Computers in biology and medicine最新文献

筛选
英文 中文
Anemia prediction using gene expression programming (GEP) and explainable artificial intelligence approaches 利用基因表达编程(GEP)和可解释的人工智能方法预测贫血
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-31 DOI: 10.1016/j.compbiomed.2025.110856
Abdullah Abdullah , Hasnain Ahmad Saddiqi , Mahnoor Qasim , Arooba Khitab , Majid Khan , Shakeel Ahmad
{"title":"Anemia prediction using gene expression programming (GEP) and explainable artificial intelligence approaches","authors":"Abdullah Abdullah ,&nbsp;Hasnain Ahmad Saddiqi ,&nbsp;Mahnoor Qasim ,&nbsp;Arooba Khitab ,&nbsp;Majid Khan ,&nbsp;Shakeel Ahmad","doi":"10.1016/j.compbiomed.2025.110856","DOIUrl":"10.1016/j.compbiomed.2025.110856","url":null,"abstract":"<div><div>Anemia being a global health disorder, affecting millions of people, especially pregnant women, children, and the elderly. Proper and timely diagnosis must be ensured to prevent its adverse effects, but the traditional diagnostic methods are very time-consuming, costly, and subject to human mistakes. This research investigates the application of Gene Expression Programming (GEP), a proven technique in machine learning (ML), in predicting anemia. A publicly available dataset on Kaggle was utilized, with clinical parameters including hemoglobin and red blood cell indices. The hyperparameters of the GEP model were best optimized, and the accuracy rate was 99.30 %. To increase the interpretability of the model, Explainable AI methods Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) were used. The findings revealed that hemoglobin levels and gender were the most significant features for predicting anemia. The work brings into limelight the usefulness of ML-based diagnostic solutions in medicine with dependable, automatic, and interpretable models for classifying anemia.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110856"},"PeriodicalIF":6.3,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739679","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
Self-supervised pre-training with joint-embedding predictive architecture boosts ECG classification performance 采用联合嵌入预测结构的自监督预训练提高了心电分类性能
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-31 DOI: 10.1016/j.compbiomed.2025.110809
Kuba Weimann, Tim O.F. Conrad
{"title":"Self-supervised pre-training with joint-embedding predictive architecture boosts ECG classification performance","authors":"Kuba Weimann,&nbsp;Tim O.F. Conrad","doi":"10.1016/j.compbiomed.2025.110809","DOIUrl":"10.1016/j.compbiomed.2025.110809","url":null,"abstract":"<div><div>Accurate diagnosis of heart arrhythmias requires the interpretation of electrocardiograms (ECG), which capture the electrical activity of the heart. Automating this process through machine learning is challenging due to the need for large annotated datasets, which are difficult and costly to collect. To address this issue, transfer learning is often employed, where models are pre-trained on large datasets and fine-tuned for specific ECG classification tasks with limited labeled data. Self-supervised learning has become a widely adopted pre-training method, enabling models to learn meaningful representations from unlabeled datasets. In this work, we explore the joint-embedding predictive architecture (JEPA) for self-supervised learning from ECG data. Unlike invariance-based methods, JEPA does not rely on hand-crafted data augmentations, and unlike generative methods, it predicts latent features rather than reconstructing input data. We create a large unsupervised pre-training dataset by combining ten public ECG databases, amounting to over one million records. We pre-train Vision Transformers using JEPA on this dataset and fine-tune them on various PTB-XL benchmarks. Our results show that JEPA outperforms existing invariance-based and generative approaches, achieving an AUC of 0.945 on the PTB-XL all statements task. JEPA consistently learns the highest quality representations, as demonstrated in frozen evaluations, and proves advantageous for pre-training even in the absence of additional data.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110809"},"PeriodicalIF":6.3,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739553","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
Interpretable one-class classification framework for prescription error detection using BERT embeddings and dimensionality reduction 使用BERT嵌入和降维的处方错误检测的可解释的一类分类框架
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-30 DOI: 10.1016/j.compbiomed.2025.110775
Yassine Ouzar , Faiza Ajmi , Sarah Ben Othman , Chloé Rousseliere , Bertrand Decaudin , Pascal Odou , Slim Hammadi
{"title":"Interpretable one-class classification framework for prescription error detection using BERT embeddings and dimensionality reduction","authors":"Yassine Ouzar ,&nbsp;Faiza Ajmi ,&nbsp;Sarah Ben Othman ,&nbsp;Chloé Rousseliere ,&nbsp;Bertrand Decaudin ,&nbsp;Pascal Odou ,&nbsp;Slim Hammadi","doi":"10.1016/j.compbiomed.2025.110775","DOIUrl":"10.1016/j.compbiomed.2025.110775","url":null,"abstract":"<div><div>Ensuring accurate prescriptions and proper medication administration is critical for patient safety and effective clinical outcomes. Identifying and preventing prescription errors can significantly reduce healthcare costs and adverse health effects. Current solutions range from rule-based systems, which rely on predefined rules and clinical expertise but lack adaptability to unexpected errors, to supervised machine learning approaches, which are hindered by limited labeled error data and opaque algorithmic processes. To overcome these limitations, we propose a prescription error detection method based on a one-class classification approach. Leveraging the publicly available MIMIC database, advanced language modeling and dimensionality reduction techniques, our framework autonomously learns meaningful representations of medication prescriptions without requiring explicit error labels. Additionally, we incorporate Lime and SHAP methods to explain the model’s predictions, providing clinicians with interpretable insights into the decision-making process and enhancing trust in the model’s reliability.</div><div>Three experiments were conducted to evaluate the effectiveness of our approach. The results reveal that leveraging BERT embeddings in conjunction with Principal Component Analysis for dimensionality reduction and Local Outlier Factor-based one-class classification achieves the highest performance, with : <span><math><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>c</mi><mi>i</mi><mi>s</mi><mi>i</mi><mi>o</mi><mi>n</mi><mo>=</mo><mn>81</mn><mo>.</mo><mn>71</mn><mtext>%</mtext></mrow></math></span>; <span><math><mrow><mi>R</mi><mi>e</mi><mi>c</mi><mi>a</mi><mi>l</mi><mi>l</mi><mo>=</mo><mn>87</mn><mo>.</mo><mn>32</mn><mtext>%</mtext></mrow></math></span>; <span><math><mrow><mi>F</mi><mn>1</mn><mtext>-</mtext><mi>s</mi><mi>c</mi><mi>o</mi><mi>r</mi><mi>e</mi><mo>=</mo><mn>86</mn><mo>.</mo><mn>84</mn><mtext>%</mtext></mrow></math></span>. These results highlight our method’s effectiveness in detecting potential prescription errors without the need for labeled error data.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110775"},"PeriodicalIF":6.3,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723530","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
M3-Net++: A multi-scale, multi-level, multi-stream network for nuclei segmentation in breast cancer histopathology using hierarchical context extraction and hybrid loss optimization M3-Net++:一个使用分层上下文提取和混合损失优化的多尺度、多层次、多流网络,用于乳腺癌组织病理学中的细胞核分割
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-30 DOI: 10.1016/j.compbiomed.2025.110804
Arbab Sufyan Wadood , Mohammad Faizal Ahmad Fauzi , Wong Lai Kuan , Jenny Tung Hiong Lee , See Yee Khor , Lai-Meng Looi
{"title":"M3-Net++: A multi-scale, multi-level, multi-stream network for nuclei segmentation in breast cancer histopathology using hierarchical context extraction and hybrid loss optimization","authors":"Arbab Sufyan Wadood ,&nbsp;Mohammad Faizal Ahmad Fauzi ,&nbsp;Wong Lai Kuan ,&nbsp;Jenny Tung Hiong Lee ,&nbsp;See Yee Khor ,&nbsp;Lai-Meng Looi","doi":"10.1016/j.compbiomed.2025.110804","DOIUrl":"10.1016/j.compbiomed.2025.110804","url":null,"abstract":"<div><div>Breast cancer remains a leading cause of morbidity and mortality worldwide. Histopathology, particularly the analysis of nuclear morphology in tissue samples, is critical for diagnosing and understanding the progression of breast cancer. Accurate nuclei segmentation plays a pivotal role in enabling detailed assessment of nuclear size, shape, and distribution patterns, which are essential for clinical diagnosis. However, traditional single-scale segmentation methods often fail to achieve this accuracy due to their inability to preserve fine details, capture broader contextual information, distinguish overlapping nuclei, and handle the inherent variability in nuclear morphology across different cell types. To address these challenges, we propose a multi-stream encoder–decoder architecture named M3-Net++ (Multi-Scale, Multi-Level, Multi-Stream Network), a novel deep learning model tailored for nuclei segmentation in histopathology images. M3-Net++ integrates both global and local tissue features for improved segmentation accuracy. The inclusion of Feature Refinement and Redundancy Elimination (FRRE) module further emphasizes critical features, while skip connections preserve high-resolution spatial information. To overcome challenges such as overlapping nuclei and class imbalance, we introduce a Hybrid Segmentation Loss (HSL) function. M3-Net++ achieves state-of-the-art performance on three benchmark datasets—ER-IHC, MoNuSAC, and CoNSeP—achieving Dice scores of 0.875, 0.871, and 0.872, and Panoptic Quality (PQ) scores of 0.730, 0.700, and 0.588, respectively, outperforming models such as HoVer-Net and SMILE. Despite these improvements, M3-Net++ remains computationally efficient, requiring only 46.18M parameters, 7.2 GB of peak GPU memory, and 0.119 s of inference time per 256×256 patch. These results highlight the robustness, adaptability, and clinical potential of M3-Net++ for breast cancer histopathology image analysis.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110804"},"PeriodicalIF":6.3,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723541","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
Efficacy of image similarity as a metric for augmenting small dataset retinal image segmentation 图像相似度作为增强小数据集视网膜图像分割的度量的有效性
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-30 DOI: 10.1016/j.compbiomed.2025.110779
Thomas Wallace , Ik Siong Heng , Senad Subasic , Chris Messenger
{"title":"Efficacy of image similarity as a metric for augmenting small dataset retinal image segmentation","authors":"Thomas Wallace ,&nbsp;Ik Siong Heng ,&nbsp;Senad Subasic ,&nbsp;Chris Messenger","doi":"10.1016/j.compbiomed.2025.110779","DOIUrl":"10.1016/j.compbiomed.2025.110779","url":null,"abstract":"<div><div>Synthetic images are an option for augmenting limited medical imaging datasets to improve the performance of various machine learning models. A common metric for evaluating synthetic image quality is the Fréchet Inception Distance (FID) which measures the similarity of two image datasets. In this study we evaluate the relationship between this metric and the improvement which synthetic images, generated by a Progressively Growing Generative Adversarial Network (PGGAN), grant when augmenting Diabetes-related Macular Edema (DME) intraretinal fluid segmentation performed by a U-Net model with limited amounts of training data. We find that the behaviour of augmenting with standard and synthetic images agrees with previously conducted experiments. Additionally, we show that dissimilar (high FID) datasets do not improve segmentation significantly. As FID between the training and augmenting datasets decreases, the augmentation datasets are shown to contribute to significant and robust improvements in image segmentation. Finally, we find that there is significant evidence to suggest that synthetic and standard augmentations follow separate log-normal trends between FID and improvements in model performance, with synthetic data proving more effective than standard augmentation techniques. Our findings show that more similar datasets (lower FID) will be more effective at improving U-Net performance, however, the results also suggest that this improvement may only occur when images are sufficiently dissimilar.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110779"},"PeriodicalIF":6.3,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723613","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
CDE-Mapper: Using retrieval-augmented language models for linking clinical data elements to controlled vocabularies CDE-Mapper:使用检索增强语言模型将临床数据元素链接到受控词汇表
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-30 DOI: 10.1016/j.compbiomed.2025.110745
Komal Gilani , Marlo Verket , Christof Peters , Michel Dumontier , Hans-Peter Brunner-La Rocca , Visara Urovi
{"title":"CDE-Mapper: Using retrieval-augmented language models for linking clinical data elements to controlled vocabularies","authors":"Komal Gilani ,&nbsp;Marlo Verket ,&nbsp;Christof Peters ,&nbsp;Michel Dumontier ,&nbsp;Hans-Peter Brunner-La Rocca ,&nbsp;Visara Urovi","doi":"10.1016/j.compbiomed.2025.110745","DOIUrl":"10.1016/j.compbiomed.2025.110745","url":null,"abstract":"<div><div>The standardization of clinical data elements (CDEs) aims to ensure consistent and comprehensive patient information across various healthcare systems. Existing methods often falter when standardizing CDEs of varying representation and complex structure, impeding data integration and interoperability in clinical research. This paper presents CDE-Mapper, a framework that combines a retrieval-augmented generation strategy with large language models to automate the alignment of CDEs with controlled vocabularies. Our modular approach features query decomposition to manage varying levels of CDEs complexity, integrates expert-defined rules within prompt engineering, and employs in-context learning alongside multiple retriever components to resolve terminological ambiguities. In addition, we propose a knowledge reservoir validated by a human-in-loop approach, achieving accurate concept linking for future applications while minimizing computational costs. For four diverse datasets, CDE-Mapper achieved an average of 7.2% higher accuracy improvement compared to baseline methods. This work highlights the potential of advanced language models in improving data harmonization and significantly advancing capabilities in clinical decision support systems and research.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110745"},"PeriodicalIF":6.3,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723528","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
Leveraging weak supervision for cell localization in digital pathology using multitask learning and consistency loss 利用多任务学习和一致性损失对数字病理学中细胞定位的弱监督
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-30 DOI: 10.1016/j.compbiomed.2025.110805
Berke Levent Cesur , Ayşe Humeyra Dur Karasayar , Pinar Bulutay , Nilgun Kapucuoglu , Cisel Aydin Mericoz , Handan Eren , Omer Faruk Dilbaz , Javidan Osmanli , Burhan Soner Yetkili , Ibrahim Kulac , Can Fahrettin Koyuncu , Cigdem Gunduz-Demir
{"title":"Leveraging weak supervision for cell localization in digital pathology using multitask learning and consistency loss","authors":"Berke Levent Cesur ,&nbsp;Ayşe Humeyra Dur Karasayar ,&nbsp;Pinar Bulutay ,&nbsp;Nilgun Kapucuoglu ,&nbsp;Cisel Aydin Mericoz ,&nbsp;Handan Eren ,&nbsp;Omer Faruk Dilbaz ,&nbsp;Javidan Osmanli ,&nbsp;Burhan Soner Yetkili ,&nbsp;Ibrahim Kulac ,&nbsp;Can Fahrettin Koyuncu ,&nbsp;Cigdem Gunduz-Demir","doi":"10.1016/j.compbiomed.2025.110805","DOIUrl":"10.1016/j.compbiomed.2025.110805","url":null,"abstract":"<div><div>Cell detection and segmentation are integral parts of automated systems in digital pathology. Encoder–decoder networks have emerged as a promising solution for these tasks. However, training of these networks has typically required full boundary annotations of cells, which are labor-intensive and difficult to obtain on a large scale. However, in many applications, such as cell counting, weaker forms of annotations–such as point annotations or approximate cell counts–can provide sufficient supervision for training. This study proposes a new mixed-supervision approach for training multitask networks in digital pathology by incorporating cell counts derived from the eyeballing process–a quick visual estimation method commonly used by pathologists. This study has two main contributions: (1) It proposes a mixed-supervision strategy for digital pathology that utilizes cell counts obtained by eyeballing as an auxiliary supervisory signal to train a multitask network for the first time. (2) This multitask network is designed to concurrently learn the tasks of cell counting and cell localization, and this study introduces a consistency loss that regularizes training by penalizing inconsistencies between the predictions of these two tasks. Our experiments on two datasets of hematoxylin-eosin stained tissue images demonstrate that the proposed approach effectively utilizes the weakest form of annotation, improving performance when stronger annotations are limited. These results highlight the potential of integrating eyeballing-derived ground truths into the network training, reducing the need for resource-intensive annotations.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110805"},"PeriodicalIF":6.3,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723531","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
FSE-Mamba: A novel Frequency-Spatial Entanglement Mamba model for retinal vessel segmentation FSE-Mamba:一种用于视网膜血管分割的新型频率-空间纠缠曼巴模型
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-30 DOI: 10.1016/j.compbiomed.2025.110776
Xutao Sun, Junwen Liu, Xiaolu Xu, Jingyi Zhou, Yonggong Ren
{"title":"FSE-Mamba: A novel Frequency-Spatial Entanglement Mamba model for retinal vessel segmentation","authors":"Xutao Sun,&nbsp;Junwen Liu,&nbsp;Xiaolu Xu,&nbsp;Jingyi Zhou,&nbsp;Yonggong Ren","doi":"10.1016/j.compbiomed.2025.110776","DOIUrl":"10.1016/j.compbiomed.2025.110776","url":null,"abstract":"<div><div>Pixel-wise segmentation of retinal vessels remains a substantial challenge in clinical and research settings. Recently, Mamba-based methods have gained significant attention due to their global receptive field and linear computational complexity. However, existing Mamba-based methods face two major limitations. Primarily, the causal constraints inherent in Mamba-based methods create directional biases that compromise their effectiveness in dense prediction tasks. Additionally, the intricate interwoven structure of retinal vessels and their high spatial similarity to surrounding tissues further exacerbate feature discrimination challenges. To address these limitations, we propose the <strong>F</strong>requency-<strong>S</strong>patial <strong>E</strong>ntanglement Mamba (FSE-Mamba) network. Specifically, the Frequency-Spatial Coordinate Mamba (FSCM) addresses directional constraints in Mamba-based architectures through multi-scale axial attention while enhancing vascular discriminability via frequency-domain guided attention. The Multi-Scale Frequency Perception Module (MSFPM) lowers pixel similarity effects by capturing inter-frequency relationships, while the Dual-domain Selective Entanglement Attention (DSEA) module integrates features across different domains through entangled learning to enhance the model’s comprehensive understanding and representation of dual-domain information. Extensive quantitative and qualitative experiments on four widely used retinal vessel segmentation datasets demonstrate that the proposed method exhibits significant competitiveness compared to existing methods. The code is made publicly available at <span><span>https://github.com/Mrxutaosun/FSE-Mamba</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110776"},"PeriodicalIF":6.3,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739678","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
Single-cell RNA sequencing reveals prolonged polyacrylamide hydrogel stimulation in vivo leads to an immunosuppressive microenvironment and potential tumorigenesis 单细胞RNA测序显示,体内长时间的聚丙烯酰胺水凝胶刺激会导致免疫抑制微环境和潜在的肿瘤发生
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-30 DOI: 10.1016/j.compbiomed.2025.110828
Zhe Liu , Meiqing Sun , Lu Lu , Xuemei Wu , Hui Wang , Yakun Gao , Antang Liu , Yuxin Qian , Hao Hu , Hua Jiang
{"title":"Single-cell RNA sequencing reveals prolonged polyacrylamide hydrogel stimulation in vivo leads to an immunosuppressive microenvironment and potential tumorigenesis","authors":"Zhe Liu ,&nbsp;Meiqing Sun ,&nbsp;Lu Lu ,&nbsp;Xuemei Wu ,&nbsp;Hui Wang ,&nbsp;Yakun Gao ,&nbsp;Antang Liu ,&nbsp;Yuxin Qian ,&nbsp;Hao Hu ,&nbsp;Hua Jiang","doi":"10.1016/j.compbiomed.2025.110828","DOIUrl":"10.1016/j.compbiomed.2025.110828","url":null,"abstract":"<div><h3>Background</h3><div>Polyacrylamide hydrogel (PAAG) was once a prevalent filler for augmentation surgery. It was banned in China in 2006 due to persistent adverse reactions. However, numerous patients who received PAAG injection still suffer from PAAG related complications, and studies on the toxic effects of PAAG in human body remains severely deficient.</div></div><div><h3>Methods</h3><div>Single-cell RNA sequencing was employed to dissect the genomic characteristics of PAAG peripheral capsules, with poly-dimethylsiloxane implant peripheral capsules serving as a control. The InferCNV method was used to identify high-CNV cells, SCENIC method was used to deduce typical transcription factors across different groups and cell types. Hematoxylin and eosin staining, along with multiplex immunofluorescence staining was used to present the pathological features of the capsular samples and to validate the results of the bioinformatics analysis.</div></div><div><h3>Results</h3><div>High copy number variation (CNV) cells within the PAAG capsules were identified, characterized by highly activated Ras and ErbB signaling pathways. The PAAG capsules were characterized with immune cell infiltration. The functional variations of macrophages, T cells and NK cells, endothelial cells and fibroblasts were also depicted. Prolonged PAAG stimulation led to the formation of foreign body giant cells, an immunosuppressive microenvironment, cellular acidification, and a robust collagen synthesis/degradation process, etc. A series of genes and ligand-receptor pairs collectively derived these biological processes, facilitated the inflammatory response to PAAG stimulation and the accumulation of high-CNV cells.</div></div><div><h3>Conclusion</h3><div>This study presented the first single-cell atlas of the PAAG capsule, offered insights into the pathophysiological process of PAAG stimulation.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110828"},"PeriodicalIF":6.3,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723527","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
Explainable multimodal hematology analysis for white blood cell classification and attribute prediction 用于白细胞分类和属性预测的可解释多模态血液学分析
IF 6.3 2区 医学
Computers in biology and medicine Pub Date : 2025-07-29 DOI: 10.1016/j.compbiomed.2025.110734
Getamesay Haile Dagnaw, Yanming Zhu, Muhammad Hassan Maqsood, Xuefei Yin, Alan Wee-Chung Liew
{"title":"Explainable multimodal hematology analysis for white blood cell classification and attribute prediction","authors":"Getamesay Haile Dagnaw,&nbsp;Yanming Zhu,&nbsp;Muhammad Hassan Maqsood,&nbsp;Xuefei Yin,&nbsp;Alan Wee-Chung Liew","doi":"10.1016/j.compbiomed.2025.110734","DOIUrl":"10.1016/j.compbiomed.2025.110734","url":null,"abstract":"<div><div>White blood cell (WBC) classification and morphological attribute prediction are critical for automated hematological analyses. To provide detailed and interpretable predictions, this paper proposes a multimodal visual–language embedding learning approach based on the contrastive language image pretraining (CLIP) model for WBC classification and attribute prediction. First, structured natural language prompts are created around WBC types and morphological attributes to offer rich semantic context that enhances the processing of multimodal inputs. Moreover, a joint-task optimization strategy is introduced to align the generated encodings from the WBC images with their corresponding structured text prompts in a shared semantic space, thus improving interpretability and prediction accuracy. Furthermore, a multi-task loss function with an adaptive weighting mechanism is employed to address class imbalance, effectively balancing classification and attribute prediction tasks to boost model performance. Experimental evaluations on publicly available datasets demonstrate that the proposed method achieves state-of-the-art performance in both WBC classification and attribute prediction.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110734"},"PeriodicalIF":6.3,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144722489","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:604180095
Book学术官方微信