Computer methods and programs in biomedicine最新文献_第4页

Effect of Doppler ultrasound and high-frame-rate ultrasound particle image velocimetry derived inlet boundary conditions on wall shear stress parameters in the stented superficial femoral artery 多普勒超声和高帧率超声粒子图像测速导出的入口边界条件对支架内股浅动脉壁剪应力参数的影响

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-04-01 Epub Date: 2026-01-17 DOI: 10.1016/j.cmpb.2026.109259

Lisa Rutten , Lennart van de Velde , Lente Pol , Kartik Jain , Michel M.P.J. Reijnen , Michel Versluis

Background and Objectives

Hemodynamic predictions by computational fluid dynamics (CFD) strongly depend on inlet boundary conditions (IBC). One-dimensional Doppler ultrasound (DUS) is typically used for estimating flow IBCs, despite its sensitivity to the operator, ultrasound hardware and assumptions in flow rate computation. An alternative is two-dimensional high-frame-rate ultrasound particle image velocimetry (echoPIV). This study investigated the differences between DUS and echoPIV-derived IBCs and their effect on wall shear stress parameters in the stented superficial femoral artery.

Methods

CFD simulations using DUS and echoPIV-derived IBCs were performed for three patients with a superficial femoral artery stenosis that were treated with a stent. Spatiotemporal velocity profiles were compared at 0 – 50 mm from the inlet. Differences were quantified with the root-mean-square error (RMSE). Regions of low time-averaged wall shear stress (TAWSS) and high oscillatory shear index (OSI) using a literature-based threshold of 0.4 Pa and 0.2, respectively, and an IBC-specific threshold (lower third and upper third, respectively) were determined. Co-localization was quantified using the Jaccard similarity index.

Results

The DUS and echoPIV-derived IBCs differed in flow rate and velocity profile, with the largest difference found at peak systole (RMSE: > 50 cm/s). Using the literature-based threshold, similarity in low TAWSS was high for two patients (0.85 – 0.88) and low for one (0.57). Agreement in high OSI was low in two patients (0.45 – 0.48) and high in one patient (0.83). The IBC-specific threshold increased the agreement for both low TAWSS and high OSI (≥0.75).

Conclusions

Differences in DUS and echoPIV-derived IBCs affected the TAWSS and OSI magnitudes. Regions of low TAWSS and high OSI corresponded well using an IBC-specific threshold. The literature-based threshold resulted in lower similarity values and different interpretations of restenosis risk that may cause differences in follow-up intensity or medical management.

背景与目的计算流体力学（CFD）的血流动力学预测在很大程度上依赖于入口边界条件（IBC）。一维多普勒超声（DUS）通常用于估计流量ibc，尽管它对操作员、超声硬件和流量计算中的假设很敏感。另一种选择是二维高帧率超声粒子图像测速（echoPIV）。本研究探讨了DUS和echopiv衍生的IBCs的差异及其对支架股浅动脉壁剪切应力参数的影响。方法采用DUS和echopiv衍生IBCs对3例经支架治疗的股浅动脉狭窄患者进行scfd模拟。在距离进气道0 ~ 50mm处比较了时空速度分布。差异用均方根误差（RMSE）量化。采用基于文献的阈值分别为0.4 Pa和0.2，以及ibc特定阈值（分别为下三分之一和上三分之一）确定了低时间平均壁剪应力（TAWSS）和高振荡剪切指数（OSI）区域。采用Jaccard相似性指数对共定位进行量化。结果DUS和echopiv衍生的IBCs在流速和速度分布上存在差异，在收缩期峰值差异最大（RMSE: 50 cm/s）。使用基于文献的阈值，低TAWSS的相似性在2例患者中较高（0.85 - 0.88），在1例患者中较低（0.57）。高OSI的一致性在2例患者中较低（0.45 - 0.48），在1例患者中较高（0.83）。ibc特异性阈值增加了低TAWSS和高OSI（≥0.75）的一致性。结论DUS和echopiv源性IBCs的差异影响TAWSS和OSI的大小。使用ibc特定阈值，低TAWSS和高OSI区域对应良好。基于文献的阈值导致较低的相似值和对再狭窄风险的不同解释，这可能导致随访强度或医疗管理的差异。

{"title":"Effect of Doppler ultrasound and high-frame-rate ultrasound particle image velocimetry derived inlet boundary conditions on wall shear stress parameters in the stented superficial femoral artery","authors":"Lisa Rutten , Lennart van de Velde , Lente Pol , Kartik Jain , Michel M.P.J. Reijnen , Michel Versluis","doi":"10.1016/j.cmpb.2026.109259","DOIUrl":"10.1016/j.cmpb.2026.109259","url":null,"abstract":"<div><h3>Background and Objectives</h3><div>Hemodynamic predictions by computational fluid dynamics (CFD) strongly depend on inlet boundary conditions (IBC). One-dimensional Doppler ultrasound (DUS) is typically used for estimating flow IBCs, despite its sensitivity to the operator, ultrasound hardware and assumptions in flow rate computation. An alternative is two-dimensional high-frame-rate ultrasound particle image velocimetry (echoPIV). This study investigated the differences between DUS and echoPIV-derived IBCs and their effect on wall shear stress parameters in the stented superficial femoral artery.</div></div><div><h3>Methods</h3><div>CFD simulations using DUS and echoPIV-derived IBCs were performed for three patients with a superficial femoral artery stenosis that were treated with a stent. Spatiotemporal velocity profiles were compared at 0 – 50 mm from the inlet. Differences were quantified with the root-mean-square error (RMSE). Regions of low time-averaged wall shear stress (TAWSS) and high oscillatory shear index (OSI) using a literature-based threshold of 0.4 Pa and 0.2, respectively, and an IBC-specific threshold (lower third and upper third, respectively) were determined. Co-localization was quantified using the Jaccard similarity index.</div></div><div><h3>Results</h3><div>The DUS and echoPIV-derived IBCs differed in flow rate and velocity profile, with the largest difference found at peak systole (RMSE: > 50 cm/s). Using the literature-based threshold, similarity in low TAWSS was high for two patients (0.85 – 0.88) and low for one (0.57). Agreement in high OSI was low in two patients (0.45 – 0.48) and high in one patient (0.83). The IBC-specific threshold increased the agreement for both low TAWSS and high OSI (≥0.75).</div></div><div><h3>Conclusions</h3><div>Differences in DUS and echoPIV-derived IBCs affected the TAWSS and OSI magnitudes. Regions of low TAWSS and high OSI corresponded well using an IBC-specific threshold. The literature-based threshold resulted in lower similarity values and different interpretations of restenosis risk that may cause differences in follow-up intensity or medical management.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"277 ","pages":"Article 109259"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146024464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Automated hemodynamic modeling to explore arterial curvature effects on intracranial aneurysm initiation 自动血流动力学建模探讨动脉曲度对颅内动脉瘤形成的影响

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-04-01 Epub Date: 2026-01-09 DOI: 10.1016/j.cmpb.2026.109245

Adi Konsens , Alejandro F. Frangi , Gil Marom

Background and objective

Intracranial aneurysms (IA) cause hundreds of thousands of deaths annually, yet most remain undiagnosed until rupture due to their asymptomatic nature. Improved prediction of aneurysm initiation could enable earlier detection and intervention. While computational hemodynamic models can identify high-risk regions, previous studies were limited to small cohorts due to labor-intensive manual workflows. We developed the first semi-automated workflow to enable large-scale, patient-specific hemodynamic analysis of IA initiation.

Methods

Our workflow integrates automated centerline extraction for quantitative morphological characterization with computational fluid dynamics (CFD) simulations to derive wall shear stress patterns and hemodynamic markers. We tested the workflow's robustness across multiple IA types and anatomical locations, focusing primarily on sidewall aneurysms of the internal carotid artery (ICA).

Results

Our semi-automated workflow successfully processed 42 diverse cases, 5 of them initially failed but were subsequently resolved through manual reconstruction, demonstrating robust performance across sidewall ICA aneurysms (16 cases), bifurcation aneurysms (6 cases), and validation cohorts. Validation against published data showed consistent trends with mean normalized TAWSS values of 1.31±0.09 in aneurysmal cases versus 1.14±0.07 in controls, aligning with previous findings despite methodological differences.

Conclusions

The workflow's adaptability was confirmed across multiple anatomical configurations and region of interest selection methods. This scalable approach enables the statistical analysis necessary to identify reliable hemodynamic biomarkers for IA initiation, representing a critical advancement towards evidence-based prediction models for clinical risk stratification.

背景与目的颅内动脉瘤（IA）每年导致数十万人死亡，但由于其无症状的性质，大多数在破裂前未被诊断出来。改进的动脉瘤起始预测可以使早期发现和干预成为可能。虽然计算血流动力学模型可以识别高危区域，但由于人工工作流程的劳动密集型，以前的研究仅限于小队列。我们开发了第一个半自动化的工作流程，以实现大规模的、患者特异性的IA起始血流动力学分析。方法sour工作流将用于定量形态学表征的自动中心线提取与计算流体动力学（CFD）模拟相结合，得出壁面剪切应力模式和血流动力学标记。我们测试了工作流程在多种IA类型和解剖位置上的稳健性，主要集中在颈内动脉（ICA）的侧壁动脉瘤上。结果我们的半自动化工作流程成功处理了42例不同的病例，其中5例最初失败，但随后通过人工重建得到解决，在侧壁ICA动脉瘤（16例）、分支动脉瘤（6例）和验证队列中表现出强大的性能。对已发表数据的验证显示，动脉瘤病例的平均归一化TAWSS值为1.31±0.09，而对照组为1.14±0.07，这与之前的研究结果一致，尽管方法存在差异。结论该工作流程在多种解剖结构和兴趣区选择方法中具有良好的适应性。这种可扩展的方法能够进行必要的统计分析，以确定IA起始的可靠血液动力学生物标志物，代表了临床风险分层循证预测模型的关键进展。

{"title":"Automated hemodynamic modeling to explore arterial curvature effects on intracranial aneurysm initiation","authors":"Adi Konsens , Alejandro F. Frangi , Gil Marom","doi":"10.1016/j.cmpb.2026.109245","DOIUrl":"10.1016/j.cmpb.2026.109245","url":null,"abstract":"<div><h3>Background and objective</h3><div>Intracranial aneurysms (IA) cause hundreds of thousands of deaths annually, yet most remain undiagnosed until rupture due to their asymptomatic nature. Improved prediction of aneurysm initiation could enable earlier detection and intervention. While computational hemodynamic models can identify high-risk regions, previous studies were limited to small cohorts due to labor-intensive manual workflows. We developed the first semi-automated workflow to enable large-scale, patient-specific hemodynamic analysis of IA initiation.</div></div><div><h3>Methods</h3><div>Our workflow integrates automated centerline extraction for quantitative morphological characterization with computational fluid dynamics (CFD) simulations to derive wall shear stress patterns and hemodynamic markers. We tested the workflow's robustness across multiple IA types and anatomical locations, focusing primarily on sidewall aneurysms of the internal carotid artery (ICA).</div></div><div><h3>Results</h3><div>Our semi-automated workflow successfully processed 42 diverse cases, 5 of them initially failed but were subsequently resolved through manual reconstruction, demonstrating robust performance across sidewall ICA aneurysms (16 cases), bifurcation aneurysms (6 cases), and validation cohorts. Validation against published data showed consistent trends with mean normalized TAWSS values of 1.31±0.09 in aneurysmal cases versus 1.14±0.07 in controls, aligning with previous findings despite methodological differences.</div></div><div><h3>Conclusions</h3><div>The workflow's adaptability was confirmed across multiple anatomical configurations and region of interest selection methods. This scalable approach enables the statistical analysis necessary to identify reliable hemodynamic biomarkers for IA initiation, representing a critical advancement towards evidence-based prediction models for clinical risk stratification.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"277 ","pages":"Article 109245"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145975305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Machine learning for the prediction of atrial fibrillation recurrence after catheter ablation: A systematic review and meta-analysis 机器学习预测导管消融后房颤复发：系统回顾和荟萃分析。

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-04-01 Epub Date: 2026-01-10 DOI: 10.1016/j.cmpb.2026.109249

Sofia M. Monteiro , Patrícia Bota , Pedro S. Cunha , Mário M. Oliveira , Sérgio Laranjo , Hugo Plácido da Silva

Background and Objective:

This systematic review evaluates the current state of Machine Learning (ML) methods for predicting Atrial Fibrillation (AF) recurrence following catheter ablation. With the growing use of ML, a systematic evaluation of performance and key influencing factors such as study design, data types, and reporting is needed. The main objectives are to provide an updated overview of current achievements of ML in this field, anticipate future challenges and opportunities, and derive methodological recommendations based on the findings.

Methods:

Seven databases were systematically searched, and studies proposing ML algorithms with well-documented implementation, testing, and reporting of performance metrics underwent a qualitative synthesis and risk-of-bias assessment. A meta-analysis of 17 studies was conducted using the Area Under the receiver operating characteristic Curve (AUC) as the most commonly reported performance metric.

Results:

The mean overall AUC was 0.81, indicating reasonable predictive accuracy, although there was substantial inter-study heterogeneity. Meta-regression identified sample size and input data type (clinical, imaging, or electrophysiological) as significant contributors to this heterogeneity. Subgroup analysis demonstrated that models incorporating complex data modalities achieved higher predictive accuracy and lower heterogeneity compared to those relying solely on simpler clinical variables.

Conclusion:

This review quantifies the performance of ML algorithms in predicting AF recurrence and establishes a benchmark for future research. It also highlights key challenges, including the lack of standardized datasets and limited generalizability. Incorporating more complex data sources may improve model performance, reduce inconsistencies, and enhance the potential clinical applicability of ML models in guiding patient management.

背景和目的：本系统综述评估了预测导管消融后房颤复发的机器学习（ML）方法的现状。随着机器学习的使用越来越多，需要对性能和关键影响因素（如研究设计、数据类型和报告）进行系统评估。主要目标是提供该领域ML当前成就的最新概述，预测未来的挑战和机遇，并根据研究结果得出方法学建议。方法：系统地检索了七个数据库，并对提出ML算法的研究进行了定性综合和偏倚风险评估，这些算法具有良好的文档实现、测试和性能指标报告。对17项研究进行了荟萃分析，使用受试者工作特征曲线下面积（AUC）作为最常报道的表现指标。结果：平均总体AUC为0.81，表明预测精度合理，但研究间存在较大异质性。元回归确定样本量和输入数据类型（临床、影像学或电生理）是造成这种异质性的重要因素。亚组分析表明，与仅依赖简单临床变量的模型相比，包含复杂数据模式的模型具有更高的预测准确性和更低的异质性。结论：本综述量化了ML算法在预测房颤复发方面的性能，并为未来的研究建立了基准。它还强调了主要挑战，包括缺乏标准化数据集和有限的通用性。纳入更复杂的数据源可以提高模型性能，减少不一致性，并增强ML模型在指导患者管理方面的潜在临床适用性。

{"title":"Machine learning for the prediction of atrial fibrillation recurrence after catheter ablation: A systematic review and meta-analysis","authors":"Sofia M. Monteiro , Patrícia Bota , Pedro S. Cunha , Mário M. Oliveira , Sérgio Laranjo , Hugo Plácido da Silva","doi":"10.1016/j.cmpb.2026.109249","DOIUrl":"10.1016/j.cmpb.2026.109249","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>This systematic review evaluates the current state of Machine Learning (ML) methods for predicting Atrial Fibrillation (AF) recurrence following catheter ablation. With the growing use of ML, a systematic evaluation of performance and key influencing factors such as study design, data types, and reporting is needed. The main objectives are to provide an updated overview of current achievements of ML in this field, anticipate future challenges and opportunities, and derive methodological recommendations based on the findings.</div></div><div><h3>Methods:</h3><div>Seven databases were systematically searched, and studies proposing ML algorithms with well-documented implementation, testing, and reporting of performance metrics underwent a qualitative synthesis and risk-of-bias assessment. A meta-analysis of 17 studies was conducted using the Area Under the receiver operating characteristic Curve (AUC) as the most commonly reported performance metric.</div></div><div><h3>Results:</h3><div>The mean overall AUC was 0.81, indicating reasonable predictive accuracy, although there was substantial inter-study heterogeneity. Meta-regression identified sample size and input data type (clinical, imaging, or electrophysiological) as significant contributors to this heterogeneity. Subgroup analysis demonstrated that models incorporating complex data modalities achieved higher predictive accuracy and lower heterogeneity compared to those relying solely on simpler clinical variables.</div></div><div><h3>Conclusion:</h3><div>This review quantifies the performance of ML algorithms in predicting AF recurrence and establishes a benchmark for future research. It also highlights key challenges, including the lack of standardized datasets and limited generalizability. Incorporating more complex data sources may improve model performance, reduce inconsistencies, and enhance the potential clinical applicability of ML models in guiding patient management.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"277 ","pages":"Article 109249"},"PeriodicalIF":4.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145965449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Noninvasive real-time dynamic monitoring of white blood cells based on microscopic imaging and deep learning 基于显微成像和深度学习的白细胞无创实时动态监测

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-03-01 Epub Date: 2026-01-05 DOI: 10.1016/j.cmpb.2026.109238

Fan Zhang , Bingchen Yu , Jianwei Zuo , Rui Xu , Kai Pang , Wei Jin , Jiajia Luo

Background and Objective

White blood cells (WBCs) are key biomarkers of immune status, but current monitoring still relies on intermittent blood sampling and hematology analyzers, which are invasive and lack real-time, dynamic information. This work aims to develop a noninvasive system that continuously monitors WBC dynamics in nailfold microcirculation by combining a compact optical imaging device with deep learning–based detection and tracking.

Methods

We designed a portable microscopic imaging system that records high-frame-rate videos of nailfold capillaries under 532 nm illumination, where WBCs appear as bright optical gaps against the red blood cell column. From videos of 22 volunteers, we constructed dedicated vessel and WBC datasets and trained a two-stage YOLOv8-based detection framework that first localizes vascular regions and then detects WBCs within these regions. To enhance temporal consistency, we integrated a Flow-Guided Feature Aggregation module, and employed the ByteTrack multi-object tracking algorithm to assign unique IDs to WBCs and achieve real-time counting from streaming video. System performance was evaluated using mean average precision (mAP), precision, recall and F1-score.

Results

The proposed framework achieved accurate and stable vessel and WBC detection, with detection results closely matching manual annotations and maintaining robustness under motion blur and partial occlusion. The complete “detect–track–count” pipeline supports real-time analysis on a general computing platform while using only a compact optical device.

Conclusions

This study demonstrates a portable, noninvasive AI system that enables continuous in vivo monitoring of WBC dynamics in nailfold microcirculation without blood sampling. The approach provides a promising tool for scenarios requiring frequent WBC surveillance, such as chemotherapy monitoring and immune function assessment, and offers a transferable framework for other cell detection and microcirculation studies in medical imaging.

背景与目的白细胞（wbc）是免疫状态的关键生物标志物，但目前的监测仍依赖于间歇性采血和血液学分析仪，这些仪器具有侵入性，缺乏实时、动态的信息。本研究旨在开发一种无创系统，通过将紧凑型光学成像设备与基于深度学习的检测和跟踪相结合，连续监测甲襞微循环中的WBC动态。方法设计了一种便携式显微成像系统，在532 nm光照下记录甲襞毛细血管的高帧率视频，其中白细胞在红细胞柱上出现明亮的光学间隙。从22名志愿者的视频中，我们构建了专用的血管和白细胞数据集，并训练了一个基于yolov8的两阶段检测框架，该框架首先定位血管区域，然后检测这些区域内的白细胞。为了增强时间一致性，我们集成了Flow-Guided Feature Aggregation模块，并采用ByteTrack多目标跟踪算法为wbc分配唯一id，实现对流媒体视频的实时计数。系统性能评估采用平均精度（mAP），精度，召回率和f1评分。结果所提出的框架实现了准确、稳定的血管和白细胞检测，检测结果与手工标注接近，在运动模糊和部分遮挡下保持了鲁棒性。完整的“检测-跟踪-计数”管道支持在通用计算平台上进行实时分析，而仅使用紧凑的光学设备。本研究展示了一种便携式、无创人工智能系统，该系统可以在不采血的情况下连续监测甲襞微循环中的白细胞动态。该方法为需要频繁监测白细胞的情况（如化疗监测和免疫功能评估）提供了一个有前途的工具，并为医学成像中的其他细胞检测和微循环研究提供了一个可转移的框架。

{"title":"Noninvasive real-time dynamic monitoring of white blood cells based on microscopic imaging and deep learning","authors":"Fan Zhang , Bingchen Yu , Jianwei Zuo , Rui Xu , Kai Pang , Wei Jin , Jiajia Luo","doi":"10.1016/j.cmpb.2026.109238","DOIUrl":"10.1016/j.cmpb.2026.109238","url":null,"abstract":"<div><h3>Background and Objective</h3><div>White blood cells (WBCs) are key biomarkers of immune status, but current monitoring still relies on intermittent blood sampling and hematology analyzers, which are invasive and lack real-time, dynamic information. This work aims to develop a noninvasive system that continuously monitors WBC dynamics in nailfold microcirculation by combining a compact optical imaging device with deep learning–based detection and tracking.</div></div><div><h3>Methods</h3><div>We designed a portable microscopic imaging system that records high-frame-rate videos of nailfold capillaries under 532 nm illumination, where WBCs appear as bright optical gaps against the red blood cell column. From videos of 22 volunteers, we constructed dedicated vessel and WBC datasets and trained a two-stage YOLOv8-based detection framework that first localizes vascular regions and then detects WBCs within these regions. To enhance temporal consistency, we integrated a Flow-Guided Feature Aggregation module, and employed the ByteTrack multi-object tracking algorithm to assign unique IDs to WBCs and achieve real-time counting from streaming video. System performance was evaluated using mean average precision (mAP), precision, recall and F1-score.</div></div><div><h3>Results</h3><div>The proposed framework achieved accurate and stable vessel and WBC detection, with detection results closely matching manual annotations and maintaining robustness under motion blur and partial occlusion. The complete “detect–track–count” pipeline supports real-time analysis on a general computing platform while using only a compact optical device.</div></div><div><h3>Conclusions</h3><div>This study demonstrates a portable, noninvasive AI system that enables continuous in vivo monitoring of WBC dynamics in nailfold microcirculation without blood sampling. The approach provides a promising tool for scenarios requiring frequent WBC surveillance, such as chemotherapy monitoring and immune function assessment, and offers a transferable framework for other cell detection and microcirculation studies in medical imaging.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"276 ","pages":"Article 109238"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Hemolysis performance investigation of aortic valve pump based on computational fluid dynamics and entropy production theory 基于计算流体力学和熵产理论的主动脉瓣泵溶血性能研究

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-03-01 Epub Date: 2025-12-22 DOI: 10.1016/j.cmpb.2025.109218

Teng Jing , Aidi Pan , Fangqun Wang, Weimin Ru, Md Rakibuzzaman, Ling Zhou

Background and objective

Heart failure is a significant cause of cardiovascular disease, resulting in pathological changes in human blood circulation. Aortic heart valve pump is well investigated to become an important influencing factor for hemolysis and increase blood circulation capacity. Energy loss is inevitable during the process of blood temperature rise. However, when analyzing the energy loss during the operation of artificial heart pumps, efficiency formulas are often used to indirectly evaluate the total hydraulic loss, which cannot directly determine the source and specific distribution of energy loss in different parts. Therefore, this research introduces the numerical simulation and entropy production theory to analyze artificial heart pumps.

Methods

This paper explores the aortic valve pump's flow field characteristics and hemolysis performance. The computational fluid dynamics (CFD) method with the hemolysis prediction model is performed. Furthermore, entropy production theory was employed to analysis the flow field and obtain more details about shearing and transporting effects. Different valve pump impeller structures were analyzed and compared based on entropy production theory. The temperature distribution, energy loss mechanism inside the blood pump, and blood damage characteristics were determined.

Results

(1) The flow vortex and the impact of fluid on the blade are important reasons for the significant local entropy generation loss in the region. The inlet and outlet flow fields of the blood pump impeller and rear guide vane are relatively disordered, the main concentration area of entropy generation loss. (2) The wall entropy generation value accounts for a more significant proportion of the aortic valve pump, followed by dense dissipative entropy generation, dominated by turbulent dissipative entropy generation; heat transfer dissipative entropy generation has the most minor proportion. (3) The hemolysis index mainly depends on shear stress and exposure time, while the areas with high entropy output values are primarily concentrated in areas with long exposure time or large velocity gradients, which leads to increased shear stress.

Conclusions

The combined analysis of Computational Fluid Dynamics and entropy production theory can provide a specific reference value for the blood cell damage mechanism and optimization of blood pumps.

背景与目的心衰是引起心血管疾病的重要原因，导致人体血液循环发生病理改变。主动脉瓣泵已成为溶血和增加血液循环能力的重要影响因素。在体温升高的过程中，能量的损失是不可避免的。然而，在分析人工心脏泵运行过程中的能量损失时，往往采用效率公式来间接评价总水力损失，不能直接确定能量损失在不同部位的来源和具体分布。因此，本研究引入数值模拟和熵产理论对人工心脏泵进行分析。方法对主动脉瓣泵的流场特性和溶血性能进行研究。采用计算流体力学（CFD）方法建立溶血预测模型。利用熵产理论对流场进行了分析，得到了更详细的剪切和输运效应。基于熵产理论，对不同阀泵叶轮结构进行了分析比较。测定血泵内部温度分布、能量损失机制及血损伤特征。结果(1)流动旋涡和流体对叶片的冲击是该区域局部熵产损失显著的重要原因。血泵叶轮和后导叶的进出口流场相对紊乱，是熵产生损失的主要集中区域。(2)壁面熵产值在主动脉瓣泵中所占比例更为显著，其次为致密耗散熵产，湍流耗散熵产占主导地位；传热耗散熵的产生所占比例最小。(3)溶血指数主要取决于剪应力和暴露时间，而高熵输出值的区域主要集中在暴露时间长或速度梯度大的区域，从而导致剪应力增大。结论计算流体力学与熵产理论的结合分析可为血细胞损伤机理及血泵的优化设计提供有针对性的参考价值。

{"title":"Hemolysis performance investigation of aortic valve pump based on computational fluid dynamics and entropy production theory","authors":"Teng Jing , Aidi Pan , Fangqun Wang, Weimin Ru, Md Rakibuzzaman, Ling Zhou","doi":"10.1016/j.cmpb.2025.109218","DOIUrl":"10.1016/j.cmpb.2025.109218","url":null,"abstract":"<div><h3>Background and objective</h3><div>Heart failure is a significant cause of cardiovascular disease, resulting in pathological changes in human blood circulation. Aortic heart valve pump is well investigated to become an important influencing factor for hemolysis and increase blood circulation capacity. Energy loss is inevitable during the process of blood temperature rise. However, when analyzing the energy loss during the operation of artificial heart pumps, efficiency formulas are often used to indirectly evaluate the total hydraulic loss, which cannot directly determine the source and specific distribution of energy loss in different parts. Therefore, this research introduces the numerical simulation and entropy production theory to analyze artificial heart pumps.</div></div><div><h3>Methods</h3><div>This paper explores the aortic valve pump's flow field characteristics and hemolysis performance. The computational fluid dynamics (CFD) method with the hemolysis prediction model is performed. Furthermore, entropy production theory was employed to analysis the flow field and obtain more details about shearing and transporting effects. Different valve pump impeller structures were analyzed and compared based on entropy production theory. The temperature distribution, energy loss mechanism inside the blood pump, and blood damage characteristics were determined.</div></div><div><h3>Results</h3><div>(1) The flow vortex and the impact of fluid on the blade are important reasons for the significant local entropy generation loss in the region. The inlet and outlet flow fields of the blood pump impeller and rear guide vane are relatively disordered, the main concentration area of entropy generation loss. (2) The wall entropy generation value accounts for a more significant proportion of the aortic valve pump, followed by dense dissipative entropy generation, dominated by turbulent dissipative entropy generation; heat transfer dissipative entropy generation has the most minor proportion. (3) The hemolysis index mainly depends on shear stress and exposure time, while the areas with high entropy output values are primarily concentrated in areas with long exposure time or large velocity gradients, which leads to increased shear stress.</div></div><div><h3>Conclusions</h3><div>The combined analysis of Computational Fluid Dynamics and entropy production theory can provide a specific reference value for the blood cell damage mechanism and optimization of blood pumps.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"276 ","pages":"Article 109218"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145881675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Dynamic mode decomposition as a framework for denoising ultrafast power doppler images 动态模态分解作为超快功率多普勒图像去噪的框架。

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-03-01 Epub Date: 2025-12-26 DOI: 10.1016/j.cmpb.2025.109221

Baptiste Pialot , Francesco Guidi , Pauline Muleki-Seya , Enrico Boni , Alessandro Ramalli , François Varray

Background and Objective

Imaging the morphology and hemodynamics of microvessels is critically important for the diagnosis and monitoring of various pathologies. Ultrafast Power Doppler (UPD) ultrasound is an emerging imaging modality for this purpose, offering a unique combination of portability, non-invasiveness, high temporal resolution, and real-time capability. However, UPD relies on unfocused wave transmission, which introduces high levels of uncorrelated noise compared to conventional Doppler imaging.

Method

We introduce a novel denoising approach for UPD imaging based on Dynamic Mode Decomposition (DMD), a data-driven algorithm originally developed for the analysis of spatiotemporal patterns in fluid dynamics. Using a new framework that links dynamic modes to ultrasound acquisitions, temporal signals corresponding to noisy modes are removed from ultrasound data prior to the calculation of the final UPD image. Based on an energy criterion, the number of discarded modes is adapted at the pixel level, resulting in local noise filtering. The method operates after beamforming and clutter filtering, making it compatible with standard ultrafast ultrasound pipelines, and requires only a single energy-thresholding parameter.

Results

We validated the DMD-based denoising method through simulations, phantom studies, and in vivo experiments. Compared to standard UPD images, our approach improved the signal-to-noise ratio by up to 26.0 dB and the contrast-to-noise ratio by up to 15.6 dB in vivo.

Conclusion

These results demonstrate that our DMD-based framework significantly enhances UPD image quality, enabling improved visualization of vessels. Beyond denoising, this method provides a principled foundation for advanced dynamic analysis in vascular ultrasound imaging.

背景与目的：微血管形态学和血流动力学成像对各种病变的诊断和监测至关重要。超快功率多普勒（UPD）超声是一种新兴的成像方式，提供了便携性、非侵入性、高时间分辨率和实时能力的独特组合。然而，UPD依赖于非聚焦波传输，与传统的多普勒成像相比，这会引入高水平的不相关噪声。方法：我们引入了一种新的基于动态模式分解（DMD）的UPD成像去噪方法，DMD是一种数据驱动的算法，最初是为了分析流体动力学中的时空模式而开发的。使用将动态模式与超声采集联系起来的新框架，在计算最终的UPD图像之前，从超声数据中去除与噪声模式对应的时间信号。基于能量准则，在像素级调整丢弃模式的数量，从而实现局部噪声滤波。该方法经过波束形成和杂波滤波后运行，使其与标准的超快超声管道兼容，并且只需要一个单一的能量阈值参数。结果：我们通过仿真、模型研究和体内实验验证了基于dmd的去噪方法。与标准的UPD图像相比，我们的方法将体内的信噪比提高了26.0 dB，比噪比提高了15.6 dB。结论：这些结果表明，我们基于dmd的框架显著提高了UPD图像质量，提高了血管的可视化。除了去噪之外，该方法还为血管超声成像中的高级动态分析提供了原则基础。

{"title":"Dynamic mode decomposition as a framework for denoising ultrafast power doppler images","authors":"Baptiste Pialot , Francesco Guidi , Pauline Muleki-Seya , Enrico Boni , Alessandro Ramalli , François Varray","doi":"10.1016/j.cmpb.2025.109221","DOIUrl":"10.1016/j.cmpb.2025.109221","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Imaging the morphology and hemodynamics of microvessels is critically important for the diagnosis and monitoring of various pathologies. Ultrafast Power Doppler (UPD) ultrasound is an emerging imaging modality for this purpose, offering a unique combination of portability, non-invasiveness, high temporal resolution, and real-time capability. However, UPD relies on unfocused wave transmission, which introduces high levels of uncorrelated noise compared to conventional Doppler imaging.</div></div><div><h3>Method</h3><div>We introduce a novel denoising approach for UPD imaging based on Dynamic Mode Decomposition (DMD), a data-driven algorithm originally developed for the analysis of spatiotemporal patterns in fluid dynamics. Using a new framework that links dynamic modes to ultrasound acquisitions, temporal signals corresponding to noisy modes are removed from ultrasound data prior to the calculation of the final UPD image. Based on an energy criterion, the number of discarded modes is adapted at the pixel level, resulting in local noise filtering. The method operates after beamforming and clutter filtering, making it compatible with standard ultrafast ultrasound pipelines, and requires only a single energy-thresholding parameter.</div></div><div><h3>Results</h3><div>We validated the DMD-based denoising method through simulations, phantom studies, and in vivo experiments. Compared to standard UPD images, our approach improved the signal-to-noise ratio by up to 26.0 dB and the contrast-to-noise ratio by up to 15.6 dB in vivo.</div></div><div><h3>Conclusion</h3><div>These results demonstrate that our DMD-based framework significantly enhances UPD image quality, enabling improved visualization of vessels. Beyond denoising, this method provides a principled foundation for advanced dynamic analysis in vascular ultrasound imaging.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"276 ","pages":"Article 109221"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Resolving high frequency fluctuations in cerebral aneurysm hemodynamics: the critical role of high-fidelity simulations and heart rate effects 解决脑动脉瘤血流动力学中的高频波动：高保真模拟和心率效应的关键作用

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-03-01 Epub Date: 2025-12-22 DOI: 10.1016/j.cmpb.2025.109219

Jana Korte , Abouelmagd Abdelsamie , Baha Al Deen El-Khader , Nikhil Shirdade , Ephraim W. Church , Melissa C. Brindise , Philipp Berg

Background and Objective

Despite their assumed laminar flow conditions, intracranial aneurysm (IA) hemodynamics can exhibit high frequency fluctuations, which recent studies have related to rupture risk. However, accurate detection of these fluctuations is challenging. Therefore, investigation of low and highly resolved numerical simulations to identify increased blood flow frequencies is fundamental for enhancing rupture risk assessments.

Methods

Highly resolved direct numerical simulations (DNS) and lower-resolution numerical simulations (LRNS) were conducted to assess IA hemodynamics under three representative heart rate frequencies in a patient-specific IA model (HR1: 60 bpm, HR2: 100 bpm, HR3: 137 bpm). The simulated flow fields were validated against particle tracking velocimetry. Flow instabilities were quantified by the power spectral density.

Results

The velocity fields obtained from both numerical approaches closely matched experimental data (mean v_norm=1 m/s at similar plane through IA). However, LRNS failed to capture intra-aneurysmal vorticity structures, whereas DNS successfully reproduced experimentally observed vorticity patterns. Both methods showed comparable root mean square values and time-resolved probe-wise results (highest differences: ∆0.08 m/s (HR1), ∆0.09 m/s (HR2-3).

Conclusions

DNS uniquely identified high frequency fluctuations in velocity detected with power spectral density. These fluctuations strengthened with increasing heart rates and were not captured by LRNS. Thus, it is suggested to consider high-fidelity setups when addressing IA rupture risk assessment.

背景与目的颅内动脉瘤（IA）的血流动力学可以表现出高频波动，尽管它们是层流状态，最近的研究表明这与破裂风险有关。然而，准确检测这些波动是具有挑战性的。因此，研究低分辨率和高分辨率的数值模拟来识别增加的血流频率是加强破裂风险评估的基础。方法采用高分辨率直接数值模拟（DNS）和低分辨率数值模拟（LRNS）对患者特异性IA模型中三个代表性心率频率（HR1: 60 bpm, HR2: 100 bpm, HR3: 137 bpm）下的IA血流动力学进行评估。用粒子跟踪测速法对模拟流场进行了验证。用功率谱密度量化流动不稳定性。结果两种数值方法得到的速度场与实验数据吻合较好，在相似平面上的平均vnorm=1 m/s。然而，LRNS未能捕捉到动脉瘤内的涡度结构，而DNS成功地再现了实验观察到的涡度模式。两种方法的均方根值和时间分辨探针结果具有可比性(最大差异：∆0.08 m/s （HR1),∆0.09 m/s (HR2-3)）。结论sdns能较好地识别出功率谱密度检测到的速度高频波动。这些波动随着心率的增加而增强，LRNS没有捕捉到。因此，建议在处理IA破裂风险评估时考虑高保真度设置。

{"title":"Resolving high frequency fluctuations in cerebral aneurysm hemodynamics: the critical role of high-fidelity simulations and heart rate effects","authors":"Jana Korte , Abouelmagd Abdelsamie , Baha Al Deen El-Khader , Nikhil Shirdade , Ephraim W. Church , Melissa C. Brindise , Philipp Berg","doi":"10.1016/j.cmpb.2025.109219","DOIUrl":"10.1016/j.cmpb.2025.109219","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Despite their assumed laminar flow conditions, intracranial aneurysm (IA) hemodynamics can exhibit high frequency fluctuations, which recent studies have related to rupture risk. However, accurate detection of these fluctuations is challenging. Therefore, investigation of low and highly resolved numerical simulations to identify increased blood flow frequencies is fundamental for enhancing rupture risk assessments.</div></div><div><h3>Methods</h3><div>Highly resolved direct numerical simulations (DNS) and lower-resolution numerical simulations (LRNS) were conducted to assess IA hemodynamics under three representative heart rate frequencies in a patient-specific IA model (HR1: 60 bpm, HR2: 100 bpm, HR3: 137 bpm). The simulated flow fields were validated against particle tracking velocimetry. Flow instabilities were quantified by the power spectral density.</div></div><div><h3>Results</h3><div>The velocity fields obtained from both numerical approaches closely matched experimental data (mean v<sub>norm</sub>=1 m/s at similar plane through IA). However, LRNS failed to capture intra-aneurysmal vorticity structures, whereas DNS successfully reproduced experimentally observed vorticity patterns. Both methods showed comparable root mean square values and time-resolved probe-wise results (highest differences: ∆0.08 m/s (HR1), ∆0.09 m/s (HR2-3).</div></div><div><h3>Conclusions</h3><div>DNS uniquely identified high frequency fluctuations in velocity detected with power spectral density. These fluctuations strengthened with increasing heart rates and were not captured by LRNS. Thus, it is suggested to consider high-fidelity setups when addressing IA rupture risk assessment.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"276 ","pages":"Article 109219"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Fitting high-dimensional mixture cure models using the hdcuremodels R package 使用hdcumodels R包拟合高维混合固化模型

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-03-01 Epub Date: 2025-12-31 DOI: 10.1016/j.cmpb.2025.109212

Kellie J. Archer , Han Fu

Background and Objective:

Time-to-event outcomes are often of interest in biomedical studies. When the dataset includes long-term survivors or subjects who will not experience the event of interest, mixture cure models (MCMs) should be fit. Further, it is clinically relevant to identify molecular features from high-throughput assays that are associated with time-to-event outcomes, both to elucidate important pathways and to identify molecular features that may be therapeutic targets or for developing improved risk stratification systems. Herein, we describe our hdcuremodels R package that can be used to model right-censored time-to-event data when a cured fraction is present and the predictor space is high-dimensional.

Methods:

We implemented two different optimization methods, the expectation–maximization and generalized monotone incremental forward stagewise algorithms, for fitting high-dimensional penalized Weibull, exponential, and Cox mixture cure models. Cross-validation functions for each optimization method are provided that can be run with or without controlling the false discovery rate. The modeling functions are flexible in that there is no requirement for the predictors to be the same in the incidence and latency components of the model. The package also includes functions for testing mixture cure modeling assumptions, evaluating performance, and generic functions that can be used to extract meaningful results.

Results:

We demonstrate fitting a high-dimensional penalized mixture cure model to an acute myeloid leukemia dataset, which had strong predictive performance on an independent test set.

Conclusion:

Our hdcuremodels package fits penalized mixture cure models that can accommodate datasets where the number of predictors exceeds the sample size.

背景与目的：时间到事件的结果在生物医学研究中经常引起人们的兴趣。当数据集包括长期幸存者或不会经历感兴趣事件的受试者时，应适合混合治疗模型（mcm）。此外，从高通量分析中识别与事件发生时间相关的分子特征具有临床意义，既可以阐明重要的途径，也可以识别可能成为治疗靶点的分子特征，或用于开发改进的风险分层系统。在此，我们描述了我们的hdcumodels R包，该包可用于在存在固化部分且预测空间为高维时对右截尾时间到事件数据进行建模。方法：我们实现了两种不同的优化方法，即期望最大化和广义单调增量前向分阶段算法，用于拟合高维惩罚Weibull，指数和Cox混合模型。提供了每种优化方法的交叉验证函数，可以在控制错误发现率或不控制错误发现率的情况下运行。建模功能是灵活的，因为不要求模型的发生率和延迟组件中的预测器相同。该软件包还包括用于测试混合物、建模假设、评估性能和可用于提取有意义结果的通用函数的功能。结果：我们展示了将高维惩罚混合治疗模型拟合到急性髓系白血病数据集，该模型在独立测试集上具有很强的预测性能。结论：我们的hdcuremodels包适合惩罚混合治疗模型，可以适应预测因子数量超过样本量的数据集。

{"title":"Fitting high-dimensional mixture cure models using the hdcuremodels R package","authors":"Kellie J. Archer , Han Fu","doi":"10.1016/j.cmpb.2025.109212","DOIUrl":"10.1016/j.cmpb.2025.109212","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Time-to-event outcomes are often of interest in biomedical studies. When the dataset includes long-term survivors or subjects who will not experience the event of interest, mixture cure models (MCMs) should be fit. Further, it is clinically relevant to identify molecular features from high-throughput assays that are associated with time-to-event outcomes, both to elucidate important pathways and to identify molecular features that may be therapeutic targets or for developing improved risk stratification systems. Herein, we describe our <strong>hdcuremodels</strong> <span>R</span> package that can be used to model right-censored time-to-event data when a cured fraction is present and the predictor space is high-dimensional.</div></div><div><h3>Methods:</h3><div>We implemented two different optimization methods, the expectation–maximization and generalized monotone incremental forward stagewise algorithms, for fitting high-dimensional penalized Weibull, exponential, and Cox mixture cure models. Cross-validation functions for each optimization method are provided that can be run with or without controlling the false discovery rate. The modeling functions are flexible in that there is no requirement for the predictors to be the same in the incidence and latency components of the model. The package also includes functions for testing mixture cure modeling assumptions, evaluating performance, and generic functions that can be used to extract meaningful results.</div></div><div><h3>Results:</h3><div>We demonstrate fitting a high-dimensional penalized mixture cure model to an acute myeloid leukemia dataset, which had strong predictive performance on an independent test set.</div></div><div><h3>Conclusion:</h3><div>Our <strong>hdcuremodels</strong> package fits penalized mixture cure models that can accommodate datasets where the number of predictors exceeds the sample size.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"276 ","pages":"Article 109212"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145881684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Development of an automated assessment of ultrasound measured diaphragm thickness 超声测量隔膜厚度自动评估系统的开发

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-03-01 Epub Date: 2025-12-24 DOI: 10.1016/j.cmpb.2025.109220

Alette A. Koopman , Jitka Burger , Kay Laarman , Douwe van der Steen , Robert G.T. Blokpoel , Eline Oppersma , Martin C.J. Kneyber

Background and objectives

Inadequate titration of support during mechanical ventilation can cause ventilator-induced diaphragmatic dysfunction through changes in diaphragm structure, leading to prolonged weaning. Bedside diaphragm ultrasound (DUS) enables real-time, noninvasive assessment of diaphragm structure, but its interpretation is often hindered by interobserver variability. To improve the accuracy of DUS measurements, we developed an automated analysis framework and evaluated its inter-method agreement.

Methods

The automated DUS analysis framework generates diaphragm thickness (T_di)-time plots. We evaluated its performance using DUS clips from mechanically ventilated children < 5 years of age who could maintain spontaneous breathing. T_di was measured at end-expiration (T_di,ee) and peak-inspiration (T_di,pi), manually by using a DICOM viewer and at the bedside, as well as automated by the software tool. Inter-method agreement was assessed by intra-class correlation coefficients (ICC).

Results

In total 26 DUS clips of 10 patients were analyzed. Overall, median T_di,pi was 1.58 mm [IQR 1.24–1.85] and T_di,ee was 1.32 mm [IQR 0.99–1.46], resulting in a thickening fraction (TF_di) of 26.9 % [IQR 22.8–31.6]. Inter-method agreement between the software tool and bedside measurements was reflected by an ICC of 0.918 (95 % CI: 0.83–0.96). The ICC between software tool and the DICOM viewer was 0.991 95 % CI [0.98–0.99]. Bland-Altman analysis showed a mean difference of -0.0076 mm [95 % LOA -0.18 – 0.17] between DICOM- and tool-based T_di(ee&pi) measurements.

Conclusions

This proof-of-concept study demonstrates that automated analysis of diaphragm thickness and thickening fraction in mechanically ventilated children is feasible and provides reproducible quantification of T_di, reflected by high intra-class correlation coefficients.

背景与目的机械通气时支持滴定不足可通过膈结构改变引起呼吸机诱导的膈功能障碍，导致脱机时间延长。床边横膈膜超声（DUS）能够实时、无创地评估横膈膜结构，但其解释常常受到观察者之间差异的阻碍。为了提高DUS测量的准确性，我们开发了一个自动化分析框架，并评估了其方法间的一致性。方法自动DUS分析框架生成膜片厚度（Tdi）时间图。我们使用来自5岁机械通气儿童的DUS夹来评估其性能，这些儿童能够保持自主呼吸。Tdi在呼气末（Tdi,ee）和吸气峰（Tdi,pi）测量，通过DICOM观察器和床边手动测量，也通过软件工具自动测量。采用类内相关系数（ICC）评价方法间一致性。结果对10例患者的26个DUS夹进行了分析。总体而言，中位Tdi，pi为1.58 mm [IQR 1.24-1.85], Tdi，ee为1.32 mm [IQR 0.99-1.46]，导致增厚分数（TFdi）为26.9% [IQR 22.8-31.6]。软件工具和床边测量之间的方法间一致性的ICC值为0.918 （95% CI: 0.83-0.96）。软件工具与DICOM查看器的ICC为0.991 95% CI[0.98-0.99]。Bland-Altman分析显示，DICOM和基于工具的Tdi（ee&pi）测量的平均差异为-0.0076 mm [95% LOA -0.18 - 0.17]。本概念验证性研究表明，机械通气儿童隔膜厚度和增厚分数的自动化分析是可行的，并提供了可重复的Tdi量化，反映在高组内相关系数上。

{"title":"Development of an automated assessment of ultrasound measured diaphragm thickness","authors":"Alette A. Koopman , Jitka Burger , Kay Laarman , Douwe van der Steen , Robert G.T. Blokpoel , Eline Oppersma , Martin C.J. Kneyber","doi":"10.1016/j.cmpb.2025.109220","DOIUrl":"10.1016/j.cmpb.2025.109220","url":null,"abstract":"<div><h3>Background and objectives</h3><div>Inadequate titration of support during mechanical ventilation can cause ventilator-induced diaphragmatic dysfunction through changes in diaphragm structure, leading to prolonged weaning. Bedside diaphragm ultrasound (DUS) enables real-time, noninvasive assessment of diaphragm structure, but its interpretation is often hindered by interobserver variability. To improve the accuracy of DUS measurements, we developed an automated analysis framework and evaluated its inter-method agreement.</div></div><div><h3>Methods</h3><div>The automated DUS analysis framework generates diaphragm thickness (T<sub>di</sub>)-time plots. We evaluated its performance using DUS clips from mechanically ventilated children < 5 years of age who could maintain spontaneous breathing. T<sub>di</sub> was measured at end-expiration (T<sub>di,ee</sub>) and peak-inspiration (T<sub>di,pi</sub>), manually by using a DICOM viewer and at the bedside, as well as automated by the software tool. Inter-method agreement was assessed by intra-class correlation coefficients (ICC).</div></div><div><h3>Results</h3><div>In total 26 DUS clips of 10 patients were analyzed. Overall, median T<sub>di,pi</sub> was 1.58 mm [IQR 1.24–1.85] and T<sub>di,ee</sub> was 1.32 mm [IQR 0.99–1.46], resulting in a thickening fraction (TF<sub>di</sub>) of 26.9 % [IQR 22.8–31.6]. Inter-method agreement between the software tool and bedside measurements was reflected by an ICC of 0.918 (95 % CI: 0.83–0.96). The ICC between software tool and the DICOM viewer was 0.991 95 % CI [0.98–0.99]. Bland-Altman analysis showed a mean difference of -0.0076 mm [95 % LOA -0.18 – 0.17] between DICOM- and tool-based T<sub>di(ee&pi)</sub> measurements.</div></div><div><h3>Conclusions</h3><div>This proof-of-concept study demonstrates that automated analysis of diaphragm thickness and thickening fraction in mechanically ventilated children is feasible and provides reproducible quantification of T<sub>di</sub>, reflected by high intra-class correlation coefficients.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"276 ","pages":"Article 109220"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145881676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

TPVNet: A domain-aware graph-based framework for reliable multivariate physiological time series classification in healthcare TPVNet：用于医疗保健中可靠的多变量生理时间序列分类的基于领域感知图的框架。

IF 4.8 2区医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer methods and programs in biomedicine

Pub Date : 2026-03-01 Epub Date: 2025-12-19 DOI: 10.1016/j.cmpb.2025.109214

Xinyue Ren , Yuxuan Xiu , Ting Chen , Zhaosheng Yao , Wai Kin (Victor) Chan

Background and Objective:

Multivariate physiological time series classification is essential for healthcare decision support within the Internet of Medical Things (IoMT). However, existing methods often struggle with high noise, non-stationarity, and privacy concerns inherent in medical signals. This study proposes TPVNet, a novel domain-aware framework, to enhance classification accuracy, stability, and privacy protection in IoMT applications.

Methods:

We propose TPVNet, a domain-aware graph-based framework specifically designed for physiological MTSC tasks. TPVNet integrates two key innovations: a Temporal-enhanced limited Penetrable Visibility Graph (TPVG) for converting raw signals into irreversible graph representations with enriched local and global temporal features. Graph Isomorphism Network (GIN) is used for feature learning followed by a channel-wise voting strategy that aligns with clinical diagnostic workflows to improve decision robustness. Experiments are conducted on seven public physiological datasets, comparing TPVNet against eight state-of-the-art baselines. Performance is evaluated using accuracy, recall, precision, F1-score and standard deviation over 10 replicate tests.

Results:

TPVNet demonstrates robust performance, achieving the highest F1-score on 6 out of 7 datasets. In terms of clinical utility, it significantly outperforms state-of-the-art baselines in data-scarce scenarios; notably, on the Atrial Fibrillation (AF) dataset, it boosts accuracy by 22.0%. Moreover, ablation studies confirm a cumulative accuracy gain of 12.7% over the graph baseline, validating the synergistic effectiveness of the proposed TPVG representation and voting mechanism. Furthermore, TPVNet exhibits superior stability, consistently yielding lower standard deviations compared to deep learning baselines.

Conclusions:

TPVNet provides a privacy-aware, accurate, and stable solution for multivariate physiological time series classification. By integrating domain-inspired graph construction and decision fusion, it offers a clinically aligned framework suitable for real-world IoMT applications, bridging the gap between algorithmic design and healthcare needs.

背景与目的：多变量生理时间序列分类对于医疗物联网（IoMT）中的医疗决策支持至关重要。然而，现有的方法往往与医疗信号固有的高噪声、非平稳性和隐私问题作斗争。本文提出了一种新的领域感知框架TPVNet，以提高IoMT应用中的分类准确性、稳定性和隐私保护。方法：我们提出了TPVNet，这是一个专门为生理MTSC任务设计的基于领域感知图的框架。TPVNet集成了两个关键创新：一个时间增强的有限穿透可见性图（TPVG），用于将原始信号转换为具有丰富的局部和全局时间特征的不可逆图表示。图同构网络（GIN）用于特征学习，然后是与临床诊断工作流程一致的通道智能投票策略，以提高决策鲁棒性。实验在7个公共生理数据集上进行，将TPVNet与8个最先进的基线进行比较。使用准确性、召回率、精密度、f1分数和超过10个重复测试的标准偏差来评估性能。结果：TPVNet表现出稳健的性能，在7个数据集中的6个数据集上获得了最高的f1分。就临床效用而言，在数据稀缺的情况下，它明显优于最先进的基线；值得注意的是，在心房颤动（AF）数据集上，它将准确率提高了22.0%。此外，消融研究证实，与图基线相比，累积精度提高了12.7%，验证了所提出的TPVG表示和投票机制的协同有效性。此外，与深度学习基线相比，TPVNet表现出卓越的稳定性，始终产生更低的标准差。结论：TPVNet为多变量生理时间序列分类提供了一种具有隐私意识、准确、稳定的解决方案。通过集成领域启发的图构建和决策融合，它提供了一个适合现实世界IoMT应用的临床一致的框架，弥合了算法设计和医疗保健需求之间的差距。

{"title":"TPVNet: A domain-aware graph-based framework for reliable multivariate physiological time series classification in healthcare","authors":"Xinyue Ren , Yuxuan Xiu , Ting Chen , Zhaosheng Yao , Wai Kin (Victor) Chan","doi":"10.1016/j.cmpb.2025.109214","DOIUrl":"10.1016/j.cmpb.2025.109214","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Multivariate physiological time series classification is essential for healthcare decision support within the Internet of Medical Things (IoMT). However, existing methods often struggle with high noise, non-stationarity, and privacy concerns inherent in medical signals. This study proposes TPVNet, a novel domain-aware framework, to enhance classification accuracy, stability, and privacy protection in IoMT applications.</div></div><div><h3>Methods:</h3><div>We propose TPVNet, a domain-aware graph-based framework specifically designed for physiological MTSC tasks. TPVNet integrates two key innovations: a Temporal-enhanced limited Penetrable Visibility Graph (TPVG) for converting raw signals into irreversible graph representations with enriched local and global temporal features. Graph Isomorphism Network (GIN) is used for feature learning followed by a channel-wise voting strategy that aligns with clinical diagnostic workflows to improve decision robustness. Experiments are conducted on seven public physiological datasets, comparing TPVNet against eight state-of-the-art baselines. Performance is evaluated using accuracy, recall, precision, F1-score and standard deviation over 10 replicate tests.</div></div><div><h3>Results:</h3><div>TPVNet demonstrates robust performance, achieving the highest F1-score on 6 out of 7 datasets. In terms of clinical utility, it significantly outperforms state-of-the-art baselines in data-scarce scenarios; notably, on the Atrial Fibrillation (AF) dataset, it boosts accuracy by 22.0%. Moreover, ablation studies confirm a cumulative accuracy gain of 12.7% over the graph baseline, validating the synergistic effectiveness of the proposed TPVG representation and voting mechanism. Furthermore, TPVNet exhibits superior stability, consistently yielding lower standard deviations compared to deep learning baselines.</div></div><div><h3>Conclusions:</h3><div>TPVNet provides a privacy-aware, accurate, and stable solution for multivariate physiological time series classification. By integrating domain-inspired graph construction and decision fusion, it offers a clinically aligned framework suitable for real-world IoMT applications, bridging the gap between algorithmic design and healthcare needs.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"276 ","pages":"Article 109214"},"PeriodicalIF":4.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145827120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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