Pub Date : 2026-01-05DOI: 10.1016/j.compbiomed.2025.111402
Sevak Ram Sahu , Parimita Roy , Ranjit Kumar Upadhyay
The onset and progression of Alzheimer’s disease (AD) have long been strongly associated with obesity and diabetes caused by hyperglycemia, which leads to beta-cell dysfunction and insulin imbalance. This imbalance promotes the release of cytokines and activation of microglia, which play a crucial role in the production of amyloid-beta and neurofibrillary tangles. In this context, we formulate a delayed reaction-diffusion model of obesity induced AD to examine the dynamical behavior of the above biological hypothesis. We investigate the existence and uniqueness of solutions, stability of equilibria (local and global), sensitivity analysis as well as the occurrence of Hopf bifurcation and Turing instability. The findings highlight the importance of insulin diffusion rate, insulin secretion delay, glucose, and beta cell in developing AD and its effective control strategies. Spatiotemporal dynamics such as patchy patterns exhibit how accumulates and spreads in the brain. A higher growth rate of beta cell supports sufficient insulin secretion, which can delay the progression of AD. In contrast, when beta cell growth is impaired, even a slight delay in secretion can accelerate disease progression. This study reveals that maintaining high-calorie food to support sufficient growth of beta cell and insulin for a long-term healthy lifestyle along with targeted anti-amyloid approaches can remarkably delay Alzheimer’s progression.
{"title":"Unraveling the link between beta cell dysfunction, insulin imbalance, and neurodegeneration in Alzheimer’s disease","authors":"Sevak Ram Sahu , Parimita Roy , Ranjit Kumar Upadhyay","doi":"10.1016/j.compbiomed.2025.111402","DOIUrl":"10.1016/j.compbiomed.2025.111402","url":null,"abstract":"<div><div>The onset and progression of Alzheimer’s disease (AD) have long been strongly associated with obesity and diabetes caused by hyperglycemia, which leads to beta-cell dysfunction and insulin imbalance. This imbalance promotes the release of cytokines and activation of microglia, which play a crucial role in the production of amyloid-beta and neurofibrillary tangles. In this context, we formulate a delayed reaction-diffusion model of obesity induced AD to examine the dynamical behavior of the above biological hypothesis. We investigate the existence and uniqueness of solutions, stability of equilibria (local and global), sensitivity analysis as well as the occurrence of Hopf bifurcation and Turing instability. The findings highlight the importance of insulin diffusion rate, insulin secretion delay, glucose, and beta cell in developing AD and its effective control strategies. Spatiotemporal dynamics such as patchy patterns exhibit how <span><math><msub><mi>A</mi><mrow><mi>β</mi></mrow></msub></math></span> accumulates and spreads in the brain. A higher growth rate of beta cell supports sufficient insulin secretion, which can delay the progression of AD. In contrast, when beta cell growth is impaired, even a slight delay in secretion can accelerate disease progression. This study reveals that maintaining high-calorie food to support sufficient growth of beta cell and insulin for a long-term healthy lifestyle along with targeted anti-amyloid approaches can remarkably delay Alzheimer’s progression.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111402"},"PeriodicalIF":6.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145910863","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}
Pub Date : 2026-01-05DOI: 10.1016/j.compbiomed.2025.111435
Luca Crugnola , Chiara Catalano , Laura Fusini , Salvatore Pasta , Gianluca Pontone , Christian Vergara
Introduced as an alternative to open-heart surgery for elderly patients, Transcatheter Aortic Valve Implantation (TAVI) has recently been extended to younger patients due to comparable performance with the gold-standard. However, the long-term durability of the bio-prosthetic TAVI valves is limited by Structural Valve Deterioration (SVD), an inevitable degenerative process whose pathogenesis is still unclear. In this study, we aim to computationally investigate a possible relationship between aortic hemodynamics and SVD development. To this aim, we collect data from twelve patients with and without SVD at long-term follow-up exams. Starting from pre-operative clinical images, we build early post-operative virtual geometries and perform Computational Fluid Dynamics simulations by prescribing a personalized flow rate based on Echo Doppler data. In order to identify a premature onset of SVD, we propose three computational hemodynamic indices: Wall Damage Index (), Leaflet Delamination Index (), and Leaflet Permeability Index (). Additionally, to each index we associate a score and, using the Wilcoxon rank-sum test, we find that each score individually shows a statistically greater median value in the SVD sub-population (: , : , : ). Finally, we define a synthetic scoring system that clearly separates between SVD and non-SVD patients. Our results suggest that aortic hemodynamics may drive a premature onset of SVD, and the synthetic score could potentially assist clinicians in a patient-specific planning of follow-up exams to closely monitor those patients at high SVD risk.
{"title":"Personalized computational hemodynamic analysis in transcatheter aortic valve: investigation of long-term degeneration","authors":"Luca Crugnola , Chiara Catalano , Laura Fusini , Salvatore Pasta , Gianluca Pontone , Christian Vergara","doi":"10.1016/j.compbiomed.2025.111435","DOIUrl":"10.1016/j.compbiomed.2025.111435","url":null,"abstract":"<div><div>Introduced as an alternative to open-heart surgery for elderly patients, Transcatheter Aortic Valve Implantation (TAVI) has recently been extended to younger patients due to comparable performance with the gold-standard. However, the long-term durability of the bio-prosthetic TAVI valves is limited by Structural Valve Deterioration (SVD), an inevitable degenerative process whose pathogenesis is still unclear. In this study, we aim to computationally investigate a possible relationship between aortic hemodynamics and SVD development. To this aim, we collect data from twelve patients with and without SVD at long-term follow-up exams. Starting from pre-operative clinical images, we build early post-operative virtual geometries and perform Computational Fluid Dynamics simulations by prescribing a personalized flow rate based on Echo Doppler data. In order to identify a premature onset of SVD, we propose three computational hemodynamic indices: Wall Damage Index (<span><math><mi>W</mi><mi>D</mi><mi>I</mi></math></span>), Leaflet Delamination Index (<span><math><mi>L</mi><mi>D</mi><mi>I</mi></math></span>), and Leaflet Permeability Index (<span><math><mi>L</mi><mi>P</mi><mi>I</mi></math></span>). Additionally, to each index we associate a score and, using the Wilcoxon rank-sum test, we find that each score individually shows a statistically greater median value in the SVD sub-population (<span><math><mi>W</mi><mi>D</mi><mi>I</mi></math></span>: <span><math><mi>p</mi><mo>=</mo><mn>0.008</mn></math></span>, <span><math><mi>L</mi><mi>D</mi><mi>I</mi></math></span>: <span><math><mi>p</mi><mo>=</mo><mn>0.001</mn></math></span>, <span><math><mi>L</mi><mi>P</mi><mi>I</mi></math></span>: <span><math><mi>p</mi><mo>=</mo><mn>0.020</mn></math></span>). Finally, we define a synthetic scoring system that clearly separates between SVD and non-SVD patients. Our results suggest that aortic hemodynamics may drive a premature onset of SVD, and the synthetic score could potentially assist clinicians in a patient-specific planning of follow-up exams to closely monitor those patients at high SVD risk.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111435"},"PeriodicalIF":6.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145910788","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}
Pub Date : 2026-01-05DOI: 10.1016/j.compbiomed.2025.111432
Henk van Voorst , Jiahang Su , Praneeta R. Konduri , Charles B.L.M. Majoie , Yvo B.W.E.M. Roos , Bart J. Emmer , Henk A. Marquering , Bob D. de Vos , Matthan W.A. Caan , Ivana Išgum , On behalf of the MR CLEAN Registry collaborators
Automated vessel segmentation in brain CT angiography (CTA) remains challenging despite the potential benefits of its applications. Expert acquisition of reference vessel segmentations is a laborious task. We propose an unsupervised generative deep learning approach that can be trained for vessel segmentation in brain CTA using a large dataset (n=908) of unlabelled brain CTAs and non-contrast enhanced CTs (NCCTs). Our semi-supervised approach uses a conditional generative adversarial network (GAN) for CTA to NCCT translation by generating a contrast map that allows for automatic extraction of vessel segmentations. Furthermore, we propose a 3D Frangi filter-based loss function to enhance tubular structures in the contrast map to improve vessel segmentations. We used a hold-out test set of 9 CTA volumes with manually annotated reference segmentations. We compared our semi-supervised approach with a state-of-the-art supervised nnUnet, trained and evaluated with test set using 9-fold nested cross-validation. Evaluation metrics included voxel-wise Dice similarity coefficient (DSC), true positive rate (TPR), and false positive rate (FPR). The DSC was 4 % lower for the semi-supervised approach (DSC: 0.74) compared to the supervised nnUnet (DSC: 0.78). Both the TPR and FPR were higher for the semi-supervised approach (TPR: 0.75, FPR/1000 voxels:2.05) compared to the supervised nnUnet (TPR:0.71, FPR/1000 voxels:0.87). Hence, the quantitative results showed that our semi-supervised method approaches a supervised state-of-the-art segmentation network. The results demonstrate that a semi-supervised generative deep learning approach for the segmentation of intracranial vessels is feasible without laborious manual segmentations.
{"title":"Deep generative models for vessel segmentation in CT angiography of the brain","authors":"Henk van Voorst , Jiahang Su , Praneeta R. Konduri , Charles B.L.M. Majoie , Yvo B.W.E.M. Roos , Bart J. Emmer , Henk A. Marquering , Bob D. de Vos , Matthan W.A. Caan , Ivana Išgum , On behalf of the MR CLEAN Registry collaborators","doi":"10.1016/j.compbiomed.2025.111432","DOIUrl":"10.1016/j.compbiomed.2025.111432","url":null,"abstract":"<div><div>Automated vessel segmentation in brain CT angiography (CTA) remains challenging despite the potential benefits of its applications. Expert acquisition of reference vessel segmentations is a laborious task. We propose an unsupervised generative deep learning approach that can be trained for vessel segmentation in brain CTA using a large dataset (n=908) of unlabelled brain CTAs and non-contrast enhanced CTs (NCCTs). Our semi-supervised approach uses a conditional generative adversarial network (GAN) for CTA to NCCT translation by generating a contrast map that allows for automatic extraction of vessel segmentations. Furthermore, we propose a 3D Frangi filter-based loss function to enhance tubular structures in the contrast map to improve vessel segmentations. We used a hold-out test set of 9 CTA volumes with manually annotated reference segmentations. We compared our semi-supervised approach with a state-of-the-art supervised nnUnet, trained and evaluated with test set using 9-fold nested cross-validation. Evaluation metrics included voxel-wise Dice similarity coefficient (DSC), true positive rate (TPR), and false positive rate (FPR). The DSC was 4 % lower for the semi-supervised approach (DSC: 0.74) compared to the supervised nnUnet (DSC: 0.78). Both the TPR and FPR were higher for the semi-supervised approach (TPR: 0.75, FPR/1000 voxels:2.05) compared to the supervised nnUnet (TPR:0.71, FPR/1000 voxels:0.87). Hence, the quantitative results showed that our semi-supervised method approaches a supervised state-of-the-art segmentation network. The results demonstrate that a semi-supervised generative deep learning approach for the segmentation of intracranial vessels is feasible without laborious manual segmentations.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111432"},"PeriodicalIF":6.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145910849","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}
Pub Date : 2026-01-05DOI: 10.1016/j.compbiomed.2025.111418
R. Ritmaleni , K. Kuswandi , M. Ikawati , C.N. Apsari , T.M. Fakih , M. Thamim , K. Thirumoorthy
Breast cancer (BC) remains one of the leading cause of mortality among women worldwide, with no universally effective treatment available despite the development of various therapeutic approaches. This study sought to address this gap by synthesizing potential anticancer agents derived from natural phenolic compounds. These compounds were reacted with 3,4,5-trimethoxybenzoyl chloride to generate novel derivatives, termed natural phenolic-3,4,5-trimethoxybenzoates. To evaluate their therapeutic potential, molecular docking, molecular dynamics simulations, and MM/PBSA free energy binding calculations were performed. Among the synthesized derivatives, sesamol-3,4,5-trimethoxybenzoate, thymol-3,4,5-trimethoxybenzoate, carvacrol-3,4,5-trimethoxybenzoate, and umbelliferone-3,4,5-trimethoxybenzoate demonstrated the most promising binding affinities, with MM/PBSA free energy values of −151.377 kJ/mol, −137.344 kJ/mol, −136.645 kJ/mol, and −131.628 kJ/mol, respectively. These results indicate strong and specific interactions with cancer cell receptors, suggesting their potential as effective therapeutic agents. Furthermore, molecular dynamics analyses including RMSD, RMSF, SASA, Rg, and RDF confirmed the stability of these compounds, further enhancing their candidacy as viable drug leads. This study underscores the critical role of computational techniques in drug discovery, offering valuable insights into molecular interactions and stability prior to experimental validation. By identifying promising natural compound derivatives, specifically natural phenolic-3,4,5-trimethoxybenzoates, this research establishes a foundation for developing targeted and effective treatments for BC. Overall, these findings highlight the potential of computational approaches in oncology drug development and pave the way for future in vitro and in vivo studies to confirm therapeutic efficacy.
{"title":"Computational investigation of natural phenolic-3,4,5-trimethoxybenzoates as potential anticancer agent targeting estrogen receptor alpha","authors":"R. Ritmaleni , K. Kuswandi , M. Ikawati , C.N. Apsari , T.M. Fakih , M. Thamim , K. Thirumoorthy","doi":"10.1016/j.compbiomed.2025.111418","DOIUrl":"10.1016/j.compbiomed.2025.111418","url":null,"abstract":"<div><div>Breast cancer (BC) remains one of the leading cause of mortality among women worldwide, with no universally effective treatment available despite the development of various therapeutic approaches. This study sought to address this gap by synthesizing potential anticancer agents derived from natural phenolic compounds. These compounds were reacted with 3,4,5-trimethoxybenzoyl chloride to generate novel derivatives, termed natural phenolic-3,4,5-trimethoxybenzoates. To evaluate their therapeutic potential, molecular docking, molecular dynamics simulations, and MM/PBSA free energy binding calculations were performed. Among the synthesized derivatives, sesamol-3,4,5-trimethoxybenzoate, thymol-3,4,5-trimethoxybenzoate, carvacrol-3,4,5-trimethoxybenzoate, and umbelliferone-3,4,5-trimethoxybenzoate demonstrated the most promising binding affinities, with MM/PBSA free energy values of −151.377 kJ/mol, −137.344 kJ/mol, −136.645 kJ/mol, and −131.628 kJ/mol, respectively. These results indicate strong and specific interactions with cancer cell receptors, suggesting their potential as effective therapeutic agents. Furthermore, molecular dynamics analyses including RMSD, RMSF, SASA, Rg, and RDF confirmed the stability of these compounds, further enhancing their candidacy as viable drug leads. This study underscores the critical role of computational techniques in drug discovery, offering valuable insights into molecular interactions and stability prior to experimental validation. By identifying promising natural compound derivatives, specifically natural phenolic-3,4,5-trimethoxybenzoates, this research establishes a foundation for developing targeted and effective treatments for BC. Overall, these findings highlight the potential of computational approaches in oncology drug development and pave the way for future in vitro and in vivo studies to confirm therapeutic efficacy.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111418"},"PeriodicalIF":6.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145910791","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}
Pub Date : 2026-01-05DOI: 10.1016/j.compbiomed.2026.111452
Kirstie Wong Chee Ching, Noor Fatmawati Mokhtar, Gee Jun Tye
{"title":"Erratum to \"Identification of significant hub genes and pathways associated with metastatic breast cancer and tolerogenic dendritic cell via bioinformatics analysis\" [Comput. Biol. Med. 184, (January 2025), 109396].","authors":"Kirstie Wong Chee Ching, Noor Fatmawati Mokhtar, Gee Jun Tye","doi":"10.1016/j.compbiomed.2026.111452","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2026.111452","url":null,"abstract":"","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":" ","pages":"111452"},"PeriodicalIF":6.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145910829","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}
Pub Date : 2026-01-03DOI: 10.1016/j.compbiomed.2025.111419
Xhesina Hita , Farrukh Javed , Stefano Lodi
Accurate and early detection of Acute Lymphoblastic Leukemia (ALL) is critical for timely intervention and improved patient outcomes. However, the development of reliable deep learning models for hematological image analysis is challenged by limited data availability, dataset bias, and the need for trustworthy predictions in clinical settings. In this study, we propose a Bayesian deep learning framework that integrates transfer learning, data augmentation, and uncertainty quantification for robust classification of leukemic and healthy lymphocytes from peripheral blood smear images. Three widely used convolutional neural network architectures, InceptionV3, VGG16, and ResNet50, pretrained on ImageNet are fine-tuned on the ALL-IDB2 dataset and extended with Monte Carlo dropout to enable Bayesian inference. Model performance is evaluated using 10-fold cross-validation on both original and augmented datasets, with accuracy, sensitivity, specificity, Youden’s index, and Brier score used as evaluation metrics. Among the evaluated models, VGG16 demonstrates the most consistent improvements under data augmentation, achieving the highest accuracy (), Youden’s index () and Brier score (), while ResNet50 shows strong but more moderate gains. In contrast, InceptionV3 exhibits limited sensitivity to augmentation and comparatively lower robustness. Beyond average predictive performance, Bayesian uncertainty analysis reveals that misclassifications and borderline predictions are consistently associated with elevated predictive entropy and mutual information. Saliency map inspection further indicates that high-uncertainty cases correspond to diffuse or non-localized attention patterns, suggesting reliance on spurious contextual features rather than stable morphological cues. These findings highlight the importance of uncertainty-aware predictions for identifying cases that may require expert pathological review. Overall, the proposed framework combines strong diagnostic performance with interpretable uncertainty estimates, supporting its role as a transparent and clinically trustworthy tool for AI-assisted leukemia screening.
{"title":"Reliable leukemia detection via transfer-enhanced Bayesian CNNs","authors":"Xhesina Hita , Farrukh Javed , Stefano Lodi","doi":"10.1016/j.compbiomed.2025.111419","DOIUrl":"10.1016/j.compbiomed.2025.111419","url":null,"abstract":"<div><div>Accurate and early detection of Acute Lymphoblastic Leukemia (ALL) is critical for timely intervention and improved patient outcomes. However, the development of reliable deep learning models for hematological image analysis is challenged by limited data availability, dataset bias, and the need for trustworthy predictions in clinical settings. In this study, we propose a Bayesian deep learning framework that integrates transfer learning, data augmentation, and uncertainty quantification for robust classification of leukemic and healthy lymphocytes from peripheral blood smear images. Three widely used convolutional neural network architectures, InceptionV3, VGG16, and ResNet50, pretrained on ImageNet are fine-tuned on the ALL-IDB2 dataset and extended with Monte Carlo dropout to enable Bayesian inference. Model performance is evaluated using 10-fold cross-validation on both original and augmented datasets, with accuracy, sensitivity, specificity, Youden’s index, and Brier score used as evaluation metrics. Among the evaluated models, VGG16 demonstrates the most consistent improvements under data augmentation, achieving the highest accuracy (<span><math><mn>98.65</mn><mi>%</mi><mo>±</mo><mn>0.09</mn></math></span>), Youden’s index (<span><math><mn>0.97</mn><mo>±</mo><mn>0.001</mn></math></span>) and Brier score (<span><math><mn>0.035</mn><mo>±</mo><mn>0.010</mn></math></span>), while ResNet50 shows strong but more moderate gains. In contrast, InceptionV3 exhibits limited sensitivity to augmentation and comparatively lower robustness. Beyond average predictive performance, Bayesian uncertainty analysis reveals that misclassifications and borderline predictions are consistently associated with elevated predictive entropy and mutual information. Saliency map inspection further indicates that high-uncertainty cases correspond to diffuse or non-localized attention patterns, suggesting reliance on spurious contextual features rather than stable morphological cues. These findings highlight the importance of uncertainty-aware predictions for identifying cases that may require expert pathological review. Overall, the proposed framework combines strong diagnostic performance with interpretable uncertainty estimates, supporting its role as a transparent and clinically trustworthy tool for AI-assisted leukemia screening.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111419"},"PeriodicalIF":6.3,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883525","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}
Pub Date : 2026-01-02DOI: 10.1016/j.compbiomed.2025.111433
Hailah M. Almohaimeed , Amany I. Almars , Nada Alkhorayef , Ahmed M. Basri , Fayez Alsulaimani , Muhammad Shahbaz , Fahad M. Alshabrmi , Sarfaraz Alam , Tahir Muhammad , Muhammad Shahab
Enterovirus D68 (EV-D68) is an enterovirus known for causing respiratory infections, as well as flaccid myelitis, meningitis and encephalitis. Despite the efforts, no licensed vaccine against EV-D68 is currently available. Vaccine development efforts are ongoing; however, the process is complex and requires extensive clinical validation. In contrast, immunoinformatic is a rapidly expanding area with the potential to significantly influence the therapeutic interventions and vaccine development for infectious diseases. Herein, immunoinformatic and reverse vaccinology strategies were utilized to design a multi-epitope vaccine construct targeting EV-D68 virus. In this connection, three virulent proteins were selected for analysis based on their immunogenic characteristics. Further, B-cells and T-cells epitopes were predicted and connected through suitable linkers and adjuvant. The predicted T-cell epitopes within the vaccine construct exhibited a significant worldwide population coverage. Moreover, Robetta was utilized to predict the 3D structure of the vaccine construct. Subsequently the molecular docking simulation of construct was employed to study the molecular interactions by using Toll-like receptors as target proteins and further subjected to MD simulation. The results reveal the stability of the vaccine-receptor complex throughout the simulation. Finally, in silico cloning showed potential for the predicted vaccine within the Escherichia coli expression system. These findings provide valuable insights that may guide subsequent experimental studies and contribute meaningfully to the early phases of EV-D68 vaccine research and development. By streamlining candidate selection and optimizing design parameters, our findings holds promise for accelerating the transition from computational predictions to effective vaccine formulations.
{"title":"Designing of a multi-epitope vaccine targeting enterovirus D68: An integrated immunoinformatic and reverse vaccinology approach","authors":"Hailah M. Almohaimeed , Amany I. Almars , Nada Alkhorayef , Ahmed M. Basri , Fayez Alsulaimani , Muhammad Shahbaz , Fahad M. Alshabrmi , Sarfaraz Alam , Tahir Muhammad , Muhammad Shahab","doi":"10.1016/j.compbiomed.2025.111433","DOIUrl":"10.1016/j.compbiomed.2025.111433","url":null,"abstract":"<div><div>Enterovirus D68 (EV-D68) is an enterovirus known for causing respiratory infections, as well as flaccid myelitis, meningitis and encephalitis. Despite the efforts, no licensed vaccine against EV-D68 is currently available. Vaccine development efforts are ongoing; however, the process is complex and requires extensive clinical validation. In contrast, immunoinformatic is a rapidly expanding area with the potential to significantly influence the therapeutic interventions and vaccine development for infectious diseases. Herein, immunoinformatic and reverse vaccinology strategies were utilized to design a multi-epitope vaccine construct targeting EV-D68 virus. In this connection, three virulent proteins were selected for analysis based on their immunogenic characteristics. Further, B-cells and T-cells epitopes were predicted and connected through suitable linkers and adjuvant. The predicted T-cell epitopes within the vaccine construct exhibited a significant worldwide population coverage. Moreover, Robetta was utilized to predict the 3D structure of the vaccine construct. Subsequently the molecular docking simulation of construct was employed to study the molecular interactions by using Toll-like receptors as target proteins and further subjected to MD simulation. The results reveal the stability of the vaccine-receptor complex throughout the simulation. Finally, <em>in silico</em> cloning showed potential for the predicted vaccine within the <em>Escherichia coli</em> expression system. These findings provide valuable insights that may guide subsequent experimental studies and contribute meaningfully to the early phases of EV-D68 vaccine research and development. By streamlining candidate selection and optimizing design parameters, our findings holds promise for accelerating the transition from computational predictions to effective vaccine formulations.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111433"},"PeriodicalIF":6.3,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145882871","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}
Pub Date : 2026-01-02DOI: 10.1016/j.compbiomed.2025.111431
Aldimir Bruzadin, Marilaine Colnago, Lucas C. Ribas, Wallace Casaca
Despite notable advances in deep learning, accurately segmenting lung lesions in computed tomography remains a significant challenge due to the scarcity of annotated data and the high diversity in lesion appearance. To address these issues, seeded image segmentation stands out as a flexible and accurate approach, adapting to diverse image contexts and target definitions. Building on this perspective, we introduce the Deep Laplacian Coordinates Neural Network (DLCNN): a novel framework that integrates deep boundary detection, anisotropic diffusion and seed-driven labeling to segment lung lesions caused by COVID-19. DLCNN employs a semantically enriched deep contour network that predicts edge weights for a graph-based image representation. These weights are then incorporated into our label propagation model, which is built upon the Laplacian Coordinates diffuser, leveraging many attractive properties such as global optimality, robust boundary delineation and directionally adaptive diffusion. By combining the representational power of deep boundary learning with the generalizability of a seed-driven anisotropic diffusion model, the proposed framework accurately captures lung lesions, even when boundaries are poorly defined. DLCNN consistently outperforms both recent and state-of-the-art marker-based segmentation methods, as confirmed by extensive quantitative and qualitative analyses, particularly in complex scenarios involving low contrast and irregular lesion shapes.
{"title":"Deep Laplacian Coordinates: End-to-end deeply guided anisotropic diffusion for COVID-19 pulmonary lesion segmentation","authors":"Aldimir Bruzadin, Marilaine Colnago, Lucas C. Ribas, Wallace Casaca","doi":"10.1016/j.compbiomed.2025.111431","DOIUrl":"10.1016/j.compbiomed.2025.111431","url":null,"abstract":"<div><div>Despite notable advances in deep learning, accurately segmenting lung lesions in computed tomography remains a significant challenge due to the scarcity of annotated data and the high diversity in lesion appearance. To address these issues, seeded image segmentation stands out as a flexible and accurate approach, adapting to diverse image contexts and target definitions. Building on this perspective, we introduce the <em>Deep Laplacian Coordinates Neural Network</em> (DLCNN): a novel framework that integrates deep boundary detection, anisotropic diffusion and seed-driven labeling to segment lung lesions caused by COVID-19. DLCNN employs a semantically enriched deep contour network that predicts edge weights for a graph-based image representation. These weights are then incorporated into our label propagation model, which is built upon the Laplacian Coordinates diffuser, leveraging many attractive properties such as global optimality, robust boundary delineation and directionally adaptive diffusion. By combining the representational power of deep boundary learning with the generalizability of a seed-driven anisotropic diffusion model, the proposed framework accurately captures lung lesions, even when boundaries are poorly defined. DLCNN consistently outperforms both recent and state-of-the-art marker-based segmentation methods, as confirmed by extensive quantitative and qualitative analyses, particularly in complex scenarios involving low contrast and irregular lesion shapes.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111431"},"PeriodicalIF":6.3,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145882874","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}
Pub Date : 2026-01-02DOI: 10.1016/j.compbiomed.2025.111421
Mariusz Bujny , Katarzyna Jesionek , Jakub Nalepa , Karol Miszalski-Jamka , Katarzyna Widawka-Żak , Sabina Wolny , Marcin Kostur
Precise localization of coronary arteries in Computed Tomography (CT) scans is critical from the perspective of medical assessment of various heart pathologies. Although manifold methods exist that offer high-quality segmentation of coronary arteries in cardiac contrast-enhanced CT scans, the potential of less invasive, non-contrast CT is still not fully exploited. Since such fine anatomical structures are hardly visible in this type of medical image, the existing methods are characterized by high recall and low precision, and are used mainly for filtering of calcified atherosclerotic plaques in the context of calcium scoring. In this paper, we address this research gap and introduce a deep learning algorithm for segmenting coronary arteries in multi-vendor ECG-gated non-contrast cardiac CT images which benefits from a novel framework for semi-automatic generation of Ground Truth (GT) via image registration. We hypothesize that the proposed GT generation process is much more efficient in this case than manual segmentation, as it allows for a fast generation of large volumes of diverse data, which translates to well-generalizing models. To thoroughly evaluate the segmentation quality based on such an approach, we propose a novel method for manual mesh-to-image registration, which is used to create our test-GT. The experimental study shows that our AutoML-powered deep machine learning model delineates the coronary arteries significantly more accurately than the GT used for its training, and leads to the Dice and clDice metrics close to the interrater variability.
从各种心脏疾病的医学评估角度来看，计算机断层扫描（CT）中冠状动脉的精确定位至关重要。尽管有多种方法可以在心脏增强CT扫描中提供高质量的冠状动脉分割，但微创、非对比CT的潜力仍未得到充分利用。由于这种精细的解剖结构在这类医学图像中很难看到，现有方法的特点是召回率高，精度低，主要用于钙评分背景下钙化动脉粥样硬化斑块的过滤。在本文中，我们解决了这一研究空白，并引入了一种深度学习算法，用于分割多供应商ecg门控非对比心脏CT图像中的冠状动脉，该算法受益于通过图像配准半自动生成Ground Truth （GT）的新框架。我们假设在这种情况下，所提出的GT生成过程比手动分割更有效，因为它允许快速生成大量不同的数据，从而转化为良好的泛化模型。为了彻底评估基于这种方法的分割质量，我们提出了一种新的手动网格到图像配准方法，并使用该方法创建了我们的测试gt。实验研究表明，我们的automl驱动的深度机器学习模型比用于其训练的GT更准确地描述冠状动脉，并导致Dice和clDice指标接近于interrater可变性。
{"title":"Coronary artery segmentation in non-contrast calcium scoring CT images using deep learning","authors":"Mariusz Bujny , Katarzyna Jesionek , Jakub Nalepa , Karol Miszalski-Jamka , Katarzyna Widawka-Żak , Sabina Wolny , Marcin Kostur","doi":"10.1016/j.compbiomed.2025.111421","DOIUrl":"10.1016/j.compbiomed.2025.111421","url":null,"abstract":"<div><div>Precise localization of coronary arteries in Computed Tomography (CT) scans is critical from the perspective of medical assessment of various heart pathologies. Although manifold methods exist that offer high-quality segmentation of coronary arteries in cardiac contrast-enhanced CT scans, the potential of less invasive, non-contrast CT is still not fully exploited. Since such fine anatomical structures are hardly visible in this type of medical image, the existing methods are characterized by high recall and low precision, and are used mainly for filtering of calcified atherosclerotic plaques in the context of calcium scoring. In this paper, we address this research gap and introduce a deep learning algorithm for segmenting coronary arteries in multi-vendor ECG-gated non-contrast cardiac CT images which benefits from a novel framework for semi-automatic generation of Ground Truth (GT) via image registration. We hypothesize that the proposed GT generation process is much more efficient in this case than manual segmentation, as it allows for a fast generation of large volumes of diverse data, which translates to well-generalizing models. To thoroughly evaluate the segmentation quality based on such an approach, we propose a novel method for manual mesh-to-image registration, which is used to create our test-GT. The experimental study shows that our AutoML-powered deep machine learning model delineates the coronary arteries significantly more accurately than the GT used for its training, and leads to the Dice and clDice metrics close to the interrater variability.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111421"},"PeriodicalIF":6.3,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145876739","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}
Pub Date : 2026-01-02DOI: 10.1016/j.compbiomed.2025.111416
Andrea Campagner , Matteo Lazzeroni , Caterina Pizzi , Caterina Sattin , Giulia Buccichini , Massimo Del Fabbro , Gianluca Martino Tartaglia , Maria Cristina Firetto , Gianpaolo Carrafiello , Michael Koch , Pasquale Capaccio , Federico Cabitza
There is a gap in real-world clinical adoption of machine learning (ML) solutions due to the inherent uncertainty and variability in treatment outcomes. To bridge this gap, we present a novel approach to the problem of medical treatment selection using ML models and we apply it to the case of submandibular sialolithiasis treatment. The study introduces a weakly supervised learning framework which allows for the inclusion of imprecise, incomplete, or noisy ground truth data. By applying this methodology to the specific medical problem of submandibular stone treatment, we demonstrate the potential of encoding treatment outcomes as credal sets—collections of probability distributions reflecting the uncertain nature of the optimal treatment—to improve surgical planning and decision-making. We validated our model using real-world patient data, showcasing its ability to offer personalized treatment recommendations based on radiological features of submandibular stones. Our study underscores the importance of incorporating proper uncertainty management into ML for clinical practice to support clinical decision-making, by showing a promising solution to improve the treatment of sialolithiasis.
{"title":"Weakly supervised treatment selection: Machine learning models for appropriate surgical planning of submandibular stones","authors":"Andrea Campagner , Matteo Lazzeroni , Caterina Pizzi , Caterina Sattin , Giulia Buccichini , Massimo Del Fabbro , Gianluca Martino Tartaglia , Maria Cristina Firetto , Gianpaolo Carrafiello , Michael Koch , Pasquale Capaccio , Federico Cabitza","doi":"10.1016/j.compbiomed.2025.111416","DOIUrl":"10.1016/j.compbiomed.2025.111416","url":null,"abstract":"<div><div>There is a gap in real-world clinical adoption of machine learning (ML) solutions due to the inherent uncertainty and variability in treatment outcomes. To bridge this gap, we present a novel approach to the problem of medical treatment selection using ML models and we apply it to the case of submandibular sialolithiasis treatment. The study introduces a weakly supervised learning framework which allows for the inclusion of imprecise, incomplete, or noisy ground truth data. By applying this methodology to the specific medical problem of submandibular stone treatment, we demonstrate the potential of encoding treatment outcomes as credal sets—collections of probability distributions reflecting the uncertain nature of the optimal treatment—to improve surgical planning and decision-making. We validated our model using real-world patient data, showcasing its ability to offer personalized treatment recommendations based on radiological features of submandibular stones. Our study underscores the importance of incorporating proper uncertainty management into ML for clinical practice to support clinical decision-making, by showing a promising solution to improve the treatment of sialolithiasis.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111416"},"PeriodicalIF":6.3,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145876742","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号