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

Cross Domain Self-Prompting SAM2 for Intraoperative OCT Video Segmentation.

IEEE journal of biomedical and health informatics·2026

Same author

Establishment and validation of a predictive scoring system for titanium clip retention at six months after endoscopic submucosal dissection for gastric lesions.

Scientific reports·2026

Same author

Streamlining stereo-differentiable rendering for marker-free real-time tracking of surgical robots.

International journal of computer assisted radiology and surgery·2026

Same author

SARS-CoV-2 infection and vaccination elicit distinct pharyngeal mucosal B cell responses in children.

Nature communications·2026

Same author

Bio-inspired cellular aerogel fibers integrating high mechanical strength and softness for thermal insulation textiles.

Nature communications·2026

Same author

ROBUST-MIPS: A Combined Skeletal Pose and Instance Segmentation Dataset for Laparoscopic Surgical Instruments.

Scientific data·2026

Search research articles

相关实验视频

Updated: Jan 18, 2026

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

RetiGen:利用多视图视网膜诊断领域概括和测试时间适应的框架.

Gongyu Zhang¹, Ze Chen², Jiayu Huo³

¹School of Biomedical Engineering & Imaging Sciences, King's College London, London, United Kingdom; School of Life Course & Population Sciences, King's College London, London, United Kingdom.

Computers in biology and medicine

|September 11, 2025

概括

RetiGen集成了眼科成像的域概括和测试时间适应,显著提高了不同数据集的诊断准确性. 这种新的方法提高了机器学习模型的稳定性,并解决了领域转移的挑战.

关键词:

深度学习是一种深度学习.域名通用化域名通用化医疗图像分析医学图像分析多视图成像多视图成像视网膜诊断视网膜诊断视网膜诊断测试时间调整.

更多相关视频

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

相关实验视频

Last Updated: Jan 18, 2026

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

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

科学领域:

眼科成像眼科成像
医疗机器学习医疗机器学习
计算机视觉计算机视觉计算机视觉

背景情况:

域泛化 (DG) 和测试时间适应 (TTA) 提高了跨不同域的医学成像模型准确性.
现有的方法往往单独针对GD或TTA,而不是利用它们的综合优势.
域名转移仍然是一个重大挑战,阻碍了AI在诊断方面的表现.

研究的目的:

引入RetiGen,一个新的测试时间优化框架,将DG和TTA整合到一个端到端的方式.
提高眼科成像领域机器学习模型的稳定性和准确性,特别是使用多视图彩色 fundus 照片.
为解决医疗成像分析领域转移的持续问题.

主要方法:

RetiGen是一个测试时间优化框架,旨在与现有的域泛化方法集成.
它使用未标记的多视图彩色基底照片,利用来自多个视角的信息.
该框架整合了类平衡,测试时间适应和多视图优化策略,以应对领域转移.

主要成果:

RetiGen显著提高了眼科成像模型的概括性和准确性.
在MFIDDR数据集中,RetiGen使AUC从0.751提高到0.872 (0.121改善).
在DRTiD数据集中,RetiGen将AUC从0.794提高到0.879 (0.085改善),超过了最先进的方法.

结论:

通过将DG和TTA结合在一个端到端的框架中,RetiGen有效地解决了域名转移问题.
拟议的方法表明,与现有的最先进的技术相比,在DG和TTA中表现优越.
RetiGen为改善眼科成像和其他医疗领域的诊断准确性提供了一个有希望的解决方案.