confirmed in larger studies.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148892342","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

Analysis of EEG microstate transition patterns and multi-instance learning-based recognition model for depression. 抑郁症脑电微态转换模式分析及基于多实例学习的识别模型。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-03 DOI: 10.1007/s11517-026-03662-5

Wanxin Zhang, Wenjie Li, Xuemei Fan, Suhong Wang, Ling Zou

{"title":"Analysis of EEG microstate transition patterns and multi-instance learning-based recognition model for depression.","authors":"Wanxin Zhang, Wenjie Li, Xuemei Fan, Suhong Wang, Ling Zou","doi":"10.1007/s11517-026-03662-5","DOIUrl":"https://doi.org/10.1007/s11517-026-03662-5","url":null,"abstract":"Accurate identification of major depressive disorder (MDD) and characterization of abnormal higher-order brain-state transitions remain important in electroencephalography (EEG)-based depression research. Although EEG microstate analysis provides a promising high-temporal-resolution tool for probing abnormal brain dynamics, most existing studies focus on static microstate parameters and may overlook higher-order transition structure embedded in microstate sequences. To address this issue, we proposed a rule-driven microstate sequence analysis framework for EEG-based depression recognition. Specifically, the RuleGrowth algorithm was used to mine discriminative microstate transition rules, which were incorporated into an attention-based multiple instance learning model for classification. The proposed method outperformed conventional approaches based on static microstate features on both datasets, achieving accuracy, F1-score, and area under the curve (AUC) values of 96.67%, 94.12%, and 97.23% on the multi-modal open dataset for mental disorder analysis (MODMA) dataset, and 92.67%, 92.78%, and 94.50% on the self-collected dataset. In addition, both datasets showed significant group differences in higher-order transition patterns after false discovery rate (FDR) correction ([Formula: see text]), with 7 and 13 significant rules identified, respectively, and the C→D→B and A→D→B rules consistently showing higher confidence in the MDD group than in healthy controls across both datasets. These findings indicate that MDD is associated with disrupted higher-order brain-state switching dynamics and support the utility of rule-based microstate representations for EEG-based depression analysis.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148889002","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

Hierarchical contrastive learning from GP-recorded and eGFR labels for CKD staging. 从gp记录和eGFR标签中分级对比学习CKD分期。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-03 DOI: 10.1007/s11517-026-03668-z

Ali Guran, Avishek Siris, Gary K L Tam, James Chess, Xianghua Xie

{"title":"Hierarchical contrastive learning from GP-recorded and eGFR labels for CKD staging.","authors":"Ali Guran, Avishek Siris, Gary K L Tam, James Chess, Xianghua Xie","doi":"10.1007/s11517-026-03668-z","DOIUrl":"https://doi.org/10.1007/s11517-026-03668-z","url":null,"abstract":"Chronic kidney disease staging from longitudinal clinical records is challenging because routinely recorded GP stage labels are scarce, whereas rule-based eGFR labels are more abundant but may not capture the broader clinical context reflected in primary-care coding. This study proposes a hierarchical contrastive learning framework for CKD staging under heterogeneous supervision, designed to maximise the use of available data by leveraging both scarce GP annotations and abundant rule-based labels, which provide complementary but partially inconsistent information. Rather than treating these supervision sources as fully consistent or conflicting, the proposed approach models graded levels of agreement and incorporates this structure into a contrastive objective. This encourages clinically concordant cases to form compact representations while progressively separating increasingly discordant cases, yielding a structured and clinically meaningful embedding space. The framework is extensively evaluated across multiple neural architectures for longitudinal CKD modelling, including recurrent, convolutional, temporal convolutional, Transformer-based, and hybrid models. Results show consistent improvements over classification-only and binary contrastive baselines, with the best performance achieved using a TCN+Transformer backbone. These findings show that structured contrastive supervision can effectively exploit complementary information from clinician-annotated and rule-based labels and provide a practical framework for longitudinal disease modelling, with potential applicability beyond CKD.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148889009","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 deep learning method for preterm birth prediction using wavelet representations and auxiliary features from electrohysterogram. 一种利用小波表示和子宫电图辅助特征进行早产预测的深度学习方法。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-02 DOI: 10.1007/s11517-026-03602-3

Xinliang Wen, Shengnan Zhuan, Xuehan Gao, Lai Jiang, Xu Zhang

{"title":"A deep learning method for preterm birth prediction using wavelet representations and auxiliary features from electrohysterogram.","authors":"Xinliang Wen, Shengnan Zhuan, Xuehan Gao, Lai Jiang, Xu Zhang","doi":"10.1007/s11517-026-03602-3","DOIUrl":"https://doi.org/10.1007/s11517-026-03602-3","url":null,"abstract":"Electrohysterogram (EHG) has been reported as promising way of predicting preterm birth, often relying on conventional machine learning approaches. However, the EHG modeling by deep learning has not been sufficiently investigated yet, probably due to both scarcity and complexity of the EHG data. To address these limitations, we propose CWT-AuxNet, an end-to-end deep learning method for preterm birth prediction with improved capability of learning discriminative patterns directly from raw EHG signals. In our method, continuous wavelet transform (CWT) is used to provide multiscale time-frequency representations of EHG data; an auxiliary feature termed peak amplitude (PA) is employed to further enhance discriminative capacity; and a cost-sensitive function with focal loss is designed during model training to handle severe data imbalance between term and preterm classes. Our CWT-AuxNet model is designed in a multibranch convolutional architecture enabling effective feature extraction and producing fine-grained window-level predictions. These window-level predictions are further aggregated using a user-level decision strategy to make individualized decisions regarding abnormalities and preterm risk during inference. Experimental results demonstrate that CWT-AuxNet consistently outperforms both traditional and deep learning baselines, achieving AUCs of 0.741 at the window level and 0.932 at the user level. Our study indicates the effectiveness of time-frequency deep representation learning and supports the potential of CWT-AuxNet as a promising framework for noninvasive preterm birth prediction.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148875817","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

Neighbor-constrained attention for multiple instance learning in whole-slide histopathology. 全切片组织病理学中多实例学习的邻域约束注意。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-01 DOI: 10.1007/s11517-026-03627-8

Mingze Li, Wei Li

{"title":"Neighbor-constrained attention for multiple instance learning in whole-slide histopathology.","authors":"Mingze Li, Wei Li","doi":"10.1007/s11517-026-03627-8","DOIUrl":"https://doi.org/10.1007/s11517-026-03627-8","url":null,"abstract":"Whole-slide image (WSI) classification is commonly formulated as multiple instance learning (MIL) with only slide-level labels, yet diagnostically relevant evidence is sparse and spatially organized. A persistent challenge is the spatial context dilemma: spatially agnostic MIL may over-attend isolated artifacts, whereas naive global context injection may oversmooth focal lesions or mix unrelated regions. We propose Neighbor-Constrained MIL (NCMIL), a dual-path MIL framework that combines a Nyströmformer global encoder with Neighbor-Constrained Attention (NCA). Rather than merely combining local and global branches, NCMIL introduces three design choices aimed at spatially structured WSI evidence: a fixed physical neighborhood with a hard attention mask to preserve tissue topology, similarity-weighted neighbor aggregation based on frozen tile embeddings to suppress spatially adjacent but morphologically inconsistent tiles, and adaptive local-global fusion to balance microenvironment fidelity with slide-level context. This inductive bias improves spatial coherence without an explicit graph-construction stage. Extensive 5-fold cross-validation on four public benchmarks shows that NCMIL achieves the best overall performance among the evaluated baselines, with absolute gains of up to +1.3 AUC points, +2.2 F1 points, and +2.2 ACC points over the strongest competitor.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876201","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

Comparative finite element modelling of surgical meshes at macro and mesoscale: assessing the role of morphology on mechanical behavior. 宏观和中尺度外科手术网的比较有限元建模：评估形态对机械行为的作用。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-01 Epub Date: 2026-08-06 DOI: 10.1007/s11517-026-03645-6

Vittoria Civilini, Alessandra Aldieri, Dario Carbonaro, Vincenzo Giacalone, Alberto L Audenino, Mara Terzini

{"title":"Comparative finite element modelling of surgical meshes at macro and mesoscale: assessing the role of morphology on mechanical behavior.","authors":"Vittoria Civilini, Alessandra Aldieri, Dario Carbonaro, Vincenzo Giacalone, Alberto L Audenino, Mara Terzini","doi":"10.1007/s11517-026-03645-6","DOIUrl":"10.1007/s11517-026-03645-6","url":null,"abstract":"Synthetic meshes are widely used in abdominal wall surgery, yet recurrences remain common. Understanding how mesh morphology evolves under physiological loads is therefore crucial. In this work, a mesoscale finite element approach was developed and compared against the conventional macroscale approach to investigate the mechanical response of lightweight and standard weight polypropylene meshes using previously performed experimental tests. The new mesoscale approach reconstructed the porous architecture from high-resolution images, allowing anisotropy to emerge from geometry while using an isotropic hyperelastic material formulation. Macroscale models were implemented for comparison, modelling meshes as homogeneous surfaces with an anisotropic hyperelastic formulation. Material properties in both approaches were calibrated on uniaxial tensile tests and evaluated through ball burst simulations. Both strategies showed comparable agreement with experiments at the surgical mesh-level. However, mesoscale models provided insights into pore-level mechanisms, including deformation and collapse, confirmed through image-based tracking. They also confirmed that the observed anisotropy can be reproduced numerically by reconstructing the textile architecture. In conclusion, while the macroscale approach is faster to implement, mesoscale models better capture how structural features influence pore-level mechanical response. Integrating this approach into more complex simulations could help predict in vivo performance and guide the design of next-generation surgical meshes.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3471-3488"},"PeriodicalIF":3.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13635049/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148680756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

A multimodal prediction model for brain hematoma expansion based on deep neural network with transformer-driven collaborative attention fusion. 基于变压器驱动协同注意力融合的深度神经网络脑血肿扩张多模态预测模型。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-01 Epub Date: 2026-08-01 DOI: 10.1007/s11517-026-03643-8

Nanxu Tao, Jianping Chen, Hongjie Wu, Jiaqi Dai, Tao Zhong, Chenyang Song, Ye Wang, Yanming Chen, Qiming Fu

{"title":"A multimodal prediction model for brain hematoma expansion based on deep neural network with transformer-driven collaborative attention fusion.","authors":"Nanxu Tao, Jianping Chen, Hongjie Wu, Jiaqi Dai, Tao Zhong, Chenyang Song, Ye Wang, Yanming Chen, Qiming Fu","doi":"10.1007/s11517-026-03643-8","DOIUrl":"10.1007/s11517-026-03643-8","url":null,"abstract":"Hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (ICH) is strongly associated with death and disability, so accurate early prediction is important for clinical decision making. Existing methods often rely on single imaging signs or traditional scoring systems and are unable to consider both the three dimensional hematoma structure and the clinical status at the same time, which limits predictive performance and robustness. To address this, we propose a multimodal deep learning model named SResFormer based on position-aware Computed Tomography (CT) feature encoding. CT images and parenchymal hematoma masks are processed in a dual channel scheme. Spatial order across slices is then modeled using position-aware CT feature encoding, enabling explicit capture of three dimensional patterns of hematoma evolution. These representations are subsequently fused with structured clinical features through semantic alignment to achieve integrated cross modality prediction. SResFormer demonstrates significantly superior performance compared with traditional scoring systems, unimodal Convolutional Neural Network (CNN) based methods, and shallow multimodal fusion approaches on multicenter datasets. Ablation studies confirm both the independent contributions and the synergistic benefits of each module. SHapley Additive exPlanations (SHAP) analysis further indicates that the model reasoning is consistent with established medical knowledge.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3371-3397"},"PeriodicalIF":3.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148654891","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 non-invasive intracranial hemorrhage detection system based on electromagnetic induction. 一种基于电磁感应的无创颅内出血检测系统。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-01 Epub Date: 2026-08-07 DOI: 10.1007/s11517-026-03642-9

Qi Wang, Ruiqiang Zheng, Rongguo Yan, Xiyun Zeng, Yunhao Hu

{"title":"A non-invasive intracranial hemorrhage detection system based on electromagnetic induction.","authors":"Qi Wang, Ruiqiang Zheng, Rongguo Yan, Xiyun Zeng, Yunhao Hu","doi":"10.1007/s11517-026-03642-9","DOIUrl":"10.1007/s11517-026-03642-9","url":null,"abstract":"Rapid, non-invasive detection of intracranial hemorrhage at the point of care is crucial for improving patient outcomes after head trauma. To overcome the limitations of bulky and expensive gold-standard imaging systems like CT and MRI, this study introduces a portable detection system based on electromagnetic induction. The core of our method is a simplified single-coil sensor that detects hemorrhage-induced changes in tissue conductivity by monitoring variations in coil impedance, facilitated by a high-precision inductance-to-digital converter (LDC1101). We rigorously evaluated the system through electromagnetic simulation, customized coil design, hardware implementation, and software development featuring an RGB localization algorithm. Experiments using a 3D-printed head phantom demonstrated that the system effectively distinguishes simulated ICH lesions (30 mL NaCl solution) from normal brain tissue and successfully localizes the hemorrhage. This work establishes a novel and practical technological pathway for developing portable, low-cost ICH monitoring devices suitable for bedside and point-of-care applications.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3489-3509"},"PeriodicalIF":3.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148686471","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

Large Intestine Model Editor (LIME): Design and pilot evaluation of an editor for parameterized large intestine 3D models. 大肠模型编辑器（LIME）：设计和试点评估的编辑器参数化大肠三维模型。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-01 Epub Date: 2026-08-07 DOI: 10.1007/s11517-026-03640-x

Adrián Lugilde-López, Fernando-Ariel Mikic-Fonte, Manuel Caeiro-Rodríguez, Martín Llamas-Nistal, Antonio Rodríguez-D'Jesús

{"title":"Large Intestine Model Editor (LIME): Design and pilot evaluation of an editor for parameterized large intestine 3D models.","authors":"Adrián Lugilde-López, Fernando-Ariel Mikic-Fonte, Manuel Caeiro-Rodríguez, Martín Llamas-Nistal, Antonio Rodríguez-D'Jesús","doi":"10.1007/s11517-026-03640-x","DOIUrl":"10.1007/s11517-026-03640-x","url":null,"abstract":"As virtual training environments for colonoscopy become more prevalent, addressing their limitations such as the scarcity of simulation scenarios and the lack of open, shareable models becomes essential. This paper introduces an editing tool developed to mitigate these issues by enabling non-technical users, such as surgeons, to create varied 3D models of the large intestine. The software employs a parametrized approach using a Bezier spline with control nodes, presets, blendshapes, and specific meshes to enable the generation of a wide range of large intestine configurations, sizes, and pathology conditions. The paper also includes the results of a pilot evaluation focused on the editor utility, model fidelity, and usability, involving 10 colonoscopy practitioners who completed a modeling task and provided feedback via a questionnaire. Results indicate a positive reception, highlighting the realism of the models, user-friendliness, and overall utility. This solution not only addresses key limitations in colonoscopy training, but also lays the foundation for future advancements in colonoscopy simulation technology.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3511-3528"},"PeriodicalIF":3.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13635033/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148686446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Inside from outside: head-to-skull-and-muscles translation with statistical shape relation and multiple region-of-interest learning. 从内到外：头部到头骨和肌肉的翻译与统计形状关系和多兴趣区域学习。

IF 3.1 4区医学

Medical & Biological Engineering & Computing Pub Date : 2026-09-01 Epub Date: 2026-08-15 DOI: 10.1007/s11517-026-03653-6

Tan-Nhu Nguyen, Trung-Nhat Nguyen, Vi-Do Tran, Trieu-Nhat-Thanh Nguyen, Marie-Christine Ho Ba Tho, Tien-Tuan Dao

{"title":"Inside from outside: head-to-skull-and-muscles translation with statistical shape relation and multiple region-of-interest learning.","authors":"Tan-Nhu Nguyen, Trung-Nhat Nguyen, Vi-Do Tran, Trieu-Nhat-Thanh Nguyen, Marie-Christine Ho Ba Tho, Tien-Tuan Dao","doi":"10.1007/s11517-026-03653-6","DOIUrl":"10.1007/s11517-026-03653-6","url":null,"abstract":"From skin to musculoskeletal prediction is a current challenge in biomechanics. Previous studies attempted head-to-skull prediction using statistical shape relationships, but they did not leverage local shape geometries and reduced muscles to simple 1-D action lines. We introduced Inside from Outside, a novel approach that reconstructs the bones of the skull and the facial muscles from external head surfaces. The method coupled Region-of-Interest (ROI) learning with Statistical Shape Relationship (SSR) modeling to capture detailed anatomical correspondences. We reconstructed 329 head and skull bone meshes from head-and-neck Computed Tomography (CT) scans. Multivariate regression models were employed to learn the statistical relationships among ROI regions. A ten-fold cross-validation procedure was used to estimate the optimal number of shape parameters, the multivariate regression method, and the prediction strategies. As a result, the prediction errors were 1.9293 ± 0.1838 mm, 1.4464 ± 0.3044 mm, and 1.4933 ± 0.2470 mm for the predicted skull bones, skull shapes, and muscle attachment points, respectively. Our novel SSR- and ROI-based approach achieved more reliable accuracy in the head-to-skull prediction problem. The proposed approach will be used to perform patient-specific, head-based simulations of facial expressions to personalize rehabilitation strategies for patients with facial palsy.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3569-3604"},"PeriodicalIF":3.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148764184","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