首页 > 最新文献

Bioengineering最新文献

英文 中文
Anomaly Detection in Embryo Development and Morphology Using Medical Computer Vision-Aided Swin Transformer with Boosted Dipper-Throated Optimization Algorithm. 利用医学计算机视觉辅助斯温变换器与助推北斗七星优化算法检测胚胎发育和形态异常。
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-18 DOI: 10.3390/bioengineering11101044
Alanoud Al Mazroa, Mashael Maashi, Yahia Said, Mohammed Maray, Ahmad A Alzahrani, Abdulwhab Alkharashi, Ali M Al-Sharafi

Infertility affects a significant number of humans. A supported reproduction technology was verified to ease infertility problems. In vitro fertilization (IVF) is one of the best choices, and its success relies on the preference for a higher-quality embryo for transmission. These have been normally completed physically by testing embryos in a microscope. The traditional morphological calculation of embryos shows predictable disadvantages, including effort- and time-consuming and expected risks of bias related to individual estimations completed by specific embryologists. Different computer vision (CV) and artificial intelligence (AI) techniques and devices have been recently applied in fertility hospitals to improve efficacy. AI addresses the imitation of intellectual performance and the capability of technologies to simulate cognitive learning, thinking, and problem-solving typically related to humans. Deep learning (DL) and machine learning (ML) are advanced AI algorithms in various fields and are considered the main algorithms for future human assistant technology. This study presents an Embryo Development and Morphology Using a Computer Vision-Aided Swin Transformer with a Boosted Dipper-Throated Optimization (EDMCV-STBDTO) technique. The EDMCV-STBDTO technique aims to accurately and efficiently detect embryo development, which is critical for improving fertility treatments and advancing developmental biology using medical CV techniques. Primarily, the EDMCV-STBDTO method performs image preprocessing using a bilateral filter (BF) model to remove the noise. Next, the swin transformer method is implemented for the feature extraction technique. The EDMCV-STBDTO model employs the variational autoencoder (VAE) method to classify human embryo development. Finally, the hyperparameter selection of the VAE method is implemented using the boosted dipper-throated optimization (BDTO) technique. The efficiency of the EDMCV-STBDTO method is validated by comprehensive studies using a benchmark dataset. The experimental result shows that the EDMCV-STBDTO method performs better than the recent techniques.

不孕不育影响着相当多的人。经过验证,一种辅助生殖技术可以缓解不孕不育问题。体外受精(IVF)是最好的选择之一,它的成功依赖于对更高质量胚胎传输的偏好。这些通常是通过在显微镜下检测胚胎来完成的。传统的胚胎形态学计算具有可预见的缺点,包括耗费精力和时间,以及与特定胚胎学家完成的个别估计有关的预期偏差风险。为了提高效率,不孕不育医院最近采用了不同的计算机视觉(CV)和人工智能(AI)技术和设备。人工智能涉及智力表现的模仿,以及模拟与人类相关的认知学习、思考和解决问题的技术能力。深度学习(DL)和机器学习(ML)是各领域先进的人工智能算法,被认为是未来人类助手技术的主要算法。本研究介绍了一种使用计算机视觉辅助斯温变换器与助推北斗七星优化(EDMCV-STBDTO)技术的胚胎发育与形态学。EDMCV-STBDTO 技术旨在准确、高效地检测胚胎发育情况,这对于利用医学 CV 技术改善生育治疗和推进发育生物学至关重要。首先,EDMCV-STBDTO 方法使用双边滤波器(BF)模型进行图像预处理,以去除噪声。然后,在特征提取技术中采用swin transformer方法。EDMCV-STBDTO 模型采用变异自动编码器 (VAE) 方法对人类胚胎发育进行分类。最后,VAE 方法的超参数选择采用了提升北斗-茁壮优化(BDTO)技术。通过使用基准数据集进行综合研究,验证了 EDMCV-STBDTO 方法的效率。实验结果表明,EDMCV-STBDTO 方法的性能优于最新技术。
{"title":"Anomaly Detection in Embryo Development and Morphology Using Medical Computer Vision-Aided Swin Transformer with Boosted Dipper-Throated Optimization Algorithm.","authors":"Alanoud Al Mazroa, Mashael Maashi, Yahia Said, Mohammed Maray, Ahmad A Alzahrani, Abdulwhab Alkharashi, Ali M Al-Sharafi","doi":"10.3390/bioengineering11101044","DOIUrl":"https://doi.org/10.3390/bioengineering11101044","url":null,"abstract":"<p><p>Infertility affects a significant number of humans. A supported reproduction technology was verified to ease infertility problems. In vitro fertilization (IVF) is one of the best choices, and its success relies on the preference for a higher-quality embryo for transmission. These have been normally completed physically by testing embryos in a microscope. The traditional morphological calculation of embryos shows predictable disadvantages, including effort- and time-consuming and expected risks of bias related to individual estimations completed by specific embryologists. Different computer vision (CV) and artificial intelligence (AI) techniques and devices have been recently applied in fertility hospitals to improve efficacy. AI addresses the imitation of intellectual performance and the capability of technologies to simulate cognitive learning, thinking, and problem-solving typically related to humans. Deep learning (DL) and machine learning (ML) are advanced AI algorithms in various fields and are considered the main algorithms for future human assistant technology. This study presents an Embryo Development and Morphology Using a Computer Vision-Aided Swin Transformer with a Boosted Dipper-Throated Optimization (EDMCV-STBDTO) technique. The EDMCV-STBDTO technique aims to accurately and efficiently detect embryo development, which is critical for improving fertility treatments and advancing developmental biology using medical CV techniques. Primarily, the EDMCV-STBDTO method performs image preprocessing using a bilateral filter (BF) model to remove the noise. Next, the swin transformer method is implemented for the feature extraction technique. The EDMCV-STBDTO model employs the variational autoencoder (VAE) method to classify human embryo development. Finally, the hyperparameter selection of the VAE method is implemented using the boosted dipper-throated optimization (BDTO) technique. The efficiency of the EDMCV-STBDTO method is validated by comprehensive studies using a benchmark dataset. The experimental result shows that the EDMCV-STBDTO method performs better than the recent techniques.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11504009/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142493986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing Cardiovascular Risk Prediction: Development of an Advanced Xgboost Model with Hospital-Level Random Effects. 加强心血管风险预测:开发具有医院级随机效应的高级 Xgboost 模型。
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-18 DOI: 10.3390/bioengineering11101039
Tim Dong, Iyabosola Busola Oronti, Shubhra Sinha, Alberto Freitas, Bing Zhai, Jeremy Chan, Daniel P Fudulu, Massimo Caputo, Gianni D Angelini

Background: Ensemble tree-based models such as Xgboost are highly prognostic in cardiovascular medicine, as measured by the Clinical Effectiveness Metric (CEM). However, their ability to handle correlated data, such as hospital-level effects, is limited.

Objectives: The aim of this work is to develop a binary-outcome mixed-effects Xgboost (BME) model that integrates random effects at the hospital level. To ascertain how well the model handles correlated data in cardiovascular outcomes, we aim to assess its performance and compare it to fixed-effects Xgboost and traditional logistic regression models.

Methods: A total of 227,087 patients over 17 years of age, undergoing cardiac surgery from 42 UK hospitals between 1 January 2012 and 31 March 2019, were included. The dataset was split into two cohorts: training/validation (n = 157,196; 2012-2016) and holdout (n = 69,891; 2017-2019). The outcome variable was 30-day mortality with hospitals considered as the clustering variable. The logistic regression, mixed-effects logistic regression, Xgboost and binary-outcome mixed-effects Xgboost (BME) were fitted to both standardized and unstandardized datasets across a range of sample sizes and the estimated prediction power metrics were compared to identify the best approach.

Results: The exploratory study found high variability in hospital-related mortality across datasets, which supported the adoption of the mixed-effects models. Unstandardized Xgboost BME demonstrated marked improvements in prediction power over the Xgboost model at small sample size ranges, but performance differences decreased as dataset sizes increased. Generalized linear models (glms) and generalized linear mixed-effects models (glmers) followed similar results, with the Xgboost models also excelling at greater sample sizes.

Conclusions: These findings suggest that integrating mixed effects into machine learning models can enhance their performance on datasets where the sample size is small.

背景:根据临床疗效指标(CEM),Xgboost 等基于集合树的模型在心血管医学中具有很强的预后能力。然而,它们处理相关数据(如医院层面的影响)的能力有限:本研究旨在开发一种二元结果混合效应 Xgboost(BME)模型,该模型整合了医院层面的随机效应。为了确定该模型在处理心血管结果的相关数据方面有多好,我们旨在评估其性能,并将其与固定效应 Xgboost 模型和传统的逻辑回归模型进行比较:纳入了 2012 年 1 月 1 日至 2019 年 3 月 31 日期间在英国 42 家医院接受心脏手术的 227087 名 17 岁以上患者。数据集分为两个队列:训练/验证队列(n = 157196;2012-2016 年)和保留队列(n = 69891;2017-2019 年)。结果变量为 30 天死亡率,医院被视为聚类变量。对不同样本量的标准化和非标准化数据集分别拟合了逻辑回归、混合效应逻辑回归、Xgboost 和二元结果混合效应 Xgboost (BME),并对估计的预测能力指标进行了比较,以确定最佳方法:探索性研究发现,不同数据集的医院相关死亡率差异很大,这支持采用混合效应模型。在小样本量范围内,非标准化 Xgboost BME 比 Xgboost 模型明显提高了预测能力,但随着数据集规模的扩大,性能差异也在缩小。广义线性模型(glms)和广义线性混合效应模型(glmers)的结果相似,Xgboost 模型在样本量较大时也表现出色:这些研究结果表明,将混合效应整合到机器学习模型中可以提高它们在样本量较小的数据集上的性能。
{"title":"Enhancing Cardiovascular Risk Prediction: Development of an Advanced Xgboost Model with Hospital-Level Random Effects.","authors":"Tim Dong, Iyabosola Busola Oronti, Shubhra Sinha, Alberto Freitas, Bing Zhai, Jeremy Chan, Daniel P Fudulu, Massimo Caputo, Gianni D Angelini","doi":"10.3390/bioengineering11101039","DOIUrl":"https://doi.org/10.3390/bioengineering11101039","url":null,"abstract":"<p><strong>Background: </strong>Ensemble tree-based models such as Xgboost are highly prognostic in cardiovascular medicine, as measured by the Clinical Effectiveness Metric (CEM). However, their ability to handle correlated data, such as hospital-level effects, is limited.</p><p><strong>Objectives: </strong>The aim of this work is to develop a binary-outcome mixed-effects Xgboost (BME) model that integrates random effects at the hospital level. To ascertain how well the model handles correlated data in cardiovascular outcomes, we aim to assess its performance and compare it to fixed-effects Xgboost and traditional logistic regression models.</p><p><strong>Methods: </strong>A total of 227,087 patients over 17 years of age, undergoing cardiac surgery from 42 UK hospitals between 1 January 2012 and 31 March 2019, were included. The dataset was split into two cohorts: training/validation (n = 157,196; 2012-2016) and holdout (n = 69,891; 2017-2019). The outcome variable was 30-day mortality with hospitals considered as the clustering variable. The logistic regression, mixed-effects logistic regression, Xgboost and binary-outcome mixed-effects Xgboost (BME) were fitted to both standardized and unstandardized datasets across a range of sample sizes and the estimated prediction power metrics were compared to identify the best approach.</p><p><strong>Results: </strong>The exploratory study found high variability in hospital-related mortality across datasets, which supported the adoption of the mixed-effects models. Unstandardized Xgboost BME demonstrated marked improvements in prediction power over the Xgboost model at small sample size ranges, but performance differences decreased as dataset sizes increased. Generalized linear models (glms) and generalized linear mixed-effects models (glmers) followed similar results, with the Xgboost models also excelling at greater sample sizes.</p><p><strong>Conclusions: </strong>These findings suggest that integrating mixed effects into machine learning models can enhance their performance on datasets where the sample size is small.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11505330/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Development of an Oral Epithelial Ex Vivo Organ Culture Model for Biocompatibility and Permeability Assessment of Biomaterials. 开发用于生物材料生物相容性和渗透性评估的口腔上皮活体器官培养模型。
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-17 DOI: 10.3390/bioengineering11101035
Foteini Machla, Chrysanthi Bekiari, Paraskevi Kyriaki Monou, Evangelia Kofidou, Astero Maria Theodosaki, Orestis L Katsamenis, Vasileios Zisis, Maria Kokoti, Athina Bakopoulou, Dimitrios Fatouros, Dimitrios Andreadis

In the present study, a customized device (Epi-ExPer) was designed and fabricated to facilitate an epithelial organ culture, allowing for controlled exposure to exogenous chemical stimuli and accommodating the evaluation of permeation of the tissue after treatment. The Epi-ExPer system was fabricated using a stereolithography (SLA)-based additive manufacturing (AM) method. Human and porcine oral epithelial mucosa tissues were inserted into the device and exposed to resinous monomers commonly released by dental restorative materials. The effect of these xenobiotics on the morphology, viability, permeability, and expression of relevant markers of the oral epithelium was evaluated. Tissue culture could be performed with the desired orientation of air-liquid interface (ALI) conditions, and exposure to xenobiotics was undertaken in a spatially guarded and reproducible manner. Among the selected monomers, HEMA and TEGDMA reduced tissue viability at high concentrations, while tissue permeability was increased by the latter. Xenobiotics affected the histological image by introducing the vacuolar degeneration of epithelial cells and increasing the expression of panCytokeratin (pCK). Epi-ExPer device offers a simple, precise, and reproducible study system to evaluate interactions of oral mucosa with external stimuli, providing a biocompatibility and permeability assessment tool aiming to an enhanced in vitro/ex vivo-to-in vivo extrapolation (IVIVE) that complies with European Union (EU) and Food and Durg Administration (FDI) policies.

在本研究中,设计并制造了一种定制装置(Epi-ExPer),以促进上皮器官培养,使其能够受控地暴露于外源化学刺激,并在处理后评估组织的渗透情况。Epi-ExPer 系统采用基于立体光刻(SLA)的增材制造(AM)方法制造。人和猪的口腔上皮粘膜组织被插入该装置,并暴露在牙科修复材料通常释放的树脂单体中。评估了这些异种生物对口腔上皮的形态、活力、渗透性和相关标记物表达的影响。组织培养可以在所需的气液界面(ALI)条件下进行,并以空间保护和可重复的方式暴露于异种生物。在选定的单体中,HEMA 和 TEGDMA 在高浓度下会降低组织的活力,而后者会增加组织的渗透性。外来生物通过引起上皮细胞空泡变性和增加泛细胞角蛋白(pCK)的表达来影响组织学图像。Epi-ExPer 装置提供了一个简单、精确、可重复的研究系统,用于评估口腔粘膜与外部刺激的相互作用,提供了一个生物相容性和渗透性评估工具,旨在增强体外/体内到体内的外推法(IVIVE),符合欧盟(EU)和食品与药品管理局(FDI)的政策。
{"title":"Development of an Oral Epithelial Ex Vivo Organ Culture Model for Biocompatibility and Permeability Assessment of Biomaterials.","authors":"Foteini Machla, Chrysanthi Bekiari, Paraskevi Kyriaki Monou, Evangelia Kofidou, Astero Maria Theodosaki, Orestis L Katsamenis, Vasileios Zisis, Maria Kokoti, Athina Bakopoulou, Dimitrios Fatouros, Dimitrios Andreadis","doi":"10.3390/bioengineering11101035","DOIUrl":"https://doi.org/10.3390/bioengineering11101035","url":null,"abstract":"<p><p>In the present study, a customized device (Epi-ExPer) was designed and fabricated to facilitate an epithelial organ culture, allowing for controlled exposure to exogenous chemical stimuli and accommodating the evaluation of permeation of the tissue after treatment. The Epi-ExPer system was fabricated using a stereolithography (SLA)-based additive manufacturing (AM) method. Human and porcine oral epithelial mucosa tissues were inserted into the device and exposed to resinous monomers commonly released by dental restorative materials. The effect of these xenobiotics on the morphology, viability, permeability, and expression of relevant markers of the oral epithelium was evaluated. Tissue culture could be performed with the desired orientation of air-liquid interface (ALI) conditions, and exposure to xenobiotics was undertaken in a spatially guarded and reproducible manner. Among the selected monomers, HEMA and TEGDMA reduced tissue viability at high concentrations, while tissue permeability was increased by the latter. Xenobiotics affected the histological image by introducing the vacuolar degeneration of epithelial cells and increasing the expression of panCytokeratin (pCK). Epi-ExPer device offers a simple, precise, and reproducible study system to evaluate interactions of oral mucosa with external stimuli, providing a biocompatibility and permeability assessment tool aiming to an enhanced in vitro/ex vivo-to-in vivo extrapolation (IVIVE) that complies with European Union (EU) and Food and Durg Administration (FDI) policies.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11504994/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Comparative Analysis of AI Models for Atypical Pigmented Facial Lesion Diagnosis. 用于面部非典型色素病变诊断的人工智能模型对比分析
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-17 DOI: 10.3390/bioengineering11101036
Alessandra Cartocci, Alessio Luschi, Linda Tognetti, Elisa Cinotti, Francesca Farnetani, Aimilios Lallas, John Paoli, Caterina Longo, Elvira Moscarella, Danica Tiodorovic, Ignazio Stanganelli, Mariano Suppa, Emi Dika, Iris Zalaudek, Maria Antonietta Pizzichetta, Jean Luc Perrot, Gabriele Cevenini, Ernesto Iadanza, Giovanni Rubegni, Harald Kittler, Philipp Tschandl, Pietro Rubegni

Diagnosing atypical pigmented facial lesions (aPFLs) is a challenging topic for dermatologists. Accurate diagnosis of these lesions is crucial for effective patient management, especially in dermatology, where visual assessment plays a central role. Incorrect diagnoses can result in mismanagement, delays in appropriate interventions, and potential harm. AI, however, holds the potential to enhance diagnostic accuracy and provide reliable support to clinicians. This work aimed to evaluate and compare the effectiveness of machine learning (logistic regression of lesion features and patient metadata) and deep learning (CNN analysis of images) models in dermoscopy diagnosis and the management of aPFLs. This study involved the analysis of 1197 dermoscopic images of facial lesions excised due to suspicious and histologically confirmed malignancy, classified into seven classes (lentigo maligna-LM; lentigo maligna melanoma-LMM; atypical nevi-AN; pigmented actinic keratosis-PAK; solar lentigo-SL; seborrheic keratosis-SK; and seborrheic lichenoid keratosis-SLK). Image samples were collected through the Integrated Dermoscopy Score (iDScore) project. The statistical analysis of the dataset shows that the patients mean age was 65.5 ± 14.2, and the gender was equally distributed (580 males-48.5%; 617 females-51.5%). A total of 41.7% of the sample constituted malignant lesions (LM and LMM). Meanwhile, the benign lesions were mainly PAK (19.3%), followed by SL (22.2%), AN (10.4%), SK (4.0%), and SLK (2.3%). The lesions were mainly localised in the cheek and nose areas. A stratified analysis of the assessment provided by the enrolled dermatologists was also performed, resulting in 2445 evaluations of the 1197 images (2.1 evaluations per image on average). The physicians demonstrated higher accuracy in differentiating between malignant and benign lesions (71.2%) than in distinguishing between the seven specific diagnoses across all the images (42.9%). The logistic regression model obtained a precision of 39.1%, a sensitivity of 100%, a specificity of 33.9%, and an accuracy of 53.6% on the test set, while the CNN model showed lower sensitivity (58.2%) and higher precision (47.0%), specificity (90.8%), and accuracy (59.5%) for melanoma diagnosis. This research demonstrates how AI can enhance the diagnostic accuracy in complex dermatological cases like aPFLs by integrating AI models with clinical data and evaluating different diagnostic approaches, paving the way for more precise and scalable AI applications in dermatology, showing their critical role in improving patient management and the outcomes in dermatology.

对皮肤科医生来说,诊断面部非典型色素性病变(aPFLs)是一个具有挑战性的课题。准确诊断这些病变对于有效管理患者至关重要,尤其是在皮肤科,视觉评估在其中发挥着核心作用。不正确的诊断会导致管理不善、适当干预的延误以及潜在的伤害。然而,人工智能具有提高诊断准确性并为临床医生提供可靠支持的潜力。这项工作旨在评估和比较机器学习(病变特征和患者元数据的逻辑回归)和深度学习(图像的 CNN 分析)模型在皮肤镜检查诊断和 aPFLs 管理中的有效性。本研究分析了 1197 张皮肤镜图像,这些图像是因可疑和组织学证实的恶性肿瘤而切除的面部病变,分为七类(恶性肿瘤-LM;恶性黑色素瘤-LMM;非典型痣-AN;色素性光化性角化病-PAK;日光性皮肤病-SL;脂溢性角化病-SK;脂溢性苔藓样角化病-SLK)。图像样本是通过皮肤镜综合评分(iDScore)项目收集的。数据集的统计分析显示,患者的平均年龄为(65.5 ± 14.2)岁,性别分布平均(580 名男性-48.5%;617 名女性-51.5%)。41.7%的样本为恶性病变(LM 和 LMM)。与此同时,良性病变主要是 PAK(19.3%),其次是 SL(22.2%)、AN(10.4%)、SK(4.0%)和 SLK(2.3%)。病变主要集中在脸颊和鼻子部位。我们还对入选的皮肤科医生提供的评估进行了分层分析,结果是对 1197 张图像进行了 2445 次评估(平均每张图像 2.1 次评估)。医生们区分恶性和良性病变的准确率(71.2%)高于区分所有图像中七个特定诊断的准确率(42.9%)。逻辑回归模型在测试集上的精确度为 39.1%,灵敏度为 100%,特异度为 33.9%,准确度为 53.6%,而 CNN 模型在黑色素瘤诊断方面的灵敏度较低(58.2%),精确度(47.0%)、特异度(90.8%)和准确度(59.5%)较高。这项研究展示了人工智能如何通过将人工智能模型与临床数据相结合并评估不同的诊断方法来提高复杂皮肤病病例(如 aPFLs)的诊断准确性,为更精确、可扩展的人工智能在皮肤病学中的应用铺平了道路,显示了人工智能在改善患者管理和皮肤病学治疗效果方面的关键作用。
{"title":"Comparative Analysis of AI Models for Atypical Pigmented Facial Lesion Diagnosis.","authors":"Alessandra Cartocci, Alessio Luschi, Linda Tognetti, Elisa Cinotti, Francesca Farnetani, Aimilios Lallas, John Paoli, Caterina Longo, Elvira Moscarella, Danica Tiodorovic, Ignazio Stanganelli, Mariano Suppa, Emi Dika, Iris Zalaudek, Maria Antonietta Pizzichetta, Jean Luc Perrot, Gabriele Cevenini, Ernesto Iadanza, Giovanni Rubegni, Harald Kittler, Philipp Tschandl, Pietro Rubegni","doi":"10.3390/bioengineering11101036","DOIUrl":"https://doi.org/10.3390/bioengineering11101036","url":null,"abstract":"<p><p>Diagnosing atypical pigmented facial lesions (aPFLs) is a challenging topic for dermatologists. Accurate diagnosis of these lesions is crucial for effective patient management, especially in dermatology, where visual assessment plays a central role. Incorrect diagnoses can result in mismanagement, delays in appropriate interventions, and potential harm. AI, however, holds the potential to enhance diagnostic accuracy and provide reliable support to clinicians. This work aimed to evaluate and compare the effectiveness of machine learning (logistic regression of lesion features and patient metadata) and deep learning (CNN analysis of images) models in dermoscopy diagnosis and the management of aPFLs. This study involved the analysis of 1197 dermoscopic images of facial lesions excised due to suspicious and histologically confirmed malignancy, classified into seven classes (lentigo maligna-LM; lentigo maligna melanoma-LMM; atypical nevi-AN; pigmented actinic keratosis-PAK; solar lentigo-SL; seborrheic keratosis-SK; and seborrheic lichenoid keratosis-SLK). Image samples were collected through the Integrated Dermoscopy Score (iDScore) project. The statistical analysis of the dataset shows that the patients mean age was 65.5 ± 14.2, and the gender was equally distributed (580 males-48.5%; 617 females-51.5%). A total of 41.7% of the sample constituted malignant lesions (LM and LMM). Meanwhile, the benign lesions were mainly PAK (19.3%), followed by SL (22.2%), AN (10.4%), SK (4.0%), and SLK (2.3%). The lesions were mainly localised in the cheek and nose areas. A stratified analysis of the assessment provided by the enrolled dermatologists was also performed, resulting in 2445 evaluations of the 1197 images (2.1 evaluations per image on average). The physicians demonstrated higher accuracy in differentiating between malignant and benign lesions (71.2%) than in distinguishing between the seven specific diagnoses across all the images (42.9%). The logistic regression model obtained a precision of 39.1%, a sensitivity of 100%, a specificity of 33.9%, and an accuracy of 53.6% on the test set, while the CNN model showed lower sensitivity (58.2%) and higher precision (47.0%), specificity (90.8%), and accuracy (59.5%) for melanoma diagnosis. This research demonstrates how AI can enhance the diagnostic accuracy in complex dermatological cases like aPFLs by integrating AI models with clinical data and evaluating different diagnostic approaches, paving the way for more precise and scalable AI applications in dermatology, showing their critical role in improving patient management and the outcomes in dermatology.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11504969/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142493999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The Psychological Nature of Female Gait Attractiveness. 女性步态吸引力的心理本质
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-17 DOI: 10.3390/bioengineering11101037
Hiroko Tanabe, Kota Yamamoto

Walking, a basic physical movement of the human body, is a resource for observers in forming interpersonal impressions. We have previously investigated the expression and perception of the attractiveness of female gaits. In this paper, drawing on our previous research, additional analysis, and reviewing previous studies, we seek to deepen our understanding of the function of gait attractiveness. First, we review previous research on gait as nonverbal information. Then, we show that fashion models' gaits reflect sociocultural genderlessness, while nonmodels express reproductive-related biological attractiveness. Next, we discuss the functions of gait attractiveness based on statistical models that link gait parameters and attractiveness scores. Finally, we focus on observers' perception of attractiveness, constructing a model of the visual information processing with respect to gait attractiveness. Overall, our results suggest that there are not only biological but also sociocultural criteria for gait attractiveness, and men and women place greater importance on the former and latter criteria, respectively, when assessing female gait attractiveness. This paper forms a major step forward in neuroaesthetics to understand the beauty of the human body and the generation of biological motions.

行走是人体的基本运动,是观察者形成人际印象的资源。我们曾研究过女性步态吸引力的表达和感知。在本文中,我们将借鉴之前的研究、补充分析以及对之前研究的回顾,力求加深我们对步态吸引力功能的理解。首先,我们回顾了之前关于步态作为非语言信息的研究。然后,我们展示了时装模特的步态反映了社会文化的无性别性,而非模特则表达了与生殖相关的生物吸引力。接下来,我们根据步态参数和吸引力得分之间的联系建立统计模型,讨论步态吸引力的功能。最后,我们将重点放在观察者对吸引力的感知上,构建了一个关于步态吸引力的视觉信息处理模型。总之,我们的研究结果表明,步态吸引力不仅有生物标准,也有社会文化标准,男性和女性在评估女性步态吸引力时,分别更重视前者和后者。本文是神经美学在理解人体美和生物运动生成方面迈出的重要一步。
{"title":"The Psychological Nature of Female Gait Attractiveness.","authors":"Hiroko Tanabe, Kota Yamamoto","doi":"10.3390/bioengineering11101037","DOIUrl":"https://doi.org/10.3390/bioengineering11101037","url":null,"abstract":"<p><p>Walking, a basic physical movement of the human body, is a resource for observers in forming interpersonal impressions. We have previously investigated the expression and perception of the attractiveness of female gaits. In this paper, drawing on our previous research, additional analysis, and reviewing previous studies, we seek to deepen our understanding of the function of gait attractiveness. First, we review previous research on gait as nonverbal information. Then, we show that fashion models' gaits reflect sociocultural genderlessness, while nonmodels express reproductive-related biological attractiveness. Next, we discuss the functions of gait attractiveness based on statistical models that link gait parameters and attractiveness scores. Finally, we focus on observers' perception of attractiveness, constructing a model of the visual information processing with respect to gait attractiveness. Overall, our results suggest that there are not only biological but also sociocultural criteria for gait attractiveness, and men and women place greater importance on the former and latter criteria, respectively, when assessing female gait attractiveness. This paper forms a major step forward in neuroaesthetics to understand the beauty of the human body and the generation of biological motions.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11504962/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mechanosensitive Differentiation of Human iPS Cell-Derived Podocytes. 人类 iPS 细胞衍生荚膜细胞的机械敏感性分化
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-17 DOI: 10.3390/bioengineering11101038
Yize Zhang, Samira Musah

Stem cell fate decisions, including proliferation, differentiation, morphological changes, and viability, are impacted by microenvironmental cues such as physical and biochemical signals. However, the specific impact of matrix elasticity on kidney cell development and function remains less understood due to the lack of models that can closely recapitulate human kidney biology. An established protocol to differentiate podocytes from human-induced pluripotent stem (iPS) cells provides a promising avenue to elucidate the role of matrix elasticity in kidney tissue development and lineage determination. In this study, we synthesized polyacrylamide hydrogels with different stiffnesses and investigated their ability to promote podocyte differentiation and biomolecular characteristics. We found that 3 kPa and 10 kPa hydrogels significantly support the adhesion, differentiation, and viability of podocytes. Differentiating podocytes on a more compliant (0.7 kPa) hydrogel resulted in significant cell loss and detachment. Further investigation of the mechanosensitive proteins yes-associated protein (YAP) and synaptopodin revealed nuanced molecular distinctions in cellular responses to matrix elasticity that may otherwise be overlooked if morphology and cell spreading alone were used as the primary metric for selecting matrices for podocyte differentiation. Specifically, hydrogels with kidney-like rigidities outperformed traditional tissue culture plates at modulating the molecular-level expression of active mechanosensitive proteins critical for podocyte health and function. These findings could guide the development of physiologically relevant platforms for kidney tissue engineering, disease modeling, and mechanistic studies of organ physiology and pathophysiology. Such advances are critical for realizing the full potential of in vitro platforms in accurately predicting human biological responses.

干细胞的命运决定(包括增殖、分化、形态变化和存活能力)受到微环境线索(如物理和生化信号)的影响。然而,由于缺乏能近似再现人类肾脏生物学的模型,人们对基质弹性对肾脏细胞发育和功能的具体影响仍然知之甚少。从人类诱导多能干细胞(iPS)分化荚膜细胞的既定方案为阐明基质弹性在肾脏组织发育和血统决定中的作用提供了一条很有希望的途径。在这项研究中,我们合成了不同硬度的聚丙烯酰胺水凝胶,并研究了它们促进荚膜细胞分化的能力和生物分子特性。我们发现,3 kPa 和 10 kPa 水凝胶可显著支持荚膜细胞的粘附、分化和存活。在顺应性更强(0.7 千帕)的水凝胶上分化荚膜细胞会导致细胞大量丢失和脱落。对机械敏感蛋白 "是 "相关蛋白(YAP)和突触蛋白的进一步研究揭示了细胞对基质弹性反应的细微分子差异,如果仅将形态学和细胞铺展作为选择荚膜细胞分化基质的主要指标,这些差异可能会被忽视。具体来说,在调节对荚膜细胞健康和功能至关重要的活性机械敏感蛋白的分子水平表达方面,具有肾脏样刚性的水凝胶优于传统的组织培养板。这些发现可以指导肾脏组织工程、疾病建模以及器官生理学和病理生理学机理研究的生理相关平台的开发。这些进展对于充分发挥体外平台在准确预测人体生物反应方面的潜力至关重要。
{"title":"Mechanosensitive Differentiation of Human iPS Cell-Derived Podocytes.","authors":"Yize Zhang, Samira Musah","doi":"10.3390/bioengineering11101038","DOIUrl":"https://doi.org/10.3390/bioengineering11101038","url":null,"abstract":"<p><p>Stem cell fate decisions, including proliferation, differentiation, morphological changes, and viability, are impacted by microenvironmental cues such as physical and biochemical signals. However, the specific impact of matrix elasticity on kidney cell development and function remains less understood due to the lack of models that can closely recapitulate human kidney biology. An established protocol to differentiate podocytes from human-induced pluripotent stem (iPS) cells provides a promising avenue to elucidate the role of matrix elasticity in kidney tissue development and lineage determination. In this study, we synthesized polyacrylamide hydrogels with different stiffnesses and investigated their ability to promote podocyte differentiation and biomolecular characteristics. We found that 3 kPa and 10 kPa hydrogels significantly support the adhesion, differentiation, and viability of podocytes. Differentiating podocytes on a more compliant (0.7 kPa) hydrogel resulted in significant cell loss and detachment. Further investigation of the mechanosensitive proteins yes-associated protein (YAP) and synaptopodin revealed nuanced molecular distinctions in cellular responses to matrix elasticity that may otherwise be overlooked if morphology and cell spreading alone were used as the primary metric for selecting matrices for podocyte differentiation. Specifically, hydrogels with kidney-like rigidities outperformed traditional tissue culture plates at modulating the molecular-level expression of active mechanosensitive proteins critical for podocyte health and function. These findings could guide the development of physiologically relevant platforms for kidney tissue engineering, disease modeling, and mechanistic studies of organ physiology and pathophysiology. Such advances are critical for realizing the full potential of in vitro platforms in accurately predicting human biological responses.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11504473/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Probiotic Enterococcus Faecium Attenuated Atherosclerosis by Improving SCFAs Associated with Gut Microbiota in ApoE-/- Mice. 益生菌肠球菌通过改善载脂蛋白E-/-小鼠肠道微生物群相关的 SCFAs 来减轻动脉粥样硬化。
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-16 DOI: 10.3390/bioengineering11101033
Yuan Zhu, Chao Yin, Yeqi Wang

Atherosclerosis, as the main root cause, makes cardiovascular diseases (CVDs) a substantial worldwide health concern. Inflammation and disrupted cholesterol metabolism are the primary clinical risk elements contributing to the onset of atherosclerosis. Few works exist on the improvement effect of gut microbiota on atherosclerosis. One specific probiotic strain, Enterococcus faecium NCIMB11508, has shown promise in mitigating inflammation. Consequently, it is critical to investigate its potential in reducing the progression of atherosclerosis. In our study, we administered E. faecium NCIMB11508 orally to ApoE-/- mice, resulting in a decrease in the formation of atherosclerotic lesions. Additionally, it demonstrated the ability to lower the inflammatory factor levels both in the aorta and blood serum while maintaining the integrity of the small intestine against lipopolysaccharides. Moreover, E. faecium NCIMB11508 had a beneficial impact on the gut microbiota composition by increasing the levels of short-chain fatty acids (SCFAs), which in turn helped to reduce inflammation and protect the intestine. The probiotic E. faecium NCIMB11508, according to our research, has a definitive capacity to prevent atherosclerosis progression by beneficially altering the SCFA composition in the gut microbiota of ApoE-/- mice.

动脉粥样硬化是导致心血管疾病(CVDs)的主要根源,也是全球关注的重大健康问题。炎症和胆固醇代谢紊乱是导致动脉粥样硬化发病的主要临床风险因素。关于肠道微生物群对动脉粥样硬化的改善作用,目前鲜有研究。一种特殊的益生菌株,即粪肠球菌 NCIMB11508,已显示出缓解炎症的前景。因此,研究它在减少动脉粥样硬化进展方面的潜力至关重要。在我们的研究中,我们给载脂蛋白E-/-小鼠口服粪肠球菌 NCIMB11508,结果发现动脉粥样硬化病变的形成有所减少。此外,它还能降低主动脉和血清中的炎症因子水平,同时保持小肠对脂多糖的完整性。此外,粪肠球菌 NCIMB11508 还通过增加短链脂肪酸(SCFAs)的含量对肠道微生物群的组成产生了有益的影响,这反过来又有助于减轻炎症和保护肠道。根据我们的研究,益生菌E. faecium NCIMB11508通过有益地改变载脂蛋白E-/-小鼠肠道微生物群中的SCFA组成,具有明确的预防动脉粥样硬化进展的能力。
{"title":"Probiotic Enterococcus Faecium Attenuated Atherosclerosis by Improving SCFAs Associated with Gut Microbiota in ApoE<sup>-/-</sup> Mice.","authors":"Yuan Zhu, Chao Yin, Yeqi Wang","doi":"10.3390/bioengineering11101033","DOIUrl":"https://doi.org/10.3390/bioengineering11101033","url":null,"abstract":"<p><p>Atherosclerosis, as the main root cause, makes cardiovascular diseases (CVDs) a substantial worldwide health concern. Inflammation and disrupted cholesterol metabolism are the primary clinical risk elements contributing to the onset of atherosclerosis. Few works exist on the improvement effect of gut microbiota on atherosclerosis. One specific probiotic strain, Enterococcus faecium NCIMB11508, has shown promise in mitigating inflammation. Consequently, it is critical to investigate its potential in reducing the progression of atherosclerosis. In our study, we administered <i>E. faecium</i> NCIMB11508 orally to ApoE<sup>-/-</sup> mice, resulting in a decrease in the formation of atherosclerotic lesions. Additionally, it demonstrated the ability to lower the inflammatory factor levels both in the aorta and blood serum while maintaining the integrity of the small intestine against lipopolysaccharides. Moreover, <i>E. faecium</i> NCIMB11508 had a beneficial impact on the gut microbiota composition by increasing the levels of short-chain fatty acids (SCFAs), which in turn helped to reduce inflammation and protect the intestine. The probiotic <i>E. faecium</i> NCIMB11508, according to our research, has a definitive capacity to prevent atherosclerosis progression by beneficially altering the SCFA composition in the gut microbiota of ApoE<sup>-/-</sup> mice.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11505145/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142516273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Precision Segmentation of Subretinal Fluids in OCT Using Multiscale Attention-Based U-Net Architecture. 利用基于多尺度注意力的 U-Net 架构精确分割 OCT 中的视网膜下液体
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-16 DOI: 10.3390/bioengineering11101032
Prakash Kumar Karn, Waleed H Abdulla

This paper presents a deep-learning architecture for segmenting retinal fluids in patients with Diabetic Macular Oedema (DME) and Age-related Macular Degeneration (AMD). Accurate segmentation of multiple fluid types is critical for diagnosis and treatment planning, but existing techniques often struggle with precision. We propose an encoder-decoder network inspired by U-Net, processing enhanced OCT images and their edge maps. The encoder incorporates Residual and Inception modules with an autoencoder-based multiscale attention mechanism to extract detailed features. Our method shows superior performance across several datasets. On the RETOUCH dataset, the network achieved F1 Scores of 0.82 for intraretinal fluid (IRF), 0.93 for subretinal fluid (SRF), and 0.94 for pigment epithelial detachment (PED). The model also performed well on the OPTIMA and DUKE datasets, demonstrating high precision, recall, and F1 Scores. This architecture significantly enhances segmentation accuracy and edge precision, offering a valuable tool for diagnosing and managing retinal diseases. Its integration of dual-input processing, multiscale attention, and advanced encoder modules highlights its potential to improve clinical outcomes and advance retinal disease treatment.

本文介绍了一种用于分割糖尿病黄斑水肿(DME)和老年性黄斑变性(AMD)患者视网膜液体的深度学习架构。准确分割多种类型的液体对于诊断和治疗计划至关重要,但现有技术往往在精确性方面存在困难。我们提出了一种受 U-Net 启发的编码器-解码器网络,用于处理增强型 OCT 图像及其边缘图。编码器结合了残差模块和插入模块,并采用基于自动编码器的多尺度关注机制来提取细节特征。我们的方法在多个数据集上表现出卓越的性能。在 RETOUCH 数据集上,该网络的视网膜内积液 (IRF) F1 分数达到 0.82,视网膜下积液 (SRF) F1 分数达到 0.93,色素上皮脱落 (PED) F1 分数达到 0.94。该模型在 OPTIMA 和 DUKE 数据集上也表现出色,显示出较高的精确度、召回率和 F1 分数。该架构大大提高了分割准确度和边缘精确度,为诊断和管理视网膜疾病提供了宝贵的工具。它集成了双输入处理、多尺度关注和高级编码器模块,突出了其改善临床结果和推进视网膜疾病治疗的潜力。
{"title":"Precision Segmentation of Subretinal Fluids in OCT Using Multiscale Attention-Based U-Net Architecture.","authors":"Prakash Kumar Karn, Waleed H Abdulla","doi":"10.3390/bioengineering11101032","DOIUrl":"https://doi.org/10.3390/bioengineering11101032","url":null,"abstract":"<p><p>This paper presents a deep-learning architecture for segmenting retinal fluids in patients with Diabetic Macular Oedema (DME) and Age-related Macular Degeneration (AMD). Accurate segmentation of multiple fluid types is critical for diagnosis and treatment planning, but existing techniques often struggle with precision. We propose an encoder-decoder network inspired by U-Net, processing enhanced OCT images and their edge maps. The encoder incorporates Residual and Inception modules with an autoencoder-based multiscale attention mechanism to extract detailed features. Our method shows superior performance across several datasets. On the RETOUCH dataset, the network achieved F1 Scores of 0.82 for intraretinal fluid (IRF), 0.93 for subretinal fluid (SRF), and 0.94 for pigment epithelial detachment (PED). The model also performed well on the OPTIMA and DUKE datasets, demonstrating high precision, recall, and F1 Scores. This architecture significantly enhances segmentation accuracy and edge precision, offering a valuable tool for diagnosing and managing retinal diseases. Its integration of dual-input processing, multiscale attention, and advanced encoder modules highlights its potential to improve clinical outcomes and advance retinal disease treatment.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11504175/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142516272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches. 医学图像分割的进展:传统、深度学习和混合方法的全面回顾。
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-16 DOI: 10.3390/bioengineering11101034
Yan Xu, Rixiang Quan, Weiting Xu, Yi Huang, Xiaolong Chen, Fengyuan Liu

Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across a wide range of clinical tasks. This review begins by offering a comprehensive overview of traditional segmentation techniques, including thresholding, edge-based methods, region-based approaches, clustering, and graph-based segmentation. While these methods are computationally efficient and interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus of this review is the transformative impact of deep learning on medical image segmentation. We delve into prominent deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), U-Net, Recurrent Neural Networks (RNNs), Adversarial Networks (GANs), and Autoencoders (AEs). Each architecture is analyzed in terms of its structural foundation and specific application to medical image segmentation, illustrating how these models have enhanced segmentation accuracy across various clinical contexts. Finally, the review examines the integration of deep learning with traditional segmentation methods, addressing the limitations of both approaches. These hybrid strategies offer improved segmentation performance, particularly in challenging scenarios involving weak edges, noise, or inconsistent intensities. By synthesizing recent advancements, this review provides a detailed resource for researchers and practitioners, offering valuable insights into the current landscape and future directions of medical image segmentation.

医学影像分割在精确诊断和治疗计划中起着至关重要的作用,可对各种临床任务进行精确分析。本综述首先全面概述了传统的分割技术,包括阈值法、基于边缘的方法、基于区域的方法、聚类和基于图的分割。虽然这些方法计算效率高、可解释性强,但在应用于复杂、嘈杂或多变的医学影像时往往面临巨大挑战。本综述的核心重点是深度学习对医学影像分割的变革性影响。我们深入探讨了著名的深度学习架构,如卷积神经网络(CNN)、全卷积网络(FCN)、U-Net、循环神经网络(RNN)、对抗网络(GAN)和自动编码器(AE)。综述从结构基础和医学影像分割的具体应用两方面分析了每种架构,说明了这些模型如何在各种临床环境中提高分割准确性。最后,综述探讨了深度学习与传统分割方法的整合,解决了两种方法的局限性。这些混合策略提高了分割性能,尤其是在涉及弱边缘、噪声或强度不一致的挑战性场景中。通过综合最新进展,本综述为研究人员和从业人员提供了详尽的资源,为医学影像分割的现状和未来方向提供了宝贵的见解。
{"title":"Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches.","authors":"Yan Xu, Rixiang Quan, Weiting Xu, Yi Huang, Xiaolong Chen, Fengyuan Liu","doi":"10.3390/bioengineering11101034","DOIUrl":"https://doi.org/10.3390/bioengineering11101034","url":null,"abstract":"<p><p>Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across a wide range of clinical tasks. This review begins by offering a comprehensive overview of traditional segmentation techniques, including thresholding, edge-based methods, region-based approaches, clustering, and graph-based segmentation. While these methods are computationally efficient and interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus of this review is the transformative impact of deep learning on medical image segmentation. We delve into prominent deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), U-Net, Recurrent Neural Networks (RNNs), Adversarial Networks (GANs), and Autoencoders (AEs). Each architecture is analyzed in terms of its structural foundation and specific application to medical image segmentation, illustrating how these models have enhanced segmentation accuracy across various clinical contexts. Finally, the review examines the integration of deep learning with traditional segmentation methods, addressing the limitations of both approaches. These hybrid strategies offer improved segmentation performance, particularly in challenging scenarios involving weak edges, noise, or inconsistent intensities. By synthesizing recent advancements, this review provides a detailed resource for researchers and practitioners, offering valuable insights into the current landscape and future directions of medical image segmentation.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11505408/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142493983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The Utility of Indocyanine Green Angiography in Breast Reconstruction to Detect Mastectomy Skin Flap Necrosis and Free Flap Perfusion: An Umbrella Review. 吲哚青绿血管造影在乳房重建中检测乳房切除皮瓣坏死和游离皮瓣灌注的实用性:综述。
IF 3.8 3区 医学 Q2 ENGINEERING, BIOMEDICAL Pub Date : 2024-10-15 DOI: 10.3390/bioengineering11101025
Nicholas Fadell, Flora Laurent, Sai Anusha Sanka, Esther Ochoa, Lauren Yaeger, Xiaowei Li, Matthew D Wood, Justin M Sacks, Saif Badran

Two of the greatest challenges in breast reconstruction are mastectomy skin flap necrosis (MSFN) and autologous flap failure. This review summarizes current evidence regarding the usage of indocyanine green angiography (ICGA) in breast reconstruction, identifies knowledge gaps, and provides directions for future studies. An umbrella review was conducted to identify related syntheses in Embase, Ovid Medline, Scopus, the Cochrane Central Register of Controlled Trials, the Cochrane Database of Systematic Reviews, and the Clinical Trials databases. Data were extracted from systematic reviews (SRs) and meta-analyses (MAs) that discussed the use of ICGA in breast reconstruction. Sixteen syntheses were included (10 SRs and 6 MAs). Syntheses showed much evidence that ICGA usage typically reduces MSFN rates. However, it tends to overpredict necrosis and is best utilized in high-risk patients or those with an unclear clinical picture. ICGA is also useful in autologous breast reconstruction by reducing rates of breast fat necrosis (BFN), total flap loss, and reoperation. ICGA usage may also aid in perforator mapping and selection intraoperatively, with minimal complication risk. Most syntheses had moderate quality scores; however, they were small with significant heterogeneity in protocols and complication definitions. The use of ICGA in breast reconstruction is safe and useful in decreasing rates of MSFN, BFN, and reoperation after free flap reconstruction.

乳房重建的两大难题是乳房切除皮瓣坏死(MSFN)和自体皮瓣失败。本综述总结了目前有关在乳房重建中使用吲哚青绿血管造影术(ICGA)的证据,指出了知识差距,并为今后的研究提供了方向。我们在 Embase、Ovid Medline、Scopus、Cochrane Central Register of Controlled Trials、Cochrane Database of Systematic Reviews 和 Clinical Trials 数据库中对相关综述进行了汇总。从讨论 ICGA 用于乳房重建的系统综述 (SR) 和荟萃分析 (MA) 中提取数据。共纳入 16 篇综述(10 篇系统综述和 6 篇荟萃分析)。综述显示,很多证据表明使用 ICGA 通常会降低 MSFN 发生率。但是,它往往会过度预测坏死,最好用于高风险患者或临床症状不明确的患者。ICGA 在自体乳房重建中也很有用,它能降低乳房脂肪坏死 (BFN)、皮瓣完全脱落和再次手术的发生率。使用 ICGA 还有助于在术中绘制和选择穿孔器,并将并发症风险降至最低。大多数综述的质量评分为中等;但这些综述的规模较小,在方案和并发症定义方面存在明显的异质性。在乳房重建中使用 ICGA 是安全的,有助于降低游离皮瓣重建后 MSFN、BFN 和再次手术的发生率。
{"title":"The Utility of Indocyanine Green Angiography in Breast Reconstruction to Detect Mastectomy Skin Flap Necrosis and Free Flap Perfusion: An Umbrella Review.","authors":"Nicholas Fadell, Flora Laurent, Sai Anusha Sanka, Esther Ochoa, Lauren Yaeger, Xiaowei Li, Matthew D Wood, Justin M Sacks, Saif Badran","doi":"10.3390/bioengineering11101025","DOIUrl":"https://doi.org/10.3390/bioengineering11101025","url":null,"abstract":"<p><p>Two of the greatest challenges in breast reconstruction are mastectomy skin flap necrosis (MSFN) and autologous flap failure. This review summarizes current evidence regarding the usage of indocyanine green angiography (ICGA) in breast reconstruction, identifies knowledge gaps, and provides directions for future studies. An umbrella review was conducted to identify related syntheses in Embase, Ovid Medline, Scopus, the Cochrane Central Register of Controlled Trials, the Cochrane Database of Systematic Reviews, and the Clinical Trials databases. Data were extracted from systematic reviews (SRs) and meta-analyses (MAs) that discussed the use of ICGA in breast reconstruction. Sixteen syntheses were included (10 SRs and 6 MAs). Syntheses showed much evidence that ICGA usage typically reduces MSFN rates. However, it tends to overpredict necrosis and is best utilized in high-risk patients or those with an unclear clinical picture. ICGA is also useful in autologous breast reconstruction by reducing rates of breast fat necrosis (BFN), total flap loss, and reoperation. ICGA usage may also aid in perforator mapping and selection intraoperatively, with minimal complication risk. Most syntheses had moderate quality scores; however, they were small with significant heterogeneity in protocols and complication definitions. The use of ICGA in breast reconstruction is safe and useful in decreasing rates of MSFN, BFN, and reoperation after free flap reconstruction.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11505175/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142494061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Bioengineering
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1