Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Diabetic Retinopathy

Diabetic Retinopathy

DefinitionDiabetic retinopathy is a microvascular complication of diabetes affecting the retinal blood vessels.Risk FactorsDiabetic retinopathy is present in almost all individuals with type 1 diabetes and more than 60% of those with type 2 diabetes after two decades of disease.The risk increases with poor glycemic control, hypertension, dyslipidemia, smoking, pregnancy, and puberty.Although cataracts and glaucoma are also more frequent in people with diabetes, retinopathy remains the leading...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds.

IEEE transactions on visualization and computer graphics·2026

Same author

Single-base 2'OMe-modified LNA and MOE gapmers selectively silence <i>ACVR1</i> <sup><i>R206H</i></sup> in fibrodysplasia ossificans progressiva.

Molecular therapy. Nucleic acids·2026

Same author

Lipid nanoparticle delivery of antisense gapmers attenuates pathology in a mouse model of facioscapulohumeral muscular dystrophy.

Molecular therapy : the journal of the American Society of Gene Therapy·2026

Same author

Metacognitive Beliefs and Symptom Dimensions in OCD: A Network Analysis Identifying Central Nodes and a Severity Predictor.

Clinical psychology & psychotherapy·2026

Same author

Gabapentsal ameliorate cisplatin-induced vomiting in pigeons: neurochemical evidences and the involvement of serotonin and dopamine modulation.

Scientific reports·2026

Same author

Systematic literature review on the real-world effectiveness and safety of bempedoic acid.

Atherosclerosis plus·2026

Search research articles

相关实验视频

Updated: Jul 18, 2026

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

多尺度自主监督学习,以深入知识转移在糖尿病视网膜病变分级的糖尿病视网膜病变.

Wadha Almattar^1,2, Saeed Anwar^3,4, Sadam Al-Azani⁴

¹Information and Computer Science Department, King Fahd University of Petroleum and Minerals, Dhahran, 31261, Saudi Arabia. wmalmattar@iau.edu.sa.

Scientific reports

|October 1, 2025

概括

糖尿病视网膜病变的检测得到了改进,使用了一种新的多规模自主监督学习 (MsSSL) 模型. 这种先进的方法集成了视觉转换器和CNN,用于更优质的视网膜图像分析和分级.

关键词:

这就是为什么CBAM是CBAM.糖尿病视网膜病变分级的分级功能金字塔网络的特点是:自主监督学习学习视觉变压器视觉变压器

更多相关视频

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

相关实验视频

Last Updated: Jul 18, 2026

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

科学领域:

眼科医生眼科眼科
医疗成像医学成像
人工智能的人工智能

背景情况:

糖尿病视网膜病变 (DR) 是视力丧失的主要原因,需要及时和精确的检测.
自动化的深度学习模型面临复杂的视网膜图像和不足的标记数据的挑战.
传统的转移学习方法在医学成像中往往表现不佳,原因是域差异.

研究的目的:

开发一个先进的深度学习模型,以改善糖尿病视网膜病变的分级.
克服现有模型在处理医疗图像复杂性和数据稀缺性方面的局限性.
为了利用混合架构的自我监督学习来增强功能提取.

主要方法:

提出了一个多尺度自主监督学习 (MsSSL) 模型,将视觉转换器 (ViTs) 集成为全球背景和卷积神经网络 (CNNs) 与特征金字塔网络 (FPN) 集成为多尺度特征.
采用深度学习模块来完善提取的特征,增强空间分辨率并捕获高级和细粒度的细节.
利用特定领域的预训练来适应模型的医学成像数据.

主要成果:

MsSSL模型在糖尿病视网膜病变分级准确度方面显著改善.
性能超过了传统的深度学习和转移学习方法.
该研究强调了将全球和多尺度特征提取相结合用于医学图像分析的有效性.

结论:

MsSSL模型为糖尿病视网膜病变的自动检测和分级提供了一个有希望的进步.
将ViTs和CNNs与FPN集成,为医学图像分析提供了一个强大的框架.
特定领域的预训练和先进的模型架构对于医疗AI的成功至关重要.