Computers in biology and medicine最新文献

筛选
英文 中文
A rule-based method to automatically locate lumbar vertebral bodies on MRI images 一种基于规则的MRI图像腰椎椎体自动定位方法
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-29 DOI: 10.1016/j.compbiomed.2025.110032
Pau Xiberta , Màrius Vila , Marc Ruiz , Adrià Julià i Juanola , Josep Puig , Joan C. Vilanova , Imma Boada
{"title":"A rule-based method to automatically locate lumbar vertebral bodies on MRI images","authors":"Pau Xiberta ,&nbsp;Màrius Vila ,&nbsp;Marc Ruiz ,&nbsp;Adrià Julià i Juanola ,&nbsp;Josep Puig ,&nbsp;Joan C. Vilanova ,&nbsp;Imma Boada","doi":"10.1016/j.compbiomed.2025.110032","DOIUrl":"10.1016/j.compbiomed.2025.110032","url":null,"abstract":"<div><h3>Background:</h3><div>Segmentation is a critical process in medical image interpretation. It is also essential for preparing training datasets for machine learning (ML)-based solutions. Despite technological advancements, achieving fully automatic segmentation is still challenging. User interaction is required to initiate the process, either by defining points or regions of interest, or by verifying and refining the output. One of the complex structures that requires semi-automatic segmentation procedures or manually defined training datasets is the lumbar spine. Automating the placement of a point within each lumbar vertebral body could significantly reduce user interaction in these procedures.</div></div><div><h3>Method:</h3><div>A new method for automatically locating lumbar vertebral bodies in sagittal magnetic resonance images (MRI) is presented. The method integrates different image processing techniques and relies on the vertebral body morphology. Testing was mainly performed using 50 MRI scans that were previously annotated manually by placing a point at the centre of each lumbar vertebral body. A complementary public dataset was also used to assess robustness. Evaluation metrics included the correct labelling of each structure, the inclusion of each point within the corresponding vertebral body area, and the accuracy of the locations relative to the vertebral body centres using root mean squared error (RMSE) and mean absolute error (MAE). A one-sample Student’s <span><math><mi>t</mi></math></span>-test was also performed to find the distance beyond which differences are considered significant (α <span><math><mo>=</mo></math></span> 0.05).</div></div><div><h3>Results:</h3><div>All lumbar vertebral bodies from the primary dataset were correctly labelled, and the average RMSE and MAE between the automatic and manual locations were less than 5 mm. Distances to the vertebral body centres were found to be significantly less than 4.33 mm with a <span><math><mi>p</mi></math></span>-value <span><math><mo>&lt;</mo></math></span> 0.05, and significantly less than half the average minimum diameter of a lumbar vertebral body with a <span><math><mi>p</mi></math></span>-value <span><math><mo>&lt;</mo></math></span> 0.00001. Results from the complementary public dataset include high labelling and inclusion rates (85.1% and 94.3%, respectively), and similar accuracy values.</div></div><div><h3>Conclusion:</h3><div>The proposed method successfully achieves robust and accurate automatic placement of points within each lumbar vertebral body. The automation of this process enables the transition from semi-automatic to fully automatic methods, thus reducing error-prone and time-consuming user interaction, and facilitating the creation of training datasets for ML-based solutions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110032"},"PeriodicalIF":7.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888051","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
Alzheimer's disease knowledge graph enhances knowledge discovery and disease prediction 阿尔茨海默病知识图谱增强了知识发现和疾病预测
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-29 DOI: 10.1016/j.compbiomed.2025.110285
Yue Yang , Kaixian Yu , Shan Gao , Sheng Yu , Di Xiong , Chuanyang Qin , Huiyuan Chen , Jiarui Tang , Niansheng Tang , Hongtu Zhu
{"title":"Alzheimer's disease knowledge graph enhances knowledge discovery and disease prediction","authors":"Yue Yang ,&nbsp;Kaixian Yu ,&nbsp;Shan Gao ,&nbsp;Sheng Yu ,&nbsp;Di Xiong ,&nbsp;Chuanyang Qin ,&nbsp;Huiyuan Chen ,&nbsp;Jiarui Tang ,&nbsp;Niansheng Tang ,&nbsp;Hongtu Zhu","doi":"10.1016/j.compbiomed.2025.110285","DOIUrl":"10.1016/j.compbiomed.2025.110285","url":null,"abstract":"<div><h3>Objective</h3><div>To construct an Alzheimer's Disease Knowledge Graph (ADKG) by extracting and integrating relationships among Alzheimer's disease (AD), genes, variants, chemicals, drugs, and other diseases from biomedical literature, aiming to identify existing treatments, potential targets, and diagnostic methods for AD.</div></div><div><h3>Methods</h3><div>We annotated 800 PubMed abstracts (ADERC corpus) with 20,886 entities and 4935 relationships, augmented via GPT-4. A SpERT model (SciBERT-based) trained on this data extracted relations from PubMed abstracts, supported by biomedical databases and entity linking refined via abbreviation resolution/string matching. The resulting knowledge graph trained embedding models to predict novel relationships. ADKG's utility was validated by integrating it with UK Biobank data for predictive modeling.</div></div><div><h3>Results</h3><div>The ADKG contained 3,199,276 entity mentions and 633,733 triplets, linking &gt;5K unique entities and capturing complex AD-related interactions. Its graph embedding models produced evidence-supported predictions, enabling testable hypotheses. In UK Biobank predictive modeling, ADKG-enhanced models achieved higher AUROC of 0.928 comparing to 0.903 without ADKG enhancement.</div></div><div><h3>Conclusion</h3><div>By synthesizing literature-derived insights into a computable framework, ADKG bridges molecular mechanisms to clinical phenotypes, advancing precision medicine in Alzheimer's research. Its structured data and predictive utility underscore its potential to accelerate therapeutic discovery and risk stratification.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110285"},"PeriodicalIF":7.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883167","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
Comparative analysis of deep learning models for predicting biocompatibility in tissue scaffold images 预测组织支架图像生物相容性的深度学习模型的比较分析
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-29 DOI: 10.1016/j.compbiomed.2025.110281
Emir Oncu , Kadriye Yasemin Usta Ayanoglu , Fatih Ciftci
{"title":"Comparative analysis of deep learning models for predicting biocompatibility in tissue scaffold images","authors":"Emir Oncu ,&nbsp;Kadriye Yasemin Usta Ayanoglu ,&nbsp;Fatih Ciftci","doi":"10.1016/j.compbiomed.2025.110281","DOIUrl":"10.1016/j.compbiomed.2025.110281","url":null,"abstract":"<div><h3>Motivation</h3><div>Bioprinting enables the creation of complex tissue scaffolds, which are vital for tissue engineering. However, predicting scaffold biocompatibility before fabrication remains a critical challenge, potentially leading to inefficiencies and resource wastage. Artificial Intelligence (AI) models, particularly Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs), offer promising predictive capabilities to address this issue. This study aims to compare the performance of ANN and CNN models to identify the most suitable approach for predicting scaffold biocompatibility using PrusaSlicer-generated designs.</div></div><div><h3>Description</h3><div>Fifteen key design parameters influencing scaffold biocompatibility were modelled using ANN, while scaffold images were analyzed using CNN. PrusaSlicer was employed in designing scaffolds, with parameters influencing biocompatibility predictions. ANN models analyzed these parameters, while CNN models processed scaffold images. Data was standardized, and models were trained on an 80/20 split dataset. Performance evaluation metrics included accuracy, precision, recall, F1-Scores, and confusion matrices. Experimental validation involved biocompatibility tests on five scaffolds.</div></div><div><h3>Results</h3><div>ANN model with 20 neurons and 100 epochs earned perfect (1.0) scores in F1-Score, Precision, and Recall, indicating the best possible model performance. A batch size of 56 for the Convolutional Neural Network model demonstrated balance in F1-Score (0.87), Precision (0.88), and Recall (0.9). Five scaffold tissues were tested for biocompatibility using these two models. ANN model predicted 5 scaffold tissues’ biocompatibilities correctly. While the ANN model accurately predicted biocompatibilities for all five scaffold samples, the CNN model misclassified one sample.</div></div><div><h3>Conclusion</h3><div>This study demonstrates that ANN models are superior to CNN models in predicting scaffold biocompatibility from numerical design parameters. The findings underscore the value of ANNs for structured data in bioprinting, enhancing prediction accuracy and efficiency. These insights can accelerate advancements in tissue engineering and personalized medicine by reducing costs and improving success rates in bioprinting applications. Future work will focus on addressing overfitting challenges and optimizing the models to further enhance their robustness and predictive capabilities.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110281"},"PeriodicalIF":7.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888052","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
Prediction tools for assessing functional impacts of gene mutations in Clear Cell Renal Cell Carcinoma: A comparative study 评估透明细胞肾细胞癌基因突变功能影响的预测工具:一项比较研究
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-29 DOI: 10.1016/j.compbiomed.2025.110187
Cheng-Hong Yang , Guan-Cheng Lin , Chih-Hsien Wu , Jin-Bor Chen , Li-Yeh Chuang
{"title":"Prediction tools for assessing functional impacts of gene mutations in Clear Cell Renal Cell Carcinoma: A comparative study","authors":"Cheng-Hong Yang ,&nbsp;Guan-Cheng Lin ,&nbsp;Chih-Hsien Wu ,&nbsp;Jin-Bor Chen ,&nbsp;Li-Yeh Chuang","doi":"10.1016/j.compbiomed.2025.110187","DOIUrl":"10.1016/j.compbiomed.2025.110187","url":null,"abstract":"<div><div>Renal cell carcinoma (RCC) is a well-known malignancy characterized by specific gene mutations that elevate its occurrence. It can be categorized into clear cell RCC (ccRCC), papillary RCC, and chromophobe RCC, which account for approximately 85 % of all primary RCC cases. The mutations typically involve single-nucleotide variants (SNVs) that lead to amino acid substitutions, which influence various biological functions, including gene expression. Therefore, predicting the functional consequences of RCC-related single-nucleotide polymorphisms (SNPs), including substitutions, insertions, deletions, and duplications, is crucial for the effective clinical management of RCC. In recent years, the accessibility and popularity of tools for predicting SNP functional variations have grown, especially in research concerning the potential risks associated with key gene mutations in cancer. Accordingly, this study focused on commonly mutated genes in ccRCC, namely <em>VHL</em>, <em>BAP1</em>, <em>PBRM1</em>, and <em>SETD2</em>. Public data from sources such as The Cancer Genome Atlas and the National Center for Biotechnology Information were used to identify 61 gene mutation positions. Nine nonsynonymous mutation prediction tools were used for analysis, namely SIFT, Polyphen-2, Mutation Assessor, Fathmm, MutPred, CHASM, Revel, Provean, and SNP&amp;GO. The tools were evaluated by their statistical performance, prediction distribution, and receiver operating characteristic curves. The three tools with the highest accuracy for predicting the functional consequences of mutations in the four frequently mutated genes associated with ccRCC were SIFT (accuracy of 0.75), Provean (0.7), and Polyphen-2 (0.69). These findings offer valuable insights into predicting ccRCC-related gene mutation effects, but further research and validation are essential to support their clinical applications.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110187"},"PeriodicalIF":7.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883168","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
Comprehensive evaluation of early-phase FP-CIT PET as a substitute for brain FDG PET in parkinsonism 早期FP-CIT PET替代脑FDG PET在帕金森病中的综合评价
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-28 DOI: 10.1016/j.compbiomed.2025.110177
Hye Joo Son , Chanwoo Kim , Hyung Jin Choi
{"title":"Comprehensive evaluation of early-phase FP-CIT PET as a substitute for brain FDG PET in parkinsonism","authors":"Hye Joo Son ,&nbsp;Chanwoo Kim ,&nbsp;Hyung Jin Choi","doi":"10.1016/j.compbiomed.2025.110177","DOIUrl":"10.1016/j.compbiomed.2025.110177","url":null,"abstract":"<div><h3>Background</h3><div>Early-phase F-18 FP-CIT PET/CT (PET<sub>FP-CIT</sub>) has been reported to possibly replace FDG PET/CT (PET<sub>FDG</sub>) in the differential diagnosis of parkinsonism. We investigated the correlation between PET<sub>FP-CIT</sub> and PET<sub>FDG</sub> to explore their potential interchangeability.</div></div><div><h3>Method</h3><div>Our retrospective study included 187 participants, categorized into Parkinson's disease (PD), atypical parkinsonian disorders (APD), and participants with intact dopamine transporters (DAT<sub>intact</sub>). We analyzed the correlation of standardized uptake value ratios (SUVR) from early-phase PET<sub>FP-CIT</sub> and PET<sub>FDG</sub> scans across 23 different brain volumes-of-interest using Pearson's correlation analysis. We conducted this analysis for all participants collectively and then separately for each group.</div></div><div><h3>Results</h3><div>For all participants without grouping, a moderate correlation (with correlation coefficients <em>R</em> ranging from 0.360 in right putamen to 0.530 in left caudate nucleus) was observed between Early-phase PET<sub>FP-CIT</sub> and PET<sub>FDG</sub>. PD group showed a weak to moderate correlation (0.226 in left frontal cortex ≤ <em>R</em> ≤ 0.555 in right cerebellum). APD group revealed a moderate correlation with <em>R</em> ranging from 0.488 in right cerebellum to 0.692 in right occipital cortex. Conversely, a lack of correlation in specific areas for DAT<sub>intact</sub> group indicated distinctions between the modalities.</div></div><div><h3>Conclusions</h3><div>Our study showed interchangeability with a moderate correlation between early-phase PET<sub>FP-CIT</sub> and PET<sub>FDG</sub>. However, careful consideration is needed for DAT<sub>intact</sub> group.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110177"},"PeriodicalIF":7.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143878946","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
Comparison between five pattern-based approaches for automated diagnostic classification of mature/peripheral B-cell neoplasms based on standardized EuroFlow flow cytometry immunophenotypic data 基于标准化EuroFlow流式细胞术免疫表型数据的成熟/外周b细胞肿瘤自动诊断分类的五种基于模式的方法比较
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-28 DOI: 10.1016/j.compbiomed.2025.110194
C.E. Pedreira , Q. Lecrevisse , R. Fluxa , J. Verde , S. Barrena , J. Flores-Montero , P. Fernandez , D. Morf , V.H.J. van der Velden , E. Mejstrikova , J. Caetano , L. Burgos , S. Böttcher , J.J.M. van Dongen , A. Orfao , EuroFlow
{"title":"Comparison between five pattern-based approaches for automated diagnostic classification of mature/peripheral B-cell neoplasms based on standardized EuroFlow flow cytometry immunophenotypic data","authors":"C.E. Pedreira ,&nbsp;Q. Lecrevisse ,&nbsp;R. Fluxa ,&nbsp;J. Verde ,&nbsp;S. Barrena ,&nbsp;J. Flores-Montero ,&nbsp;P. Fernandez ,&nbsp;D. Morf ,&nbsp;V.H.J. van der Velden ,&nbsp;E. Mejstrikova ,&nbsp;J. Caetano ,&nbsp;L. Burgos ,&nbsp;S. Böttcher ,&nbsp;J.J.M. van Dongen ,&nbsp;A. Orfao ,&nbsp;EuroFlow","doi":"10.1016/j.compbiomed.2025.110194","DOIUrl":"10.1016/j.compbiomed.2025.110194","url":null,"abstract":"<div><div>Flow cytometry immunophenotyping is critical for the diagnostic classification of mature/peripheral B-cell neoplasms/B-cell chronic lymphoproliferative disorders (B-CLPD). Quantitative driven classification approaches applied to multiparameter flow cytometry immunophenotypic data can be used to extract maximum information from a multidimensional space created by individual parameters (e.g., immunophenotypic markers), for highly accurate and automated classification of individual patient (sample) data. Here, we developed and compared five diagnostic classification algorithms, based on a large set of EuroFlow multicentric flow cytometry data files from a cohort 659 B-CLPD patients. These included automatic population separators based on Principal Component Analysis (PCA), Canonical Variate Analysis (CVA), Neighbourhood Component Analysis (NCA), Support Vector Machine algorithms (SVM) and a variant of the CA(Canonical Analysis) algorithm, in which the number of SDs (Standard Deviations) varied for each of the comparisons of different pairs of diseases (<em>CA-vSD</em>). All five classification approaches are based on direct prospective interrogation of individual B-CLPD patients against the EuroFlow flow cytometry B-CLPD database composed of tumor B-cells of 659 individual patients stained in an identical way and classified a priori by the World Health Organization (WHO) criteria into nine diagnostic categories. Each classification approach was evaluated in parallel in terms of accuracy (% properly classified cases), precision (multiple or single diagnosis/case) and coverage (% cases with a proposed diagnosis). Overall, average rates of correct diagnosis (for the nine B-CLPD diagnostic entities) of between 58.9 % and 90.6 % were obtained with the five algorithms, with variable percentages of cases being either misclassified (4.1 %–14.0 %) or unclassifiable (0.3 %–37.0 %). Automatic population separators based on CA, SVM and PCA showed a high average level of correctness (90.6 %, 86.8 %, and 86.0 %, respectively). Nevertheless, this was at the expense of proposing a considerable number of multiple diagnoses for a significant proportion of the test cases (54.5 %, 53.5 %, and 49.6 %, respectively). The <em>CA-vSD</em> algorithm generated the smaller average misclassification rate (4.1 %), but with 37.0 % of cases for which no diagnosis was proposed. In contrast, the NCA algorithm left only 2.7 % of cases without an associated diagnosis but misclassified 14.0 %. Among correctly classified cases (83.3 % of total), 91.2 % had a single proposed diagnosis, 8.6 % had two possible diagnoses, and 0.2 % had three. We demonstrate that the proposed AI algorithms provide an acceptable level of accuracy for the diagnostic classification of B-CLPD patients and, in general, surpass other algorithms reported in the literature.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110194"},"PeriodicalIF":7.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879050","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
Improving delay and strength maps derived from resting-state fMRI using PCA-based denoising and group data from the HCP dataset 使用基于pca的去噪和分组HCP数据集的数据,改进静息状态fMRI得出的延迟和强度图
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-28 DOI: 10.1016/j.compbiomed.2025.110262
Serdar Aslan , Lia M. Hocke , Blaise B. Frederick
{"title":"Improving delay and strength maps derived from resting-state fMRI using PCA-based denoising and group data from the HCP dataset","authors":"Serdar Aslan ,&nbsp;Lia M. Hocke ,&nbsp;Blaise B. Frederick","doi":"10.1016/j.compbiomed.2025.110262","DOIUrl":"10.1016/j.compbiomed.2025.110262","url":null,"abstract":"<div><div>Resting-state functional magnetic resonance imaging (rs-fMRI) analyses use correlations in low-frequency “noise” to infer neuronal connectivity. A significant fraction of this oscillatory signal is non-neuronal, and is therefore a confound for rs-fMRI; however, we have shown that these signals carry valuable information, which can aid in clinical diagnosis and tracking recovery in stroke and moyamoya patients. Specifically, we have developed a method (RIPTiDe) that extracts blood arrival time delay (blood flow) and signal strength maps (perfusion) from BOLD data, yielding critical insight into vascular structure and function. In this study, we demonstrate a principal component analysis (PCA)-based method to denoise these rs-fMRI derived delay and strength maps to enhance signal-to-noise ratio without requiring prior knowledge of the noise percentage. We used group data from the Human Connectome Project (HCP) dataset, and conducted spectral analysis on the BOLD derived maps to identify the structural components' locations using both a naïve, and an optimized approach; we removed noise components by back-projecting only a subset of images to the original space. To assess signal reliability, we calculated the intraclass correlation coefficients (ICC) of the voxelwise parameters before and after noise removal within each subject. Mean ICC values were calculated for each projection dimension. The dimension achieving the highest ICC was selected as the signal-to-noise separation threshold for denoising. This optimized method for selecting the number of PCA components to retain increases the average ICC values of the delay and strength maps by 250 % and 108 %, respectively.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110262"},"PeriodicalIF":7.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883166","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 Global Visual Information Intervention Model for Medical Visual Question Answering 医学视觉问答的全局视觉信息干预模型
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-28 DOI: 10.1016/j.compbiomed.2025.110195
Peixi Peng , Wanshu Fan , Yue Shen , Xin Yang , Dongsheng Zhou
{"title":"A Global Visual Information Intervention Model for Medical Visual Question Answering","authors":"Peixi Peng ,&nbsp;Wanshu Fan ,&nbsp;Yue Shen ,&nbsp;Xin Yang ,&nbsp;Dongsheng Zhou","doi":"10.1016/j.compbiomed.2025.110195","DOIUrl":"10.1016/j.compbiomed.2025.110195","url":null,"abstract":"<div><div>Medical Visual Question Answering (Med-VQA) aims to furnish precise responses to clinical queries related to medical imagery. While its transformative potential in healthcare is undeniable, current solutions remain nascent and are yet to see widespread clinical adoption. Med-VQA presents heightened complexities compared to standard visual question answering (VQA) tasks due to the myriad of clinical scenarios and the scarcity of labeled medical imagery. This often culminates in language biases and overfitting vulnerabilities. In light of these challenges, this study introduces Global Visual Information Intervention (GVII), an innovative Med-VQA model designed to mitigate language biases and improve model generalizability. GVII is centered on two key branches: the Global Visual Information Branch (GVIB), which extracts and filters holistic visual data to amplify the image’s contribution and reduce question dominance, and the Forward Compensation Branch (FCB), which refines multimodal features to counterbalance disruptions introduced by GVIB. These branches work in tandem to enhance predictive accuracy and robustness. Furthermore, a multi-branch fusion mechanism ensures cohesive integration of features and losses across the model. Experimental results demonstrate that the proposed model outperforms existing state-of-the-art models, achieving a 2.6% improvement in accuracy on the PathVQA dataset. In conclusion, the GVII-based Med-VQA model not only successfully mitigates prevalent language biases and overfitting issues but also significantly improves diagnostic precision, offering a considerable stride toward robust, clinically applicable VQA systems.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110195"},"PeriodicalIF":7.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143878958","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
Identification and characterization of oncogenic KRAS G12V inhibitory peptides by phage display, molecular docking and molecular dynamic simulation 利用噬菌体展示、分子对接、分子动力学模拟等方法鉴定KRAS G12V抑癌肽
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-28 DOI: 10.1016/j.compbiomed.2025.110272
Jirakrit Saetang , Montarop Yamabhai , Kuntalee Rangnoi , Napat Prompat , Thaiyawat Haewphet , Surasak Sangkhathat , Varomyalin Tipmanee , Soottawat Benjakul
{"title":"Identification and characterization of oncogenic KRAS G12V inhibitory peptides by phage display, molecular docking and molecular dynamic simulation","authors":"Jirakrit Saetang ,&nbsp;Montarop Yamabhai ,&nbsp;Kuntalee Rangnoi ,&nbsp;Napat Prompat ,&nbsp;Thaiyawat Haewphet ,&nbsp;Surasak Sangkhathat ,&nbsp;Varomyalin Tipmanee ,&nbsp;Soottawat Benjakul","doi":"10.1016/j.compbiomed.2025.110272","DOIUrl":"10.1016/j.compbiomed.2025.110272","url":null,"abstract":"<div><div>The KRAS G12V mutation is a critical oncogenic driver in aggressive cancers, yet developing effective inhibitors remains challenging due to its elusive structural features. In this study, we employed phage display technology using both linear and cyclic peptide libraries to identify inhibitory peptides against KRAS G12V. Through subtractive bio-panning against wild-type KRAS, we identified two 23-mer peptides (Pep I and Pep II) that demonstrated selective binding to KRAS G12V. Molecular dynamics simulations revealed distinct binding mechanisms - Pep II showed stronger selective binding to G12V (−35.96 kcal/mol) compared to wild-type KRAS (−18.06 kcal/mol), while Pep I exhibited similar binding energies but interacted with different regions. Notably, Pep I bound to functional regions in KRAS G12V but non-functional regions in wild-type KRAS. Both peptides demonstrated significant inhibition of KRAS G12V-carrying cancer cell lines (NCI-H2444 and SW620), reducing cell viability by 70–75 % at 400 μM after 48 h while showing minimal effects (20–30 % reduction) on wild-type KRAS-carrying Caco-2 cells, which is equal to DMSO diluent control. These findings provide new insights into peptide-based targeting of KRAS G12V and demonstrate the potential of using subtractive phage display for developing selective inhibitors against oncogenic mutations.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110272"},"PeriodicalIF":7.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879047","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
Spatio-temporal CNN-BiLSTM dynamic approach to emotion recognition based on EEG signal 基于脑电信号的时空CNN-BiLSTM动态情感识别方法
IF 7 2区 医学
Computers in biology and medicine Pub Date : 2025-04-27 DOI: 10.1016/j.compbiomed.2025.110277
Usman Goni Redwan, Tanha Zaman, Hazzaz Bin Mizan
{"title":"Spatio-temporal CNN-BiLSTM dynamic approach to emotion recognition based on EEG signal","authors":"Usman Goni Redwan,&nbsp;Tanha Zaman,&nbsp;Hazzaz Bin Mizan","doi":"10.1016/j.compbiomed.2025.110277","DOIUrl":"10.1016/j.compbiomed.2025.110277","url":null,"abstract":"<div><div>In this paper, a hybrid CNN-BiLSTM model for EEG-based emotion detection system is presented. The proposed technique is developed by extracting features using Power Spectral Density (PSD) signal. The proposed approach is carried out by combining CNN and bidirectional LSTM models to increase the comprehension of context in sequential data. The proposed approach is tested on the widely-used SEED datasets for the accurate classification of milder emotions such as positive, negative and neutral. The proposed approach is designed with the effectiveness in extracting spatial features of CNN architecture and LSTM network are utilized for their capability in modeling temporal relationships in EEG signals. The proposed approach is robust because experimentally the proposed approach yields a rate of 97.5 % accuracy to categorize emotions, improving the performance of EEG-based emotion recognition systems, opening up new possibilities for developing advanced brain monitoring and real-time emotion-aware systems.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"192 ","pages":"Article 110277"},"PeriodicalIF":7.0,"publicationDate":"2025-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877241","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信