Computers in biology and medicine最新文献_第4页

Gastrointestinal image classification with GIDNet CNN model and non-linear Tansh activation function 基于GIDNet CNN模型和非线性Tansh激活函数的胃肠图像分类。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1016/j.compbiomed.2026.111500

Ayan Mondal , Ayan Chatterjee , Michael A. Reigler

Gastrointestinal (GI) diseases pose significant health risks to humans. To help medical professionals in early GI disease detection and diagnosis through image processing and analysis, this article offers an in-depth exploration of improving GI disease classification through artificial intelligence, specifically focusing on convolutional neural networks (CNNs). The central objective of this research is to formulate a highly accurate model for GI disease classification. We introduce GIDNet, a novel CNN model, and present a new activation function, called Tansh, designed to improve classification accuracy. The effectiveness of the proposed approach is evaluated using the Kvasir dataset. The study addresses research gaps in the existing literature, such as limited exploration of activation functions tailored for the classification of GI diseases and lack of explainability in model decisions. The methodology section describes the experimental setup, including the implementation of the Tansh activation function, model architecture, and dataset preparation. The study conducts a comparative analysis of Tansh against well-established activation functions, evaluating classification accuracy and model explainability using well-established methods. The results reveal that the pro-posed GIDNet model integrated with the Tansh activation function achieves an unparalleled classification accuracy of 98.75 % in the Kvasir dataset, surpass-ing existing state-of-the-art models. The study concludes with discussions of the implications of the findings, potential applications in clinical practice, and avenues for future research. In general, the study contributes novel information.

on the classification of GI diseases by introducing a novel activation function and demonstrating its effectiveness in improving classification accuracy and model explainability. The findings have significant implications for automated diagno-sis and treatment planning in gastroenterology, paving the way for more reliable and interpretable AI-driven healthcare solutions.

胃肠道疾病对人类健康构成重大威胁。为了帮助医疗专业人员通过图像处理和分析来早期发现和诊断胃肠道疾病，本文深入探索了利用人工智能来改进胃肠道疾病分类，特别是卷积神经网络（cnn）。本研究的中心目标是建立一个高度准确的胃肠道疾病分类模型。我们引入了一种新的CNN模型GIDNet，并提出了一个新的激活函数，称为Tansh，旨在提高分类精度。使用Kvasir数据集评估了所提出方法的有效性。该研究解决了现有文献中的研究空白，例如针对胃肠道疾病分类量身定制的激活功能的探索有限，以及模型决策缺乏可解释性。方法学部分描述了实验设置，包括Tansh激活函数的实现、模型架构和数据集准备。本研究将Tansh与已建立的激活函数进行对比分析，利用已建立的方法评估分类准确性和模型可解释性。结果表明，结合Tansh激活函数的GIDNet模型在Kvasir数据集中的分类准确率达到了98.75%，超过了现有的最先进的模型。研究最后讨论了研究结果的意义、临床实践中的潜在应用以及未来研究的途径。总的来说，这项研究提供了新的信息。通过引入一种新的激活函数并证明其在提高分类精度和模型可解释性方面的有效性，对胃肠道疾病的分类进行了研究。这些发现对胃肠病学的自动诊断和治疗计划具有重大意义，为更可靠和可解释的人工智能驱动的医疗保健解决方案铺平了道路。

{"title":"Gastrointestinal image classification with GIDNet CNN model and non-linear Tansh activation function","authors":"Ayan Mondal , Ayan Chatterjee , Michael A. Reigler","doi":"10.1016/j.compbiomed.2026.111500","DOIUrl":"10.1016/j.compbiomed.2026.111500","url":null,"abstract":"<div><div>Gastrointestinal (GI) diseases pose significant health risks to humans. To help medical professionals in early GI disease detection and diagnosis through image processing and analysis, this article offers an in-depth exploration of improving GI disease classification through artificial intelligence, specifically focusing on convolutional neural networks (CNNs). The central objective of this research is to formulate a highly accurate model for GI disease classification. We introduce GIDNet, a novel CNN model, and present a new activation function, called Tansh, designed to improve classification accuracy. The effectiveness of the proposed approach is evaluated using the Kvasir dataset. The study addresses research gaps in the existing literature, such as limited exploration of activation functions tailored for the classification of GI diseases and lack of explainability in model decisions. The methodology section describes the experimental setup, including the implementation of the Tansh activation function, model architecture, and dataset preparation. The study conducts a comparative analysis of Tansh against well-established activation functions, evaluating classification accuracy and model explainability using well-established methods. The results reveal that the pro-posed GIDNet model integrated with the Tansh activation function achieves an unparalleled classification accuracy of 98.75 <strong>%</strong> in the Kvasir dataset, surpass-ing existing state-of-the-art models. The study concludes with discussions of the implications of the findings, potential applications in clinical practice, and avenues for future research. In general, the study contributes novel information.</div><div>on the classification of GI diseases by introducing a novel activation function and demonstrating its effectiveness in improving classification accuracy and model explainability. The findings have significant implications for automated diagno-sis and treatment planning in gastroenterology, paving the way for more reliable and interpretable AI-driven healthcare solutions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111500"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146137284","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

Modeling the effect of substrate topography on cellular and nuclear deformations 模拟基质地形对细胞和核变形的影响。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-10 DOI: 10.1016/j.compbiomed.2026.111536

Ana Bensabat , Marcos Gouveia , Claire Leclech , João Carvalho , Abdul I. Barakat , Rui D.M. Travasso

As they navigate complex extracellular environments, cells and their nuclei undergo extensive deformation. Recent experiments have demonstrated that vascular endothelial cells cultured on microgroove substrates, which mimic the anisotropic topography of the basement membrane, exhibit complex nuclear deformations, leading to partial or even complete nuclear penetration into the microgrooves. Interestingly, the experiments suggest that nuclear entry into the microgrooves is driven mainly by cellular adhesion and spreading rather than by cytoskeleton-mediated pulling and/or pushing forces. In the present work, we develop a phase-field model to describe endothelial cell deformation on microgroove substrates and characterize the conditions necessary for nuclear confinement within the grooves, a process that has been termed “caging" in the experiments. The model introduces a novel non-local term that prevents the cellular body from fragmenting under conditions of strong adhesion and high curvature. Our numerical simulations show that significant nuclear deformation and partial caging occur for strong cell-substrate adhesion and for nuclear membrane stiffness close to or inferior to that of the cell membrane. We further show that the dimensions of the grooves are critical for the caging process, with increasing groove depth and width favoring nuclear penetration into and caging within the grooves. These results are in close agreement with experimental observations, thus corroborating the notion that cell-substrate adhesion forces can drive large-scale nuclear deformations without the need for cytoskeleton-generated forces.

在复杂的细胞外环境中，细胞及其细胞核经历了广泛的变形。最近的实验表明，在模拟基底膜各向异性地形的微槽基质上培养的血管内皮细胞表现出复杂的核变形，导致核部分甚至完全渗透到微槽中。有趣的是，实验表明细胞核进入微凹槽主要是由细胞粘附和扩散驱动的，而不是由细胞骨架介导的拉力和/或推力驱动的。在目前的工作中，我们开发了一个相场模型来描述微槽基底上的内皮细胞变形，并表征了微槽内核约束所需的条件，这一过程在实验中被称为“笼化”。该模型引入了一种新的非局部项，以防止细胞体在强附着力和高曲率条件下破碎。我们的数值模拟表明，当细胞-基质粘附较强，核膜刚度接近或低于细胞膜刚度时，会发生显著的核变形和部分笼化。我们进一步表明，凹槽的尺寸对保持过程至关重要，随着凹槽深度和宽度的增加，有利于核渗透到凹槽内并在凹槽内保持。这些结果与实验观察结果非常一致，从而证实了细胞-基质粘附力可以在不需要细胞骨架产生力的情况下驱动大规模核变形的概念。

{"title":"Modeling the effect of substrate topography on cellular and nuclear deformations","authors":"Ana Bensabat , Marcos Gouveia , Claire Leclech , João Carvalho , Abdul I. Barakat , Rui D.M. Travasso","doi":"10.1016/j.compbiomed.2026.111536","DOIUrl":"10.1016/j.compbiomed.2026.111536","url":null,"abstract":"<div><div>As they navigate complex extracellular environments, cells and their nuclei undergo extensive deformation. Recent experiments have demonstrated that vascular endothelial cells cultured on microgroove substrates, which mimic the anisotropic topography of the basement membrane, exhibit complex nuclear deformations, leading to partial or even complete nuclear penetration into the microgrooves. Interestingly, the experiments suggest that nuclear entry into the microgrooves is driven mainly by cellular adhesion and spreading rather than by cytoskeleton-mediated pulling and/or pushing forces. In the present work, we develop a phase-field model to describe endothelial cell deformation on microgroove substrates and characterize the conditions necessary for nuclear confinement within the grooves, a process that has been termed “caging\" in the experiments. The model introduces a novel non-local term that prevents the cellular body from fragmenting under conditions of strong adhesion and high curvature. Our numerical simulations show that significant nuclear deformation and partial caging occur for strong cell-substrate adhesion and for nuclear membrane stiffness close to or inferior to that of the cell membrane. We further show that the dimensions of the grooves are critical for the caging process, with increasing groove depth and width favoring nuclear penetration into and caging within the grooves. These results are in close agreement with experimental observations, thus corroborating the notion that cell-substrate adhesion forces can drive large-scale nuclear deformations without the need for cytoskeleton-generated forces.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111536"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146164570","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

Exploring the potential of explainable deep learning for EEG-based cognitive decline prediction 探索基于脑电图的认知衰退预测中可解释深度学习的潜力。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-09 DOI: 10.1016/j.compbiomed.2026.111538

Anna Josefine Grillenberger , Nelly Shenton , Martin Lauritzen , Krisztina Benedek , Sadasivan Puthusserypady

Objective

Detecting Alzheimer’s disease (AD) at an early stage is essential for administering effective treatments and preventing neuronal damage. Unfortunately, current diagnostic techniques are often invasive and expensive. Our research focuses on creating a cost-effective and non-invasive method for the early detection of cognitive decline.

Methods

Using a publicly available dataset of resting state electroencephalographic (EEG) data on healthy controls and patients with Mild Cognitive Impairment (MCI), two novel deep learning (DL) algorithms with self-attention mechanisms were developed and evaluated for their performance in predicting MCI and cognitive decline.

Results

Both proposed DL algorithms outperformed a traditional convolutional neural network (CNN) model in predicting MCI, achieving test accuracy improvements of 8.5% and 10%, respectively, while utilizing significantly fewer trainable parameters. An ablation study highlighted the attention layer as a key feature, enhancing model accuracy by 8.5%. Analysis of the attention layers indicated that beta band frequencies (13-30 Hz) were essential for distinguishing MCI from control subjects, highlighting the role of high EEG frequencies in early cognitive deficits. Predicting pre-clinical cognitive decline in healthy subjects proved more challenging than predicting diagnosed MCI. However, using transfer-learning methods, we achieved a test accuracy of 56.08%.

Conclusion

Our models achieved state-of-the-art results in the MCI classification task, and demonstrated learning progress in predicting cognitive decline in the preclinical stage. As this is the first time DL models have been evaluated to classify healthy subjects based on cognitive scores, where brain changes are minimal and difficult to detect, this study opens new avenues for discovering biomarkers in early AD diagnosis and facilitating early interventions. Interpretation of the trained DL attention models provided valuable insights that aligned with the existing brain research, serving as a helpful tool for validating AI in healthcare applications.

目的：早期发现阿尔茨海默病（AD）对于给予有效治疗和预防神经元损伤至关重要。不幸的是，目前的诊断技术往往是侵入性的和昂贵的。我们的研究重点是创造一种具有成本效益和非侵入性的方法来早期检测认知能力下降。方法：利用公开的健康对照和轻度认知障碍（MCI）患者静息状态脑电图（EEG）数据集，开发了两种具有自我注意机制的新型深度学习（DL）算法，并评估了它们在预测轻度认知障碍（MCI）和认知能力下降方面的表现。结果：两种DL算法在预测MCI方面都优于传统的卷积神经网络（CNN）模型，在使用更少的可训练参数的同时，测试准确率分别提高了8.5%和10%。一项消融研究强调了注意力层作为关键特征，将模型精度提高了8.5%。对注意层的分析表明，β频带频率（13-30 Hz）是区分轻度认知障碍和对照组的关键，强调了高脑电图频率在早期认知缺陷中的作用。事实证明，预测健康受试者的临床前认知能力下降比预测诊断为轻度认知障碍的受试者更具挑战性。然而，使用迁移学习方法，我们实现了56.08%的测试准确率。结论：我们的模型在MCI分类任务中取得了最先进的结果，并且在预测临床前阶段的认知衰退方面显示了学习进展。由于这是首次评估DL模型以基于认知评分对健康受试者进行分类，其中大脑变化最小且难以检测，因此该研究为发现早期AD诊断中的生物标志物和促进早期干预开辟了新的途径。对训练好的DL注意力模型的解释提供了与现有大脑研究相一致的有价值的见解，可以作为验证医疗保健应用程序中的AI的有用工具。

{"title":"Exploring the potential of explainable deep learning for EEG-based cognitive decline prediction","authors":"Anna Josefine Grillenberger , Nelly Shenton , Martin Lauritzen , Krisztina Benedek , Sadasivan Puthusserypady","doi":"10.1016/j.compbiomed.2026.111538","DOIUrl":"10.1016/j.compbiomed.2026.111538","url":null,"abstract":"<div><h3>Objective</h3><div>Detecting Alzheimer’s disease (AD) at an early stage is essential for administering effective treatments and preventing neuronal damage. Unfortunately, current diagnostic techniques are often invasive and expensive. Our research focuses on creating a cost-effective and non-invasive method for the early detection of cognitive decline.</div></div><div><h3>Methods</h3><div>Using a publicly available dataset of resting state electroencephalographic (EEG) data on healthy controls and patients with Mild Cognitive Impairment (MCI), two novel deep learning (DL) algorithms with self-attention mechanisms were developed and evaluated for their performance in predicting MCI and cognitive decline.</div></div><div><h3>Results</h3><div>Both proposed DL algorithms outperformed a traditional convolutional neural network (CNN) model in predicting MCI, achieving test accuracy improvements of 8.5% and 10%, respectively, while utilizing significantly fewer trainable parameters. An ablation study highlighted the attention layer as a key feature, enhancing model accuracy by 8.5%. Analysis of the attention layers indicated that beta band frequencies (13-30 Hz) were essential for distinguishing MCI from control subjects, highlighting the role of high EEG frequencies in early cognitive deficits. Predicting pre-clinical cognitive decline in healthy subjects proved more challenging than predicting diagnosed MCI. However, using transfer-learning methods, we achieved a test accuracy of 56.08%.</div></div><div><h3>Conclusion</h3><div>Our models achieved state-of-the-art results in the MCI classification task, and demonstrated learning progress in predicting cognitive decline in the preclinical stage. As this is the first time DL models have been evaluated to classify healthy subjects based on cognitive scores, where brain changes are minimal and difficult to detect, this study opens new avenues for discovering biomarkers in early AD diagnosis and facilitating early interventions. Interpretation of the trained DL attention models provided valuable insights that aligned with the existing brain research, serving as a helpful tool for validating AI in healthcare applications.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111538"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146156339","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

A machine learning model to identify pulmonary embolism in patients admitted to intensive care 一种识别重症监护患者肺栓塞的机器学习模型

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-13 DOI: 10.1016/j.compbiomed.2026.111548

Sampath Rapuri , Kirby Gong , Carl Harris , Robert D. Stevens

Background

Pulmonary embolism (PE) is a leading cause of preventable death, yet statistical prediction models have shown inconsistent validity. Our primary objective was to determine if a machine learning model trained with data routinely collected in clinical care can successfully identify acute PE in critically ill patients.

Methods

Leveraging two multicenter datasets acquired nationally (development cohort) and within the Johns Hopkins Health System (external validation cohort), we trained machine learning models with features extracted from demographics, comorbidities, physiologic and laboratory data available following intensive care unit (ICU) admission. The primary endpoint was the identification of acute PE during ICU admission. Model performance was contrasted with two benchmark PE risk scores.

Findings

PE was diagnosed in 2647 of 164,383 (1.61%) and 754 of 64,923 admissions (1.16%) in the development and external validation datasets respectively. Using data from the first 48 h after ICU admission, the mean (95% CI) discrimination measured by area under the receiver characteristic curve (AUROC) was 0.829 (0.808–0.852), 0.704 (0.681–0.727), and 0.667 (0.653–0.681) for our logistic regression machine learning model and for the two benchmark scores, respectively; mean area under the precision recall curve was 0.150 (0.138–0.162), 0.080 (0.071–0.089), and 0.081 (0.071–0.091), respectively. Discrimination was maintained in the external validation dataset with an AUROC of 0.819 (0.802–0.836).

Interpretation

Findings indicate that PE can be detected accurately in ICU patients using routinely collected clinical data. The machine learning model successfully validated and outperformed existing benchmark risk scores. Such a model could become a valuable tool for assessing the likelihood of PE among critically ill patients.

肺栓塞（PE）是可预防死亡的主要原因，但统计预测模型的有效性不一致。我们的主要目的是确定用临床护理中常规收集的数据训练的机器学习模型是否可以成功识别危重患者的急性肺泡。方法利用在全国范围内获得的两个多中心数据集（发展队列）和在约翰霍普金斯卫生系统内获得的数据集（外部验证队列），我们使用从重症监护室（ICU）入院后可获得的人口统计学、合并症、生理和实验室数据中提取的特征来训练机器学习模型。主要终点是ICU入院时急性PE的识别。模型性能与两个基准PE风险评分进行对比。在开发和外部验证数据集中，164,383例患者中有2647例（1.61%）诊断为spe， 64,923例患者中有754例（1.16%）诊断为spe。使用ICU入院后48 h的数据，我们的logistic回归机器学习模型和两个基准评分的受试者特征曲线下面积（AUROC）的平均判别（95% CI）分别为0.829（0.808-0.852）、0.704（0.681-0.727）和0.667 (0.653-0.681)；精密度召回曲线下平均面积分别为0.150（0.138 ~ 0.162）、0.080（0.071 ~ 0.089）和0.081（0.071 ~ 0.091）。在外部验证数据集中保持鉴别性，AUROC为0.819（0.802-0.836）。研究结果表明，使用常规收集的临床资料可以准确地检测出ICU患者的PE。机器学习模型成功验证并优于现有的基准风险评分。这种模型可能成为评估危重患者PE可能性的有价值的工具。

{"title":"A machine learning model to identify pulmonary embolism in patients admitted to intensive care","authors":"Sampath Rapuri , Kirby Gong , Carl Harris , Robert D. Stevens","doi":"10.1016/j.compbiomed.2026.111548","DOIUrl":"10.1016/j.compbiomed.2026.111548","url":null,"abstract":"<div><h3>Background</h3><div>Pulmonary embolism (PE) is a leading cause of preventable death, yet statistical prediction models have shown inconsistent validity. Our primary objective was to determine if a machine learning model trained with data routinely collected in clinical care can successfully identify acute PE in critically ill patients.</div></div><div><h3>Methods</h3><div>Leveraging two multicenter datasets acquired nationally (development cohort) and within the Johns Hopkins Health System (external validation cohort), we trained machine learning models with features extracted from demographics, comorbidities, physiologic and laboratory data available following intensive care unit (ICU) admission. The primary endpoint was the identification of acute PE during ICU admission. Model performance was contrasted with two benchmark PE risk scores.</div></div><div><h3>Findings</h3><div>PE was diagnosed in 2647 of 164,383 (1.61%) and 754 of 64,923 admissions (1.16%) in the development and external validation datasets respectively. Using data from the first 48 h after ICU admission, the mean (95% CI) discrimination measured by area under the receiver characteristic curve (AUROC) was 0.829 (0.808–0.852), 0.704 (0.681–0.727), and 0.667 (0.653–0.681) for our logistic regression machine learning model and for the two benchmark scores, respectively; mean area under the precision recall curve was 0.150 (0.138–0.162), 0.080 (0.071–0.089), and 0.081 (0.071–0.091), respectively. Discrimination was maintained in the external validation dataset with an AUROC of 0.819 (0.802–0.836).</div></div><div><h3>Interpretation</h3><div>Findings indicate that PE can be detected accurately in ICU patients using routinely collected clinical data. The machine learning model successfully validated and outperformed existing benchmark risk scores. Such a model could become a valuable tool for assessing the likelihood of PE among critically ill patients.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111548"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171746","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

Oncogenic β-tubulin mutations disrupt nucleotide-dependent allostery and free energy landscape of tubulin dimer 致癌β-微管蛋白突变破坏了核苷酸依赖性变构和微管蛋白二聚体的自由能格局。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-02 DOI: 10.1016/j.compbiomed.2026.111512

Thasni Fazil , Sharanya C. Suresh , Ravindar Lavoori , Kathiresan Natarajan

Dynamic instability of microtubules arises from nucleotide-dependent conformational changes within the tubulin dimers; however, little is known about the molecular mechanisms linking specific mutations to microtubule dysfunction. Here, we combined molecular-dynamics simulations with multi-parametric analysis to investigate wild-type and four lung cancer-associated β-tubulin mutations: Q134L, D177H, G269S, and Q426E. GTP-bound tubulin dimers exhibited enhanced flexibility in the H1–S2, T5, M-loop, and H7 regions, and strong correlated motions across longitudinal interfaces were observed consistent with an assembly-competent tubulin dimer conformation. Our analyses show that each mutation perturbs tubulin heterodimer stability through distinct mechanisms. Mutations such as Q134L and Q426E mutations loosened tubulin dimer inter-subunit packing and shifted the H7 helix toward open conformations, producing fragmented shallow free energy basins. D177H mutation preserved global stability but the tubulin dimer skewed toward a compact closed state. G269S mutation promoted tighter packing with heterogeneous conformers. These findings identify the core helix H7 as a central pivot linking nucleotide state, local perturbations, and global conformational equilibria. Principal component and free energy analyses reveal that these mutations shift the conformational equilibrium toward flexible, energetically unfavorable states incompatible with stable microtubule formation. Thus, our results provide atomistic insights into how these mutations remodel long-range allosteric communication within the tubulin dimer, offering a structural framework for comprehending the regulation of microtubule dynamics.

微管的动态不稳定性源于微管蛋白二聚体内核苷酸依赖的构象变化；然而，关于特异性突变与微管功能障碍之间的分子机制知之甚少。在这里，我们将分子动力学模拟与多参数分析相结合，研究了野生型和四种肺癌相关的β-微管蛋白突变：Q134L， D177H， G269S和Q426E。gtp结合的微管蛋白二聚体在H1-S2、T5、M-loop和H7区域表现出更强的灵活性，并且在纵向界面上观察到强烈的相关运动，与装配能力强的微管蛋白二聚体构象一致。我们的分析表明，每个突变通过不同的机制扰乱微管蛋白异源二聚体的稳定性。Q134L和Q426E等突变使微管蛋白二聚体亚基间堆积松散，使H7螺旋向开放构象移动，产生碎片状的浅层自由能盆地。D177H突变保持了整体稳定性，但微管蛋白二聚体倾向于紧凑的封闭状态。G269S突变促进异质构象更紧密的排列。这些发现确定核心螺旋H7是连接核苷酸状态、局部扰动和全局构象平衡的中心支点。主成分分析和自由能分析表明，这些突变将构象平衡转移到与稳定微管形成不相容的柔性、能量不利的状态。因此，我们的研究结果为这些突变如何重塑微管蛋白二聚体内的远程变构通讯提供了原子性的见解，为理解微管动力学的调节提供了结构框架。

{"title":"Oncogenic β-tubulin mutations disrupt nucleotide-dependent allostery and free energy landscape of tubulin dimer","authors":"Thasni Fazil , Sharanya C. Suresh , Ravindar Lavoori , Kathiresan Natarajan","doi":"10.1016/j.compbiomed.2026.111512","DOIUrl":"10.1016/j.compbiomed.2026.111512","url":null,"abstract":"<div><div>Dynamic instability of microtubules arises from nucleotide-dependent conformational changes within the tubulin dimers; however, little is known about the molecular mechanisms linking specific mutations to microtubule dysfunction. Here, we combined molecular-dynamics simulations with multi-parametric analysis to investigate wild-type and four lung cancer-associated β-tubulin mutations: Q134L, D177H, G269S, and Q426E. GTP-bound tubulin dimers exhibited enhanced flexibility in the H1–S2, T5, M-loop, and H7 regions, and strong correlated motions across longitudinal interfaces were observed consistent with an assembly-competent tubulin dimer conformation. Our analyses show that each mutation perturbs tubulin heterodimer stability through distinct mechanisms. Mutations such as Q134L and Q426E mutations loosened tubulin dimer inter-subunit packing and shifted the H7 helix toward open conformations, producing fragmented shallow free energy basins. D177H mutation preserved global stability but the tubulin dimer skewed toward a compact closed state. G269S mutation promoted tighter packing with heterogeneous conformers. These findings identify the core helix H7 as a central pivot linking nucleotide state, local perturbations, and global conformational equilibria. Principal component and free energy analyses reveal that these mutations shift the conformational equilibrium toward flexible, energetically unfavorable states incompatible with stable microtubule formation. Thus, our results provide atomistic insights into how these mutations remodel long-range allosteric communication within the tubulin dimer, offering a structural framework for comprehending the regulation of microtubule dynamics.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111512"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146112372","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

Enhancing survival analysis through federated learning in non-IID and scarce data scenarios 通过联邦学习在非iid和稀缺数据场景中增强生存分析。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-19 DOI: 10.1016/j.compbiomed.2026.111558

Patricia A. Apellániz, Juan Parras, Santiago Zazo

Integrating Artificial Intelligence (AI) into Survival Analysis (SA) has advanced predictive modeling in healthcare, enabling precise and personalized predictions of time-to-event outcomes, such as patient survival. However, real-world SA datasets often suffer from data scarcity, heterogeneity, and privacy constraints, which limit the applicability of traditional and modern AI methods. To address these challenges, we propose the Federated Synthetic Data Sharing (FedSDS) framework, which integrates synthetic data generation with Federated Learning (FL). For SA, we leverage SAVAE, a state-of-the-art model for complex datasets. Using the Variational Autoencoder-Bayesian Gaussian Mixture model enhanced with artificial inductive bias, FedSDS generates high-quality synthetic data locally and shares them among nodes, enabling collaborative model training without direct data sharing. FedSDS introduces a biased aggregation strategy that aligns synthetic data with local distributions, outperforming traditional FL methods, such as Federated Average. Validated under independent and identically distributed (IID) and non-IID scenarios, FedSDS mitigates data imbalances and heterogeneity, showing significant performance improvements in scarce and heterogeneous data. The proposed framework offers a scalable and privacy-preserving solution for SA in decentralized environments. By enhancing model generalizability and robustness, FedSDS provides a promising path forward for collaborative analytics in healthcare, paving the way for improved patient outcomes and greater adoption of federated techniques in real-world applications.

将人工智能（AI）集成到生存分析（SA）中，可以在医疗保健领域实现先进的预测建模，实现对事件发生时间（如患者生存）结果的精确和个性化预测。然而，现实世界的人工智能数据集经常受到数据稀缺性、异质性和隐私约束的影响，这限制了传统和现代人工智能方法的适用性。为了应对这些挑战，我们提出了联邦合成数据共享（FedSDS）框架，该框架将合成数据生成与联邦学习（FL）集成在一起。对于SA，我们利用SAVAE，这是一种最先进的复杂数据集模型。FedSDS使用人工归纳偏置增强的变分自编码器-贝叶斯高斯混合模型，在本地生成高质量的合成数据并在节点之间共享，实现了无需直接共享数据的协同模型训练。FedSDS引入了一种有偏差的聚合策略，将合成数据与本地分布对齐，优于传统的FL方法，如Federated Average。在独立和同分布（IID）和非IID场景下验证，FedSDS减轻了数据不平衡和异构性，在稀缺和异构数据中显示出显着的性能改进。提出的框架为分散环境中的SA提供了可扩展和隐私保护的解决方案。通过增强模型的通用性和健壮性，FedSDS为医疗保健领域的协作分析提供了一条很有前途的道路，为改善患者治疗效果和在实际应用程序中更多地采用联合技术铺平了道路。

{"title":"Enhancing survival analysis through federated learning in non-IID and scarce data scenarios","authors":"Patricia A. Apellániz, Juan Parras, Santiago Zazo","doi":"10.1016/j.compbiomed.2026.111558","DOIUrl":"10.1016/j.compbiomed.2026.111558","url":null,"abstract":"<div><div>Integrating Artificial Intelligence (AI) into Survival Analysis (SA) has advanced predictive modeling in healthcare, enabling precise and personalized predictions of time-to-event outcomes, such as patient survival. However, real-world SA datasets often suffer from data scarcity, heterogeneity, and privacy constraints, which limit the applicability of traditional and modern AI methods. To address these challenges, we propose the Federated Synthetic Data Sharing (FedSDS) framework, which integrates synthetic data generation with Federated Learning (FL). For SA, we leverage SAVAE, a state-of-the-art model for complex datasets. Using the Variational Autoencoder-Bayesian Gaussian Mixture model enhanced with artificial inductive bias, FedSDS generates high-quality synthetic data locally and shares them among nodes, enabling collaborative model training without direct data sharing. FedSDS introduces a <em>biased</em> aggregation strategy that aligns synthetic data with local distributions, outperforming traditional FL methods, such as Federated Average. Validated under independent and identically distributed (IID) and non-IID scenarios, FedSDS mitigates data imbalances and heterogeneity, showing significant performance improvements in scarce and heterogeneous data. The proposed framework offers a scalable and privacy-preserving solution for SA in decentralized environments. By enhancing model generalizability and robustness, FedSDS provides a promising path forward for collaborative analytics in healthcare, paving the way for improved patient outcomes and greater adoption of federated techniques in real-world applications.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111558"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146257656","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

Global trends, regional disparities and key determinants of neonatal sepsis: A pan-database analysis from 1990 to 2021 新生儿败血症的全球趋势、地区差异和关键决定因素：1990年至2021年的泛数据库分析

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-08 DOI: 10.1016/j.compbiomed.2026.111537

Zhenglin Chang , Wenhan Cao , Qianjun Li , Yuerong Chen , Youpeng Chen , Haiyang Li , Bingsen Chen , Zhiman Liang , Haojie Wu , Xiujin Han , Guohua Zeng , Zhangkai J. Cheng , Baoqing Sun

Objective

Neonatal sepsis (NS) poses a significant global health challenge, with mortality rates ranging from 11% to 19%. Despite its substantial burden, there is currently a lack of systematic understanding of the global epidemiological trends and influencing factors of NS.

Study design

We conducted a comprehensive pan-database analysis integrating data from 18 international databases across 201 countries (1990-2021). Through advanced statistical modeling, including correlation analyses, risk parsimonious modeling, and confounder adjustments, we examined temporal trends, regional disparities, and key determinants of NS.

Results

While NS prevalence increased annually due to improved detection, age-standardized rates showed consistent declines. For NS incidence, novel correlates included European ancestry (strongest), systolic/diastolic blood pressure, and inverse associations with Human Development Index. We developed a parsimonious model incorporating diastolic blood pressure, Global Hunger Index, and European ancestry, which showed strong cross-regional predictive capability (r = 0.727). For mortality, socioeconomic factors were primary correlates: positive associations with Global Hunger Index and food insecurity, and inverse associations with Inequality Adjusted HDI.

Conclusion

This first comprehensive global analysis reveals that NS outcomes are determined by both medical and socioeconomic factors. While blood pressure metrics and genetic factors influence incidence, mortality is primarily driven by socioeconomic determinants. These findings suggest that reducing NS burden requires a dual approach: enhancing medical care while addressing fundamental socioeconomic disparities, particularly in resource-limited regions.

新生儿败血症（NS）是全球健康面临的重大挑战，其死亡率从11%到19%不等。尽管其负担沉重，但目前对NS的全球流行病学趋势和影响因素缺乏系统的了解。研究设计：我们进行了全面的泛数据库分析，整合了来自201个国家的18个国际数据库（1990-2021）的数据。通过先进的统计模型，包括相关分析、风险简约模型和混杂因素调整，我们研究了时间趋势、区域差异和NS的关键决定因素。结果：虽然由于检测水平的提高，NS患病率逐年上升，但年龄标准化率呈持续下降趋势。对于NS发病率，新的相关因素包括欧洲血统（最强）、收缩压/舒张压，以及与人类发展指数呈负相关。我们建立了一个包含舒张压、全球饥饿指数和欧洲血统的简约模型，显示出很强的跨区域预测能力（r = 0.727）。对于死亡率，社会经济因素是主要相关因素：与全球饥饿指数和粮食不安全呈正相关，与不平等调整的人类发展指数呈负相关。结论：这是第一次全面的全球分析，揭示了NS结果是由医学和社会经济因素共同决定的。虽然血压指标和遗传因素影响发病率，但死亡率主要由社会经济决定因素驱动。这些研究结果表明，减少NS负担需要双重途径：加强医疗保健，同时解决基本的社会经济差距，特别是在资源有限的地区。

{"title":"Global trends, regional disparities and key determinants of neonatal sepsis: A pan-database analysis from 1990 to 2021","authors":"Zhenglin Chang , Wenhan Cao , Qianjun Li , Yuerong Chen , Youpeng Chen , Haiyang Li , Bingsen Chen , Zhiman Liang , Haojie Wu , Xiujin Han , Guohua Zeng , Zhangkai J. Cheng , Baoqing Sun","doi":"10.1016/j.compbiomed.2026.111537","DOIUrl":"10.1016/j.compbiomed.2026.111537","url":null,"abstract":"<div><h3>Objective</h3><div>Neonatal sepsis (NS) poses a significant global health challenge, with mortality rates ranging from 11% to 19%. Despite its substantial burden, there is currently a lack of systematic understanding of the global epidemiological trends and influencing factors of NS.</div></div><div><h3>Study design</h3><div>We conducted a comprehensive pan-database analysis integrating data from 18 international databases across 201 countries (1990-2021). Through advanced statistical modeling, including correlation analyses, risk parsimonious modeling, and confounder adjustments, we examined temporal trends, regional disparities, and key determinants of NS.</div></div><div><h3>Results</h3><div>While NS prevalence increased annually due to improved detection, age-standardized rates showed consistent declines. For NS incidence, novel correlates included European ancestry (strongest), systolic/diastolic blood pressure, and inverse associations with Human Development Index. We developed a parsimonious model incorporating diastolic blood pressure, Global Hunger Index, and European ancestry, which showed strong cross-regional predictive capability (r = 0.727). For mortality, socioeconomic factors were primary correlates: positive associations with Global Hunger Index and food insecurity, and inverse associations with Inequality Adjusted HDI.</div></div><div><h3>Conclusion</h3><div>This first comprehensive global analysis reveals that NS outcomes are determined by both medical and socioeconomic factors. While blood pressure metrics and genetic factors influence incidence, mortality is primarily driven by socioeconomic determinants. These findings suggest that reducing NS burden requires a dual approach: enhancing medical care while addressing fundamental socioeconomic disparities, particularly in resource-limited regions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111537"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146149437","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

Hentriacontane alleviates streptozotocin-induced Alzheimer's disease-like conditions in rats: In silico and in vivo investigations revealed the unifying principles 亨三康烷减轻大鼠链脲佐菌素诱导的阿尔茨海默病样疾病：计算机和体内研究揭示了统一的原则。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-09 DOI: 10.1016/j.compbiomed.2026.111513

Sagar A. More, Awez Sikkalgar, Nayna Chourasiya, Yogeeta O. Agrawal, Sameer N. Goyal, Kartik T. Nakhate, Mohd Usman Mohd Siddique, Sumit S. Rathod

Intracerebroventricular (ICV) streptozotocin (STZ) deveops Alzheimer's disease (AD)-like conditions in rodents, which are characterized by insulin resistance, tau pathology, and neurodegeneration. Hentriacontane, a natural compound found in various sources, including beeswax, possesses anti-inflammatory and antioxidant properties. In the present investigation, we performed in silico molecular docking, molecular dynamics, MMGBSA, PCA, and FEL analysis of hentriacontane and rivastigmine with acetylcholinesterase (AchE). Further, we assessed the in vivo neuroprotective effects of hentriacontane in an ICV-STZ-induced AD-like condition in rats. STZ (3 mg/kg/ICV) was injected into male Sprague-Dawley rats. Cognitive functions were evaluated by Barnes-Maze (BM), novel object recognition test (NORT), and passive avoidance test (PAT). Hentriacontane (3 and 5 mg/kg) and rivastigmine (1 mg/kg) were given intraperitoneally for 14 days. Brain-derived neurotrophic factor (BDNF), AchE, oxidative stress parameters including GSH, MDA, SOD, and CAT, and proinflammatory cytokines including IL-6, TNF-α, IL-1β, and NF-ҡB were measured via ELISA. Further, we have also estimated the BACE1 and NO levels. Histopathological evaluation was conducted using hematoxylin and eosin staining. In silico molecular docking, dynamics, and post-dynamics data revealed promising binding affinities of hentriacontane for AchE. Further, hentriacontane attenuated ICV-STZ-induced cognitive deficit in BM, NORT, and PAT. Additionally, altered oxidative stress, proinflammatory, and cell signalling parameters were restored. Histopathology revealed that the hentriacontane-treated group showed significant restoration of the small pyramidal cells in the CA1 and CA2 regions of the brain. Hentriacontane demonstrated neuroprotective effects by modulation of AchE, leading to improved cognitive functions as evidenced by in silico and in vivo investigations.

脑室内（ICV）链脲佐菌素（STZ）在啮齿动物中发展为阿尔茨海默病（AD）样疾病，其特征是胰岛素抵抗、tau病理和神经变性。亨三康烷是一种天然化合物，存在于各种来源，包括蜂蜡中，具有抗炎和抗氧化特性。在本研究中，我们用乙酰胆碱酯酶（AchE）对hentriacontane和rivastigming进行了硅分子对接、分子动力学、MMGBSA、PCA和FEL分析。此外，我们评估了亨三康烷对icv - stz诱导的ad样大鼠的体内神经保护作用。雄性sd大鼠注射STZ （3 mg/kg/ICV）。采用Barnes-Maze （BM）、新目标识别测试（NORT）和被动回避测试（PAT）评估认知功能。Hentriacontane（3和5 mg/kg）和rivastigming （1 mg/kg）腹腔注射14 d。ELISA法检测脑源性神经营养因子（BDNF）、乙酰胆碱酯酶（AchE）、氧化应激参数GSH、MDA、SOD、CAT和促炎因子IL-6、TNF-α、IL-1β、NF-ҡB。此外，我们还估计了BACE1和NO水平。采用苏木精和伊红染色进行组织病理学评价。硅分子对接、动力学和后动力学数据显示，三康烷对乙酰胆碱具有良好的结合亲和力。此外，hentriacontane减轻了icv - stz诱导的BM， NORT和PAT的认知缺陷。此外，氧化应激、促炎和细胞信号参数的改变也得以恢复。组织病理学显示，hentriacontan处理组显示出大脑CA1和CA2区域的小锥体细胞的显著恢复。Hentriacontane通过调节AchE显示出神经保护作用，导致认知功能的改善，这在计算机和体内研究中得到了证明。

{"title":"Hentriacontane alleviates streptozotocin-induced Alzheimer's disease-like conditions in rats: In silico and in vivo investigations revealed the unifying principles","authors":"Sagar A. More, Awez Sikkalgar, Nayna Chourasiya, Yogeeta O. Agrawal, Sameer N. Goyal, Kartik T. Nakhate, Mohd Usman Mohd Siddique, Sumit S. Rathod","doi":"10.1016/j.compbiomed.2026.111513","DOIUrl":"10.1016/j.compbiomed.2026.111513","url":null,"abstract":"<div><div>Intracerebroventricular (ICV) streptozotocin (STZ) deveops Alzheimer's disease (AD)-like conditions in rodents, which are characterized by insulin resistance, tau pathology, and neurodegeneration. Hentriacontane, a natural compound found in various sources, including beeswax, possesses anti-inflammatory and antioxidant properties. In the present investigation, we performed <em>in silico</em> molecular docking, molecular dynamics, MMGBSA, PCA, and FEL analysis of hentriacontane and rivastigmine with acetylcholinesterase (AchE). Further, we assessed the <em>in vivo</em> neuroprotective effects of hentriacontane in an ICV-STZ-induced AD-like condition in rats. STZ (3 mg/kg/ICV) was injected into male Sprague-Dawley rats. Cognitive functions were evaluated by Barnes-Maze (BM), novel object recognition test (NORT), and passive avoidance test (PAT). Hentriacontane (3 and 5 mg/kg) and rivastigmine (1 mg/kg) were given intraperitoneally for 14 days. Brain-derived neurotrophic factor (BDNF), AchE, oxidative stress parameters including GSH, MDA, SOD, and CAT, and proinflammatory cytokines including IL-6, TNF-α, IL-1β, and NF-ҡB were measured via ELISA. Further, we have also estimated the BACE1 and NO levels. Histopathological evaluation was conducted using hematoxylin and eosin staining. <em>In silico</em> molecular docking, dynamics, and post-dynamics data revealed promising binding affinities of hentriacontane for AchE. Further, hentriacontane attenuated ICV-STZ-induced cognitive deficit in BM, NORT, and PAT. Additionally, altered oxidative stress, proinflammatory, and cell signalling parameters were restored. Histopathology revealed that the hentriacontane-treated group showed significant restoration of the small pyramidal cells in the CA1 and CA2 regions of the brain. Hentriacontane demonstrated neuroprotective effects by modulation of AchE, leading to improved cognitive functions as evidenced by <em>in silico</em> and <em>in vivo</em> investigations.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111513"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146156371","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

Multi-structure CT radiomics-based consensus model for the diagnosis of pancreatic ductal adenocarcinoma and vascular involvement 基于多结构CT放射组学的胰腺导管腺癌及血管累及诊断共识模型。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-09 DOI: 10.1016/j.compbiomed.2026.111542

Jia Peng , Shiyao Xie , Xinnan Liao , Mengnan Tai , Zixuan Nie , Yaoqi Wang , Zhiyuan Chen , Zheng Wang , Ya Peng

Background

Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal malignancy, with accurate preoperative assessment of vascular involvement critical for determining resectability and treatment planning. Conventional contrast-enhanced CT relies on qualitative evaluations, leading to interobserver variability and diagnostic uncertainty. Existing radiomics studies for PDAC mostly focus on single anatomical structures and lack organ-level interpretability, limiting clinical translation.

Methods

A retrospective study was conducted using the international PANORAMA CT cohort, with 1488 eligible samples stratified into PDAC diagnosis (1186 cases) and vascular involvement prediction (302 cases) tasks. Standardized radiomic features were extracted from five key structures (artery, vein, pancreatic parenchyma, pancreatic duct, common bile duct) following IBSI guidelines. After LASSO-based dimensionality reduction, six machine learning classifiers were trained for each structure, with top-performing models integrated into structure-specific consensus models. A meta-level consensus model was constructed via stacking, and SHAP analysis was applied for organ-level interpretability. Model performance was evaluated using AUC, accuracy, calibration curves, and decision curve analysis (DCA).

Results

The multi-structure consensus model achieved an AUC of 0.975 (95% CI: 0.956–0.990) with 0.937 accuracy for PDAC diagnosis, and an AUC of 0.868 (95% CI: 0.769–0.952) with 0.803 accuracy for vascular involvement prediction in independent testing cohorts. DeLong tests demonstrated the model significantly outperformed four single-structure models (artery, vein, pancreatic duct, common bile duct) in both tasks (all P < 0.05), with no significant difference compared to the pancreas parenchyma model (PDAC diagnosis: P = 0.078; vascular involvement prediction: P = 0.093). SHAP analysis identified pancreatic parenchyma as the dominant contributor to PDAC diagnosis and arterial features as key for vascular involvement prediction. The model exhibited robust calibration (MAE = 0.01 for PDAC; MAE = 0.02 for vascular involvement) and clinical net benefit via DCA.

Conclusion

The proposed multi-structure CT radiomics consensus model integrates contextual information from multiple pancreatic structures, achieving competitive performance for PDAC diagnosis and vascular involvement prediction. Organ-level SHAP interpretation enhances clinical transparency, offering a reliable tool to support preoperative decision-making in PDAC.

背景：胰腺导管腺癌（Pancreatic ductal adencarcinoma， PDAC）是一种高致死率的恶性肿瘤，术前准确评估血管受累情况对确定可切除性和治疗计划至关重要。传统的对比增强CT依赖于定性评估，导致观察者之间的差异和诊断的不确定性。现有的放射组学研究主要集中在单个解剖结构上，缺乏器官水平的可解释性，限制了临床翻译。方法：采用国际PANORAMA CT队列进行回顾性研究，1488例符合条件的样本分为PDAC诊断（1186例）和血管受累预测（302例）任务。按照IBSI指南提取5个关键结构（动脉、静脉、胰腺实质、胰管、胆总管）的标准化放射学特征。在基于lasso的降维之后，为每个结构训练了六个机器学习分类器，其中表现最好的模型集成到特定于结构的共识模型中。通过堆叠构建了元水平共识模型，并采用SHAP分析对器官水平的可解释性进行分析。使用AUC、精度、校准曲线和决策曲线分析（DCA）评估模型性能。结果：多结构共识模型在PDAC诊断中的AUC为0.975 (95% CI: 0.956-0.990)，准确率为0.937；在独立测试队列中，血管受损伤预测的AUC为0.868 (95% CI: 0.769-0.952)，准确率为0.803。DeLong测试表明，该模型在两项任务中都明显优于四种单结构模型（动脉、静脉、胰管、胆总管）（均为P）。结论：所提出的多结构CT放射组学共识模型集成了来自多个胰腺结构的上下文信息，在PDAC诊断和血管受累预测方面具有竞争力。器官水平的SHAP解释提高了临床透明度，为支持PDAC的术前决策提供了可靠的工具。

{"title":"Multi-structure CT radiomics-based consensus model for the diagnosis of pancreatic ductal adenocarcinoma and vascular involvement","authors":"Jia Peng , Shiyao Xie , Xinnan Liao , Mengnan Tai , Zixuan Nie , Yaoqi Wang , Zhiyuan Chen , Zheng Wang , Ya Peng","doi":"10.1016/j.compbiomed.2026.111542","DOIUrl":"10.1016/j.compbiomed.2026.111542","url":null,"abstract":"<div><h3>Background</h3><div>Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal malignancy, with accurate preoperative assessment of vascular involvement critical for determining resectability and treatment planning. Conventional contrast-enhanced CT relies on qualitative evaluations, leading to interobserver variability and diagnostic uncertainty. Existing radiomics studies for PDAC mostly focus on single anatomical structures and lack organ-level interpretability, limiting clinical translation.</div></div><div><h3>Methods</h3><div>A retrospective study was conducted using the international PANORAMA CT cohort, with 1488 eligible samples stratified into PDAC diagnosis (1186 cases) and vascular involvement prediction (302 cases) tasks. Standardized radiomic features were extracted from five key structures (artery, vein, pancreatic parenchyma, pancreatic duct, common bile duct) following IBSI guidelines. After LASSO-based dimensionality reduction, six machine learning classifiers were trained for each structure, with top-performing models integrated into structure-specific consensus models. A meta-level consensus model was constructed via stacking, and SHAP analysis was applied for organ-level interpretability. Model performance was evaluated using AUC, accuracy, calibration curves, and decision curve analysis (DCA).</div></div><div><h3>Results</h3><div>The multi-structure consensus model achieved an AUC of 0.975 (95% CI: 0.956–0.990) with 0.937 accuracy for PDAC diagnosis, and an AUC of 0.868 (95% CI: 0.769–0.952) with 0.803 accuracy for vascular involvement prediction in independent testing cohorts. DeLong tests demonstrated the model significantly outperformed four single-structure models (artery, vein, pancreatic duct, common bile duct) in both tasks (all P < 0.05), with no significant difference compared to the pancreas parenchyma model (PDAC diagnosis: P = 0.078; vascular involvement prediction: P = 0.093). SHAP analysis identified pancreatic parenchyma as the dominant contributor to PDAC diagnosis and arterial features as key for vascular involvement prediction. The model exhibited robust calibration (MAE = 0.01 for PDAC; MAE = 0.02 for vascular involvement) and clinical net benefit via DCA.</div></div><div><h3>Conclusion</h3><div>The proposed multi-structure CT radiomics consensus model integrates contextual information from multiple pancreatic structures, achieving competitive performance for PDAC diagnosis and vascular involvement prediction. Organ-level SHAP interpretation enhances clinical transparency, offering a reliable tool to support preoperative decision-making in PDAC.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111542"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146156501","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

Topology-aware multiclass segmentation of the Circle of Willis from MRA and CTA images 基于拓扑感知的MRA和CTA图像中Willis环的多类分割。

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-03-01 Epub Date: 2026-02-03 DOI: 10.1016/j.compbiomed.2026.111516

Rachika E. Hamadache, Clara Lisazo, Cansu Yalcin, Uma M. Lal-Trehan Estrada, Valeriia Abramova, Adrià Casamitjana, Arnau Oliver, Xavier Lladó

The Circle of Willis (CoW) is an essential network of arteries that ensures blood flow throughout the brain. From a clinical perspective, evaluating the vessels of the CoW is highly relevant as its angioarchitecture and variants are important biomarkers of neurovascular pathologies. However, achieving a topologically accurate segmentation of these vessels remains challenging due to their anatomical complexity. In this work, we propose a pipeline for the multiclass segmentation of the CoW vessels (13 possible classes), focusing on achieving both topology correctness and segmentation accuracy in magnetic resonance angiography (MRA) and computed tomography angiography (CTA) imaging techniques. We propose a deep learning framework based on the nnUNet model, together with a post-processing block that requires no additional training and that is adapted to the specific multiclass CoW segmentation task. We train and validate our framework using the publicly available TopCoW 2024 dataset (MRA and CTA) and evaluate it on the hidden test set (through an online system) and on an independent subset from the CROWN 2023 challenge dataset (MRA). The obtained results demonstrate the positive impact of our approach, achieving an average Dice (centerline Dice) scores of 0.90 (0.99) for MRA and 0.88 (0.99) for CTA on the in-domain test set, and 0.81 (0.97) on the out-of-domain test set for MRA. These high performances align with state-of-the-art methods, and rank among the top in the TopCoW 2024 challenge. The approach is publicly available for the research community at https://github.com/NIC-VICOROB/CoW-multiclass-segmentation-TopCoW24.

威利斯圈（CoW）是一个重要的动脉网络，确保血液在整个大脑中流动。从临床角度来看，评估CoW的血管是高度相关的，因为其血管结构和变异是神经血管病变的重要生物标志物。然而，由于其解剖复杂性，实现这些血管的拓扑精确分割仍然具有挑战性。在这项工作中，我们提出了一个用于CoW血管多类别分割的管道（13个可能的类别），重点是在磁共振血管成像（MRA）和计算机断层血管成像（CTA）成像技术中实现拓扑正确性和分割准确性。我们提出了一个基于nnUNet模型的深度学习框架，以及一个不需要额外训练的后处理块，该后处理块适用于特定的多类CoW分割任务。我们使用公开可用的TopCoW 2024数据集（MRA和CTA）训练和验证我们的框架，并在隐藏测试集（通过在线系统）和来自CROWN 2023挑战数据集（MRA）的独立子集上对其进行评估。得到的结果证明了我们的方法的积极影响，在域内测试集中，MRA的平均Dice（中心线Dice）得分为0.90 (0.99)，CTA的平均Dice (0.88) (0.99)， MRA的域外测试集中的平均Dice(0.81)（0.97）。这些高性能与最先进的方法相一致，并在TopCoW 2024挑战中名列前茅。该方法可在研究社区的https://github.com/NIC-VICOROB/CoW-multiclass-segmentation-TopCoW24上公开获取。

{"title":"Topology-aware multiclass segmentation of the Circle of Willis from MRA and CTA images","authors":"Rachika E. Hamadache, Clara Lisazo, Cansu Yalcin, Uma M. Lal-Trehan Estrada, Valeriia Abramova, Adrià Casamitjana, Arnau Oliver, Xavier Lladó","doi":"10.1016/j.compbiomed.2026.111516","DOIUrl":"10.1016/j.compbiomed.2026.111516","url":null,"abstract":"<div><div>The Circle of Willis (CoW) is an essential network of arteries that ensures blood flow throughout the brain. From a clinical perspective, evaluating the vessels of the CoW is highly relevant as its angioarchitecture and variants are important biomarkers of neurovascular pathologies. However, achieving a topologically accurate segmentation of these vessels remains challenging due to their anatomical complexity. In this work, we propose a pipeline for the multiclass segmentation of the CoW vessels (13 possible classes), focusing on achieving both topology correctness and segmentation accuracy in magnetic resonance angiography (MRA) and computed tomography angiography (CTA) imaging techniques. We propose a deep learning framework based on the nnUNet model, together with a post-processing block that requires no additional training and that is adapted to the specific multiclass CoW segmentation task. We train and validate our framework using the publicly available TopCoW 2024 dataset (MRA and CTA) and evaluate it on the hidden test set (through an online system) and on an independent subset from the CROWN 2023 challenge dataset (MRA). The obtained results demonstrate the positive impact of our approach, achieving an average Dice (centerline Dice) scores of 0.90 (0.99) for MRA and 0.88 (0.99) for CTA on the in-domain test set, and 0.81 (0.97) on the out-of-domain test set for MRA. These high performances align with state-of-the-art methods, and rank among the top in the TopCoW 2024 challenge. The approach is publicly available for the research community at <span><span>https://github.com/NIC-VICOROB/CoW-multiclass-segmentation-TopCoW24</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111516"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146118163","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