Computer methods and programs in biomedicine最新文献

{"title":"Patient-specific pulmonary venous flow characterization and its impact on left atrial appendage thrombosis in atrial fibrillation patients","authors":"","doi":"10.1016/j.cmpb.2024.108428","DOIUrl":"10.1016/j.cmpb.2024.108428","url":null,"abstract":"<div><h3>Background</h3><div>Cardioembolic strokes are commonly occurred in non-valvular atrial fibrillation (AF) patients, with over 90% of cases originating from clot in left atrial appendage (LAA), which is believed to be greatly related with hemodynamic characters. Numerical simulation is widely accepted in the hemodynamic analysis, and patient-specific boundaries are required for realistic numerical simulations.</div></div><div><h3>Method</h3><div>This paper firstly proposed a method that maps personalized pulmonary venous flow (PVF) by utilizing the volume changes of the left atrium (LA) over the cardiac cycle. Then we used data from patients with AF to investigate the correlation between PVF patterns and hemodynamics within the LAA. Meanwhile, we conducted a fluid-structure interaction analysis to assess the impact of velocity- and time-related PVF parameters on LAA hemodynamic characters.</div></div><div><h3>Results</h3><div>The analysis reveal that the ratio of systolic to diastolic peak velocity (<em>V</em>_S/<em>V</em>_D), and systolic velocity-time integral (VTI) showed a significant influence on LAA velocity in patients with atrial fibrillation, and the increases of velocity- and time-related parameters were found to be positively correlated with the blood update in the LAA.</div></div><div><h3>Conclusions</h3><div>This study established a method for mapping patient-specific PVF based on LA volume change, and evaluated the relationship between PVF parameters and thrombosis risk. The present work provides an insight from PVF characters to evaluate the risk of thrombus formation within LAA in patients with AF.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel GAN-based three-axis mutually supervised super-resolution reconstruction method for rectal cancer MR image","authors":"","doi":"10.1016/j.cmpb.2024.108426","DOIUrl":"10.1016/j.cmpb.2024.108426","url":null,"abstract":"<div><h3>Background and objective</h3><div>This study aims to enhance the resolution in the axial direction of rectal cancer magnetic resonance (MR) imaging scans to improve the accuracy of visual interpretation and quantitative analysis. MR imaging is a critical technique for the diagnosis and treatment planning of rectal cancer. However, obtaining high-resolution MR images is both time-consuming and costly. As a result, many hospitals store only a limited number of slices, often leading to low-resolution MR images, particularly in the axial plane. Given the importance of image resolution in accurate assessment, these low-resolution images frequently lack the necessary detail, posing substantial challenges for both human experts and computer-aided diagnostic systems. Image super-resolution (SR), a technique developed to enhance image resolution, was originally applied to natural images. Its success has since led to its application in various other tasks, especially in the reconstruction of low-resolution MR images. However, most existing SR methods fail to account for all anatomical planes during reconstruction, leading to unsatisfactory results when applied to rectal cancer MR images.</div></div><div><h3>Methods</h3><div>In this paper, we propose a GAN-based three-axis mutually supervised super-resolution reconstruction method tailored for low-resolution rectal cancer MR images. Our approach involves performing one-dimensional (1D) intra-slice SR reconstruction along the axial direction for both the sagittal and coronal planes, coupled with inter-slice SR reconstruction based on slice synthesis in the axial direction. To further enhance the accuracy of super-resolution reconstruction, we introduce a consistency supervision mechanism across the reconstruction results of different axes, promoting mutual learning between each axis. A key innovation of our method is the introduction of Depth-GAN for synthesize intermediate slices in the axial plane, incorporating depth information and leveraging Generative Adversarial Networks (GANs) for this purpose. Additionally, we enhance the accuracy of intermediate slice synthesis by employing a combination of supervised and unsupervised interactive learning techniques throughout the process.</div></div><div><h3>Results</h3><div>We conducted extensive ablation studies and comparative analyses with existing methods to validate the effectiveness of our approach. On the test set from Shanxi Cancer Hospital, our method achieved a Peak Signal-to-Noise Ratio (PSNR) of 34.62 and a Structural Similarity Index (SSIM) of 96.34 %. These promising results demonstrate the superiority of our method.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142379216","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}

{"title":"Investigating the effect of brain atrophy on transcranial direct current stimulation: A computational study using ADNI dataset","authors":"","doi":"10.1016/j.cmpb.2024.108429","DOIUrl":"10.1016/j.cmpb.2024.108429","url":null,"abstract":"<div><h3>Background</h3><div>Transcranial direct current stimulation (tDCS) is a non-invasive brain stimulation technique that uses weak electrical currents to modulate brain activity, thus potentially aiding the treatment of brain diseases. Although tDCS offers convenience, it yields inconsistent electric-field distributions among individuals. This inconsistency may be attributed to certain factors, such as brain atrophy. Brain atrophy is accompanied by increased cerebrospinal fluid (CSF) volume. Owing to the high electrical conductivity of CSF, its increased volume complicates current delivery to the brain, thus resulting in greater inter-subject variability.</div></div><div><h3>Objective</h3><div>We aim to investigate the differences in tDCS-induced electric fields between groups with different severities of brain atrophy.</div></div><div><h3>Methods</h3><div>We classified 180 magnetic resonance images into four groups based on the presence of Alzheimer's disease and sex. We used two montages, i.e., F-3 &amp; Fp-2 and TP-9 &amp; TP-10, to target the left rostral middle frontal gyrus and the hippocampus/amygdala complex, respectively. Differences between the groups in terms of regional volume variation, stimulation effect, and correlation were analyzed.</div></div><div><h3>Results</h3><div>Significant differences were observed in the geometrical variations of the CSF and two target regions. Electric fields induced by tDCS were similar in both sexes. Unique patterns were observed in each group in the correlation analysis.</div></div><div><h3>Conclusion</h3><div>Our findings show that factors such as brain atrophy affect the tDCS results and that the factors present complex relationships. Further studies are necessary to better understand the relationships between these factors and optimize tDCS as a therapeutic tool.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142307292","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}

{"title":"Computational techniques to monitoring fractional order type-1 diabetes mellitus model for feedback design of artificial pancreas","authors":"","doi":"10.1016/j.cmpb.2024.108420","DOIUrl":"10.1016/j.cmpb.2024.108420","url":null,"abstract":"<div><h3>Background and objectives:</h3><p>In this paper, we developed a significant class of control issues regulated by nonlinear fractal order systems with input and output signals, our goal is to design a direct transcription method with impulsive instant order. Recent advances in the artificial pancreas system provide an emerging treatment option for type 1 diabetes. The performance of the blood glucose regulation directly relies on the accuracy of the glucose-insulin modeling. This work leads to the monitoring and assessment of comprehensive type-1 diabetes mellitus for controller design of artificial panaceas for the precision of the glucose-insulin glucagon in finite time with Caputo fractional approach for three primary subsystems.</p></div><div><h3>Methods:</h3><p>For the proposed model, we admire the qualitative analysis with equilibrium points lying in the feasible region. Model satisfied the biological feasibility with the Lipschitz criteria and linear growth is examined, considering positive solutions, boundedness and uniqueness at equilibrium points with Leray–Schauder results under time scale ideas. Within each subsystem, the virtual control input laws are derived by the application of input to state theorems and Ulam Hyers Rassias.</p></div><div><h3>Results:</h3><p>Chaotic Relation of Glucose insulin glucagon compartmental in the feasible region and stable in finite time interval monitoring is derived through simulations that are stable and bounded in the feasible regions. Additionally, as blood glucose is the only measurable state variable, the unscented power-law kernel estimator appropriately takes into account the significant problem of estimating inaccessible state variables that are bound to significant values for the glucose-insulin system. The comparative results on the simulated patients suggest that the suggested controller strategy performs remarkably better than the compared methods.</p></div><div><h3>Conclusion:</h3><p>In the model under investigation, parametric uncertainties are identified since the glucose, insulin, and glucagon system’s parameters are accurately measured numerically at different fractional order values. In terms of algorithm resilience and Caputo tracking in the presence of glucagon and insulin intake disturbance to maintain the glucose level. A comprehensive analysis of numerous difficult test issues is conducted in order to offer a thorough justification of the planned strategy to control the type 1 diabetes mellitus with designed the artificial pancreas.</p></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274286","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}

{"title":"Immunohistochemistry annotations enhance AI identification of lymphocytes and neutrophils in digitized H&E slides from inflammatory bowel disease","authors":"","doi":"10.1016/j.cmpb.2024.108423","DOIUrl":"10.1016/j.cmpb.2024.108423","url":null,"abstract":"<div><h3>Background and Objective</h3><p>Histologic assessment of the immune infiltrate in H&amp;E slides is vital in diagnosing and managing inflammatory bowel diseases, but these assessments are subjective and time-consuming even for those with expertise. The development of deep learning models to aid in these assessments has been limited by the paucity of image data with reliably annotated immune cells available for training.</p></div><div><h3>Methods</h3><p>To address these challenges, we developed a pipeline that automates the neutrophil and lymphocyte labeling in ROIs from digital H&amp;E slides. The data included ROIs extracted from 19 digitized H&amp;E slides and the same slides restained with immunohistochemistry. Our pipeline first delineates each nucleus in H&amp;E ROIs. Using the colorimetric features of the immunohistochemical stains (red: neutrophils, green: lymphocytes) in the immunohistochemistry ROIs, each cell was labeled as a neutrophil, a lymphocyte, or another cell. The labels were then transferred to the corresponding H&amp;E ROIs by image registration, and the ROI registration accuracy was assessed by the median target registration error resulting in a labeled dataset. The newly formed dataset (NeuLy-IHC) comprising 519 ROIs with 235,256 labeled cells (74,339 lymphocytes, 16,326 neutrophils and 144,591 other cells) was used to train the HoVer-Net^(NeuLy) model. The performance of HoVer-Net^(NeuLy) measured by DICE coefficient (segmentation accuracy) and F1-scores (classification accuracy), was compared to those achieved by HoVer-Net^(MoNuSAC) and SMILE^(MoNuSAC) publicly available models trained on cancer-containing ROIs from the MoNuSAC dataset with manual cell labeling and pathologists’ annotations.</p></div><div><h3>Results</h3><p>The 1.0 μm median target registration error of ROIs observed was low demonstrating robust transferring of cellular labels from immunohistochemistry ROIs to H&amp;E ROIs. In the test set comprising 76 NeuLy-IHC and 78 MoNuSAC ROIs, the HoVer-Net^(NeuLy) achieved a DICE coefficient of 0.861 and F1-sores of 0.827, 0.838, and 0.828, for neutrophils, lymphocytes, and other cells, respectively, outperforming the HoVer-Net^(MoNuSAC)'s and SMILE^(MoNuSAC)’s DICE coefficient and F1 scores for each cell category.</p></div><div><h3>Conclusions</h3><p>We attribute the improved performance of HoVer-Net^(NeuLy) to the larger number of immune cells in the NeuLy-IHC dataset (in total 5x more, including 21x more neutrophils) than in the MoNuSAC dataset. Despite being trained on data from inflammatory bowel disease specimens, our model maintained robust performance when tested on previously unseen data derived from cancer specimens. The NeuLy-IHC set provides opportunities for training accurate models to quantify the inflammatory infiltrate in digital histologic slides.</p></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274201","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}

{"title":"Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms","authors":"","doi":"10.1016/j.cmpb.2024.108419","DOIUrl":"10.1016/j.cmpb.2024.108419","url":null,"abstract":"<div><h3>Background and Objective:</h3><p>The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions.</p></div><div><h3>Methods:</h3><p>This paper proposes an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model’s predictions are both accurate and comprehensible.</p></div><div><h3>Results:</h3><p>The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively.</p></div><div><h3>Conclusion:</h3><p>Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.</p></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142239776","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}

{"title":"Bayesian networks in modeling leucocyte interplay following brain irradiation: A comprehensive framework","authors":"","doi":"10.1016/j.cmpb.2024.108421","DOIUrl":"10.1016/j.cmpb.2024.108421","url":null,"abstract":"<div><h3>Background and objective</h3><p>Understanding the intricate interactions among leucocyte subpopulations following radiotherapy is crucial for advancing cancer research and immunology. Recently, interest in recent radiotherapy modalities, such as protons, has increased. Herein, we present a framework utilizing Bayesian networks to uncover these complex relationships via an illustrative example of brain irradiation in rodents.</p></div><div><h3>Methods</h3><p>We utilized data from 96 healthy C57BL/6 adult mice subjected to either X-ray or proton brain irradiation. Leucocyte subpopulations in the blood collected 12 h after the final irradiated fraction were quantified. We employed Bayesian networks to detect causal interplay between physiological parameters, radiation variables and circulating leucocytes. The causal structure was learned via the use of the Bayesian information criterion as a scored criterion. Parameter estimation was performed to quantify the strength of the identified causal relationships. Cross-validation was used to validate our Bayesian network model's performance.</p></div><div><h3>Results</h3><p>In the X-ray model, we discovered previously undisclosed interactions between NK-cells and neutrophils, and between monocytes and T-CD4⁺ cells. The proton model revealed an interplay involving T-CD4⁺ cells and neutrophils. Both X-rays and protons led to heightened interactions between T-CD8+ cells and B cells, indicating their significant role in orchestrating immune responses. Additionally, the proton model displayed strengthened interactions between T-CD4⁺ and T-CD8⁺ cells, emphasizing a dynamic and coordinated immune response post-irradiation. Cross-validation results demonstrated the robustness of the Bayesian network model in explaining data uncertainty.</p></div><div><h3>Conclusion</h3><p>The use of Bayesian networks as tools for causal structure discovery has revealed novel insights into the dynamics of immune responses to radiation exposure.</p></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142228782","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}

{"title":"A time-dependent explainable radiomic analysis from the multi-omic cohort of CPTAC-Pancreatic Ductal Adenocarcinoma","authors":"","doi":"10.1016/j.cmpb.2024.108408","DOIUrl":"10.1016/j.cmpb.2024.108408","url":null,"abstract":"<div><h3>Background and Objective</h3><div>In Pancreatic Ductal Adenocarcinoma (PDA), multi-omic models are emerging to answer unmet clinical needs to derive novel quantitative prognostic factors. We realized a pipeline that relies on survival machine-learning (SML) classifiers and explainability based on patients’ follow-up (FU) to stratify prognosis from the public-available multi-omic datasets of the CPTAC-PDA project.</div></div><div><h3>Materials and Methods</h3><div>Analyzed datasets included tumor-annotated radiologic images, clinical, and mutational data. A feature selection was based on univariate (UV) and multivariate (MV) survival analyses according to Overall Survival (OS) and recurrence (REC). In this study, we considered seven multi-omic datasets and compared four SML classifiers: Cox, survival random forest, generalized boosted, and support vector machines (SVM). For each classifier, we assessed the concordance (C) index on the validation set. The best classifiers for the validation set on both OS and REC underwent explainability analyses using SurvSHAP(t), which extends SHapley Additive exPlanations (SHAP).</div></div><div><h3>Results</h3><div>According to OS, after UV and MV analyses we selected 18/37 and 10/37 multi-omic features, respectively. According to REC, based on UV and MV analyses we selected 10/35 and 5/35 determinants, respectively. Generally, SML classifiers including radiomics outperformed those modelled on clinical or mutational predictors. For OS, the Cox model encompassing radiomic, clinical, and mutational features reached 75 % of C index, outperforming other classifiers. On the other hand, for REC, the SVM model including only radiomics emerged as the best-performing, with 68 % of C index. For OS, SurvSHAP(t) identified the first order Median Gray Level (GL) intensities, the gender, the tumor grade, the Joint Energy GL Co-occurrence Matrix (GLCM), and the GLCM Informational Measures of Correlations of type 1 as the most important features. For REC, the first order Median GL intensities, the GL size zone matrix Small Area Low GL Emphasis, and first order variance of GL intensities emerged as the most discriminative.</div></div><div><h3>Conclusions</h3><div>In this work, radiomics showed the potential for improving patients’ risk stratification in PDA. Furthermore, a deeper understanding of how radiomics can contribute to prognosis in PDA was achieved with a time-dependent explainability of the top multi-omic predictors.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Colorectal cancer risk mapping through Bayesian networks","authors":"","doi":"10.1016/j.cmpb.2024.108407","DOIUrl":"10.1016/j.cmpb.2024.108407","url":null,"abstract":"<div><h3>Background and Objective:</h3><p>Only about 14% of eligible EU citizens finally participate in colorectal cancer (CRC) screening programs despite it being the third most common type of cancer worldwide. The development of CRC risk models can enable predictions to be embedded in decision-support tools facilitating CRC screening and treatment recommendations. This paper develops a predictive model that aids in characterizing CRC risk groups and assessing the influence of a variety of risk factors on the population.</p></div><div><h3>Methods:</h3><p>A CRC Bayesian Network is learnt by aggregating extensive expert knowledge and data from an observational study and making use of structure learning algorithms to model the relations between variables. The network is then parametrised to characterize these relations in terms of local probability distributions at each of the nodes. It is finally used to predict the risks of developing CRC together with the uncertainty around such predictions.</p></div><div><h3>Results:</h3><p>A graphical CRC risk mapping tool is developed from the model and used to segment the population into risk subgroups according to variables of interest. Furthermore, the network provides insights on the predictive influence of modifiable risk factors such as alcohol consumption and smoking, and medical conditions such as diabetes or hypertension linked to lifestyles that potentially have an impact on an increased risk of developing CRC.</p></div><div><h3>Conclusion:</h3><p>CRC is most commonly developed in older individuals. However, some modifiable behavioral factors seem to have a strong predictive influence on its potential risk of development. Modeling these effects facilitates identifying risk groups and targeting influential variables which are subsequently helpful in the design of screening and treatment programs.</p></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0169260724004000/pdfft?md5=14821825e54e4858393460b90caf6a05&pid=1-s2.0-S0169260724004000-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142228783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MMGCN: Multi-modal multi-view graph convolutional networks for cancer prognosis prediction","authors":"","doi":"10.1016/j.cmpb.2024.108400","DOIUrl":"10.1016/j.cmpb.2024.108400","url":null,"abstract":"<div><h3>Background and objective</h3><p>Accurate prognosis prediction for cancer patients plays a significant role in the formulation of treatment strategies, considerably impacting personalized medicine. Recent advancements in this field indicate that integrating information from various modalities, such as genetic and clinical data, and developing multi-modal deep learning models can enhance prediction accuracy. However, most existing multi-modal deep learning methods either overlook patient similarities that benefit prognosis prediction or fail to effectively capture diverse information due to measuring patient similarities from a single perspective. To address these issues, a novel framework called multi-modal multi-view graph convolutional networks (MMGCN) is proposed for cancer prognosis prediction.</p></div><div><h3>Methods</h3><p>Initially, we utilize the similarity network fusion (SNF) algorithm to merge patient similarity networks (PSNs), individually constructed using gene expression, copy number alteration, and clinical data, into a fused PSN for integrating multi-modal information<em>.</em> To capture diverse perspectives of patient similarities, we treat the fused PSN as a multi-view graph by considering each single-edge-type subgraph as a view graph, and propose multi-view graph convolutional networks (GCNs) with a view-level attention mechanism. Moreover, an edge homophily prediction module is designed to alleviate the adverse effects of heterophilic edges on the representation power of GCNs. Finally, comprehensive representations of patient nodes are obtained to predict cancer prognosis.</p></div><div><h3>Results</h3><p>Experimental results demonstrate that MMGCN outperforms state-of-the-art baselines on four public datasets, including METABRIC, TCGA-BRCA, TCGA-LGG, and TCGA-LUSC, with the area under the receiver operating characteristic curve achieving 0.827 ± 0.005, 0.805 ± 0.014, 0.925 ± 0.007, and 0.746 ± 0.013, respectively.</p></div><div><h3>Conclusions</h3><p>Our study reveals the effectiveness of the proposed MMGCN, which deeply explores patient similarities related to different modalities from a broad perspective, in enhancing the performance of multi-modal cancer prognosis prediction. The source code is publicly available at <span><span>https://github.com/ping-y/MMGCN</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":null,"pages":null},"PeriodicalIF":4.9,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142173710","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}