Computers in biology and medicine最新文献

{"title":"SpeechBrain-MOABB: An open-source Python library for benchmarking deep neural networks applied to EEG signals","authors":"","doi":"10.1016/j.compbiomed.2024.109097","DOIUrl":"10.1016/j.compbiomed.2024.109097","url":null,"abstract":"<div><p>Deep learning has revolutionized EEG decoding, showcasing its ability to outperform traditional machine learning models. However, unlike other fields, EEG decoding lacks comprehensive open-source libraries dedicated to neural networks. Existing tools (MOABB and braindecode) prevent the creation of robust and complete decoding pipelines, as they lack support for hyperparameter search across the entire pipeline, and are sensitive to fluctuations in results due to network random initialization. Furthermore, the absence of a standardized experimental protocol exacerbates the reproducibility crisis in the field. To address these limitations, we introduce SpeechBrain-MOABB, a novel open-source toolkit carefully designed to facilitate the development of a comprehensive EEG decoding pipeline based on deep learning. SpeechBrain-MOABB incorporates a complete experimental protocol that standardizes critical phases, such as hyperparameter search and model evaluation. It natively supports multi-step hyperparameter search for finding the optimal hyperparameters in a high-dimensional space defined by the entire pipeline, and multi-seed training and evaluation for obtaining performance estimates robust to the variability caused by random initialization. SpeechBrain-MOABB outperforms other libraries, including MOABB and braindecode, with accuracy improvements of 14.9% and 25.2% (on average), respectively. By enabling easy-to-use and easy-to-share decoding pipelines, our toolkit can be exploited by neuroscientists for decoding EEG with neural networks in a replicable and trustworthy way.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S001048252401182X/pdfft?md5=21410d08ca8aa7ccd223ed448678df87&pid=1-s2.0-S001048252401182X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168043","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":"Mesoscopic structure graphs for interpreting uncertainty in non-linear embeddings","authors":"","doi":"10.1016/j.compbiomed.2024.109105","DOIUrl":"10.1016/j.compbiomed.2024.109105","url":null,"abstract":"<div><p>Probabilistic-based non-linear dimensionality reduction (PB-NL-DR) methods, such as t-SNE and UMAP, are effective in unfolding complex high-dimensional manifolds, allowing users to explore and understand the structural patterns of data. However, due to the trade-off between global and local structure preservation and the randomness during computation, these methods may introduce false neighborhood relationships, known as distortion errors and misleading visualizations. To address this issue, we first conduct a detailed survey to illustrate the design space of prior layout enrichment visualizations for interpreting DR results, and then propose a node-link visualization technique, ManiGraph. This technique rethinks the neighborhood fidelity between the high- and low-dimensional spaces by constructing dynamic mesoscopic structure graphs and measuring region-adapted trustworthiness. ManiGraph also addresses the overplotting issue in scatterplot visualization for large-scale datasets and supports examining in unsupervised scenarios. We demonstrate the effectiveness of ManiGraph in different analytical cases, including generic machine learning using 3D toy data illustrations and fashion-MNIST, a computational biology study using a single-cell RNA sequencing dataset, and a deep learning-enabled colorectal cancer study with histopathology-MNIST.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168037","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":"Novel chiral phthalimides: Antimicrobial evaluation and docking study against Acinetobacter baumannii's OmpA protein","authors":"","doi":"10.1016/j.compbiomed.2024.109099","DOIUrl":"10.1016/j.compbiomed.2024.109099","url":null,"abstract":"<div><p>Antibiotics have been a vital component in the fight against microbial diseases for over 75 years, saving countless lives. However, the global rise of multi-drug-resistance (MDR) bacterial infections is pushing us closer to a post-antibiotic era where common infections may once again become lethal. To combat MDR <em>Acinetobacter baumannii</em>, we investigated chiral phthalimides and used molecular docking to identify potential targets. Outer membrane protein A (OmpA) is crucial for <em>A. baumannii</em> resistant to antibiotics, making it a pathogen of great concern due to its high mortality rate and limited treatment options. In this study, we evaluated three distinct compounds against the OmpA protein: FIA (2-(1,3-dioxoindolin-2yl)-3-phenylpropanoic acid), FIC (2-(1,3-dioxoindolin-2yl)-4-(methylthio) butanoic acid), and FII (3-(1,3-dioxoindolin-2yl)-3-phenylpropanoic acid). Molecular docking results showed that these three compounds exhibited strong interactions with the OmpA protein. Molecular dynamics (MD) simulation analysis further confirmed the stability and binding efficacy of these compounds with OmpA. Their antimicrobial activities were assessed using the agar well diffusion method, revealing that FIA had an optimal zone of inhibition of 24 mm. Additionally, the minimum inhibitory concentrations (MIC) of these compounds were determined, demonstrating their bactericidal properties against <em>A. baumannii,</em> with MICs of 11 μg/μL for FIA, 46 μg/μL for FIC, and 375 μg/μL for FII. In vitro cytotoxicity data indicated that none of the three compounds were hemolytic when exposed to human red blood cells. This finding is particularly significant as it highlights the superior efficacy of FIA against <em>A. baumannii</em> compared to the other compounds. With thorough pharmacokinetic validations, these chiral phthalimides are promising alternative therapeutic options for treating infections caused by <em>A. baumannii</em>, offering new hope in the face of rising antibiotic resistance.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168041","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":"Improving deep learning-based automatic cranial defect reconstruction by heavy data augmentation: From image registration to latent diffusion models","authors":"","doi":"10.1016/j.compbiomed.2024.109129","DOIUrl":"10.1016/j.compbiomed.2024.109129","url":null,"abstract":"<div><p>Modeling and manufacturing of personalized cranial implants are important research areas that may decrease the waiting time for patients suffering from cranial damage. The modeling of personalized implants may be partially automated by the use of deep learning-based methods. However, this task suffers from difficulties with generalizability into data from previously unseen distributions that make it difficult to use the research outcomes in real clinical settings. Due to difficulties with acquiring ground-truth annotations, different techniques to improve the heterogeneity of datasets used for training the deep networks have to be considered and introduced. In this work, we present a large-scale study of several augmentation techniques, varying from classical geometric transformations, image registration, variational autoencoders, and generative adversarial networks, to the most recent advances in latent diffusion models. We show that the use of heavy data augmentation significantly increases both the quantitative and qualitative outcomes, resulting in an average Dice Score above 0.94 for the SkullBreak and above 0.96 for the SkullFix datasets. The results show that latent diffusion models combined with vector quantized variational autoencoder outperform other generative augmentation strategies. Moreover, we show that the synthetically augmented network successfully reconstructs real clinical defects, without the need to acquire costly and time-consuming annotations. The findings of the work will lead to easier, faster, and less expensive modeling of personalized cranial implants. This is beneficial to numerous people suffering from cranial injuries. The work constitutes a considerable contribution to the field of artificial intelligence in the automatic modeling of personalized cranial implants.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524012149/pdfft?md5=b6f383ebf92a6f19bf68abaa479cd713&pid=1-s2.0-S0010482524012149-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168040","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":"The onset of coarctation of the aorta before birth: Mechanistic insights from fetal arch anatomy and haemodynamics","authors":"","doi":"10.1016/j.compbiomed.2024.109077","DOIUrl":"10.1016/j.compbiomed.2024.109077","url":null,"abstract":"<div><p>Accurate prenatal diagnosis of coarctation of the aorta (CoA) is challenging due to high false positive rate burden and poorly understood aetiology. Despite associations with abnormal blood flow dynamics, fetal arch anatomy changes and alterations in tissue properties, its underlying mechanisms remain a longstanding subject of debate hindering diagnosis in utero. This study leverages computational fluid dynamics (CFD) simulations and statistical shape modelling to investigate the interplay between fetal arch anatomy and blood flow alterations in CoA. Using cardiac magnetic resonance imaging data from 188 fetuses, including normal controls and suspected CoA cases, a statistical shape model of the fetal arch anatomy was built. From this analysis, digital twin models of false and true positive CoA cases were generated. These models were then used to perform CFD simulations of the three-dimensional fetal arch haemodynamics, considering physiological variations in arch shape and blood flow conditions across the disease spectrum. This analysis revealed that independent changes in the shape of.</p><p>the arch and the balance of left-to-right ventricular output led to qualitatively similar haemodynamic alterations. Transitioning from a false to a true positive phenotype increased retrograde flow through the aortic isthmus. This resulted in the appearance of an area of low wall shear stress surrounded by high wall shear stress values at the flow split apex on the aortic posterior wall opposite the ductal insertion point.</p><p>Our results suggest a distinctive haemodynamic signature in CoA characterised by the appearance of retrograde flow through the aortic isthmus and altered wall shear stress at its posterior side. The consistent link between alterations in shape and blood flow in CoA suggests the need for comprehensive anatomical and functional diagnostic approaches in CoA. This study presents an application of the digital twin approach to support the understanding of CoA mechanisms in utero and its potential for improved diagnosis before birth.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524011624/pdfft?md5=aa03e092b92cb388d63b773cba3ddc04&pid=1-s2.0-S0010482524011624-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168042","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":"Finite element and experimental modeling of jaw movement-induced deformations in the human earcanal","authors":"","doi":"10.1016/j.compbiomed.2024.109125","DOIUrl":"10.1016/j.compbiomed.2024.109125","url":null,"abstract":"<div><p>As ear-related technologies proliferate, optimizing comfort, retention, and battery life is crucial for enhancing user experience. A thorough understanding of the anatomical interaction between the temporomandibular joint (TMJ) and the earcanal during mouth-opening is essential. This study develops a finite element model and an experimental setup to investigate the biomechanical coupling between the TMJ and the earcanal. We analyze reverse-static deformations, focusing on cartilage-bone junction geometry, mandibular condyle location, and concha mobility. The earcanal geometry is assessed across five cross-sections with seven key dimensions measured. The results indicate that the deformations in cantilever-beam-like models closely match the reference geometry in both approaches, particularly in the lateral region. These findings suggest that a dynamic motion model of the earcanal, accurately simulating its behavior, is feasible.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168044","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":"Unanticipated evolution of cardio-respiratory interactions with cognitive load during a Go-NoGo shooting task in virtual reality","authors":"","doi":"10.1016/j.compbiomed.2024.109109","DOIUrl":"10.1016/j.compbiomed.2024.109109","url":null,"abstract":"<div><p>The cardiovascular system interacts continuously with the respiratory system to maintain the vital balance of oxygen and carbon dioxide in our body. The interplay between the sympathetic and parasympathetic branches of the autonomic nervous system regulates the aforesaid involuntary functions. This study analyzes the dynamics of the cardio-respiratory (CR) interactions using RR Intervals (RRI), Systolic Blood Pressure (SBP), and Respiration signals after first-order differencing to make them stationary. It investigates their variation with cognitive load induced by a virtual reality (VR) based Go-NoGo shooting task with low and high levels of task difficulty. We use Pearson’s correlation-based linear and mutual information-based nonlinear measures of association to indicate the reduction in RRI-SBP and RRI-Respiration interactions with cognitive load. However, no linear correlation difference was observed in SBP-Respiration interactions with cognitive load, but their mutual information increased. A couple of open-loop autoregressive models with exogenous input (ARX) are estimated using RRI and SBP, and one closed-loop ARX model is estimated using RRI, SBP, and Respiration. The impulse responses (IRs) are derived for each input–output pair, and a reduction in the positive and negative peak amplitude of all the IRs is observed with cognitive load. Some novel parameters are derived by representing the IR as a double exponential curve with cosine modulation and show significant differences with cognitive load compared to other measures, especially for the IR between SBP and Respiration.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524011946/pdfft?md5=95c54f35d0b220d83d015156aae5294a&pid=1-s2.0-S0010482524011946-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142163862","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":"Antibiotic profile classification of Proteus mirabilis using machine learning: An investigation into multidimensional radiomics features","authors":"","doi":"10.1016/j.compbiomed.2024.109131","DOIUrl":"10.1016/j.compbiomed.2024.109131","url":null,"abstract":"<div><p>Antimicrobial resistance (AMR) presents a significant threat to global healthcare. <em>Proteus mirabilis</em> causes catheter-associated urinary tract infections (CAUTIs) and exhibits increased antibiotic resistance. Traditional diagnostics still rely on culture-based approaches, which remain time-consuming. Here, we study the use of machine learning (ML) to classify bacterial resistance profiles using straightforward microscopic imaging of <em>P. mirabilis</em> for resistance classification integrated with radiomics feature analysis and ML models.</p><p>From 150 <em>P. mirabilis</em> strains isolated from catheters of patients diagnosed with a CAUTI, 30 % displayed multidrug resistance using the standardized disk diffusion method, and 60 % showed strong biofilm activity in microtiter plate assays. As a more rapid alternative, we introduce wavelet-based and regular microscopy imaging with feature extraction/selection, following image preprocessing steps (image denoising, normalization, and mask creation). These features enable training and testing different ML models with 5-fold cross-validation for <em>P. mirabilis</em> resistance classification. From these models, the Random Forest (RF) algorithm exhibited the highest performance with ACC = 0.95, specificity = 0.97, sensitivity = 0.88, and AUC = 0.98 among the other ML algorithms considered in this study for <em>P. mirabilis</em> resistance classification.</p><p>This successful application of wavelet-based feature Radiomics analysis with RF model represents a crucial step towards a precise, rapid, and cost-effective method to distinguish antibiotic resistant <em>P. mirabilis</em> strains.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142163861","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":"The transformative potential of AI-driven CRISPR-Cas9 genome editing to enhance CAR T-cell therapy","authors":"","doi":"10.1016/j.compbiomed.2024.109137","DOIUrl":"10.1016/j.compbiomed.2024.109137","url":null,"abstract":"<div><p>This narrative review examines the promising potential of integrating artificial intelligence (AI) with CRISPR-Cas9 genome editing to advance CAR T-cell therapy. AI algorithms offer unparalleled precision in identifying genetic targets, essential for enhancing the therapeutic efficacy of CAR T-cell treatments. This precision is critical for eliminating negative regulatory elements that undermine therapy effectiveness. Additionally, AI streamlines the manufacturing process, significantly reducing costs and increasing accessibility, thereby encouraging further research and development investment. A key benefit of AI integration is improved safety; by predicting and minimizing off-target effects, AI enhances the specificity of CRISPR-Cas9 edits, contributing to safer CAR T-cell therapy. This advancement is crucial for patient safety and broader clinical adoption. The convergence of AI and CRISPR-Cas9 has transformative potential, poised to revolutionize personalized immunotherapy. These innovations could expand the application of CAR T-cell therapy beyond hematologic malignancies to various solid tumors and other non-hematologic conditions, heralding a new era in cancer treatment that substantially improves patient outcomes.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524012228/pdfft?md5=9e5091baed3a845f17da4f6e8d1805c6&pid=1-s2.0-S0010482524012228-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142163863","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":"Can generative AI replace immunofluorescent staining processes? A comparison study of synthetically generated cellpainting images from brightfield","authors":"","doi":"10.1016/j.compbiomed.2024.109102","DOIUrl":"10.1016/j.compbiomed.2024.109102","url":null,"abstract":"<div><p>Cell imaging assays utilising fluorescence stains are essential for observing sub-cellular organelles and their responses to perturbations. Immunofluorescent staining process is routinely in labs, however the recent innovations in generative AI is challenging the idea of wet lab immunofluorescence (IF) staining. This is especially true when the availability and cost of specific fluorescence dyes is a problem to some labs. Furthermore, staining process takes time and leads to inter–intra-technician and hinders downstream image and data analysis, and the reusability of image data for other projects. Recent studies showed the use of generated synthetic IF images from brightfield (BF) images using generative AI algorithms in the literature. Therefore, in this study, we benchmark and compare five models from three types of IF generation backbones—CNN, GAN, and diffusion models—using a publicly available dataset. This paper not only serves as a comparative study to determine the best-performing model but also proposes a comprehensive analysis pipeline for evaluating the efficacy of generators in IF image synthesis. We highlighted the potential of deep learning-based generators for IF image synthesis, while also discussed potential issues and future research directions. Although generative AI shows promise in simplifying cell phenotyping using only BF images with IF staining, further research and validations are needed to address the key challenges of model generalisability, batch effects, feature relevance and computational costs.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524011879/pdfft?md5=173fce9fb81a23a38c28344d652ebbf9&pid=1-s2.0-S0010482524011879-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142163983","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}