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

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

PrP<sup>C</sup> modulates BACE1-dependent amyloid pathology under chronic cerebral hypoperfusion: Implications for vascular cognitive impairment.

Neurotherapeutics : the journal of the American Society for Experimental NeuroTherapeutics·2026

Same author

TDLAS-Based Antimicrobial Susceptibility Testing Using Microbial CO2 Evolution and Validation in Gram-Positive and Gram-Negative Bacteria.

Journal of applied microbiology·2026

Same author

Microbial DNA analysis of paired blood-bronchoalveolar lavage fluid in post-HSCT patients with pneumonia implying application conditions of blood as a surrogate in pathogen detection.

Respiratory research·2026

Same author

The Sunlight-7 Framework: an optics-inspired approach to accelerating Sustainable Development Goals.

Science bulletin·2026

Same author

Exercise as a multiscale recalibration of stress-related homeostatic balance.

Frontiers in neuroscience·2026

Same author

Tetrandrine-based in situ vaccination via multifunctional Mn²⁺-hyaluronic acid hydrogel loading gelatinase-responsive nanoparticles.

Journal of nanobiotechnology·2026

Search research articles

相关实验视频

Updated: Sep 12, 2025

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

亚特拉斯:一个具有解剖学意识的自我监督的学习框架,用于可泛化的视网膜疾病检测.

Abdullah Aman Khan, Khwaja Mutahir Ahmad, Sidra Shafiq

IEEE journal of biomedical and health informatics

|August 6, 2025

概括

此摘要是机器生成的。

这项研究引入了用于视网膜成像的解剖意识自主监督学习 (SSL) 框架. 它通过结合视网膜解剖学来改进深度学习诊断,克服眼部疾病检测稀缺注释数据的局限性.

更多相关视频

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

相关实验视频

Last Updated: Sep 12, 2025

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

科学领域:

眼科和医学成像学
医疗保健中的人工智能
计算生物学计算生物学

背景情况:

医学成像,特别是视网膜底部摄影,对于早期发现眼部疾病至关重要.
由于缺乏专家注释的视网膜数据,深度学习诊断受到阻碍,这是昂贵和耗时的.
目前的自我监督学习 (SSL) 模型缺乏关键的视网膜解剖知识的整合,限制了临床相关性.

研究的目的:

开发一个解剖意识的SSL框架用于视网膜成像.
通过整合领域知识来解决医疗AI中有限的标记数据的挑战.
增强视网膜疾病深度学习模型的临床相关性和诊断能力.

主要方法:

在预训练期间引入了一种新的SSL框架,利用视网膜结构 (血管,光盘) 的专业掩护.
使用容器和光盘细分图来指导SSL过程.
结合了视觉变压器与双掩盖策略和解剖学知情损失函数.

主要成果:

具有解剖学意识的SSL框架在分类各种视网膜疾病方面表现出了竞争力.
在不需要广泛的标记数据的情况下,成功开发了临床相关的特征表示.
在多个数据集中验证的有效性用于糖尿病视网膜病变,玻璃眼和与年龄相关的黄斑变性检测.

结论:

具有解剖学意识的SSL有效地推进了视网膜疾病的自动诊断.
拟议的框架克服了眼科中有限的标记医疗数据的关键挑战.
这种方法增强了深度学习对眼部疾病检测和治疗规划的有用性.