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

The Retina

The Retina

The retina is a layer of nervous tissue at the back of the eye that transduces light into neural signals. This process, called phototransduction, is carried out by rod and cone photoreceptor cells in the back of the retina.

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

PD-ViCo: an explainable AI-based contrastive captioner vision transformer with patch dropout for multi-class brinjal disease classification.

BMC plant biology·2026

Same author

Comprehensive computer analysis of an intratumoral viable biological agent as a systemic multi-mechanistic therapeutic strategy for pancreatic cancer treatment.

In silico pharmacology·2026

Same author

Digital Darkness in Cardiovascular Care: Ransomware, System Outages, and the Emerging Threat to Cardiac Patient Safety.

Journal of patient safety·2026

Same author

Decoding the hydrogen storage and functional properties of MgBH<sub>3</sub> (B = Mo and In) <i>via</i> first-principles simulations.

RSC advances·2026

Same author

BPBiLSTM-IDS: a lightweight intrusion detection framework for cyber-physical UAV networks.

Scientific reports·2026

Same author

Implementation Effect of a Pilot Urban Primary Health Care Model on the Usage of Health Care From Medically Trained Providers for Chronic Diseases Among Slum Populations in Bangladesh: Findings From an Implementation Research Study.

JMIR public health and surveillance·2026

Search research articles

相关实验视频

Updated: May 29, 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

一个低复杂度高效的深度学习模型用于自动视网膜疾病诊断.

Sadia Sultana Chowa¹, Md Rahad Islam Bhuiyan¹, Israt Jahan Payel¹

¹Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka-1341, Bangladesh.

Journal of healthcare informatics research

|February 3, 2025

概括

使用光学连贯断层扫描 (OCT) 早期检测视网膜疾病对于预防视力丧失至关重要. 一个新的深度学习模型,OCCT,在从OCT图像中分类视网膜疾病时,达到97.09%的准确性,优于其他先进模型.

关键词:

废除研究是废除的研究.紧型卷积变压器 (CCT) 的使用生成对抗网络 (GAN) 是一种产生对抗网络.光学连贯性断层扫描 (OCT)视网膜疾病视网膜疾病变压器模型模型

更多相关视频

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

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling

Published on: December 22, 2023

相关实验视频

Last Updated: May 29, 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

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

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling

Author Spotlight: Simple and Efficient Neural Retina Organoid Production for Disease Modeling

Published on: December 22, 2023

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:

早期发现和治疗视网膜疾病对于保持视力至关重要.
光学连贯断层扫描 (OCT) 是用于诊断眼睛疾病的关键成像技术.
深度学习为自动分析海外国家和地区图像提供了潜力.

研究的目的:

开发和评估一个深度学习模型,将人类视网膜OCT图像分为四类.
通过预处理和生成对抗网络 (GAN) 提高图像质量并解决数据不平衡.
将拟议模型的性能与已建立的基于变压器的架构进行比较.

主要方法:

人类视网膜OCT图像使用GANs进行了预处理和增强,最终得到了130,649张图像.
开发了一种新的轻量级优化紧卷积变压器 (OCCT) 模型.
在32x32图像上训练和评估OCCT模型,以及视觉转换器 (ViT),Swin转换器和八个转移学习模型.

主要成果:

在分类视网膜疾病方面,OCCT模型实现了97.09%的高精度.
与ViT和Swin变压器模型相比,OCCT表现出卓越的性能.
模型的稳定性得到证实,即使训练数据减少,性能也保持不变.

结论:

拟议的OCCT模型是有效的准确和可靠的分类视网膜疾病从OCT图像.
这种深度学习方法有望改善早期诊断和治疗危及视力的疾病.
OCCT模型为自动视网膜图像分析提供了强大而高效的解决方案.