Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

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

The Influence of Hobby Engagement on Cognitive Function Among Older Adults: A Population-Based Cohort Study Using Statistical Analysis and Machine Learning Predictions.

Neurology international·2025
Same author

Adaptive digital platforms for youth tobacco cessation: a meta-analytic evaluation of web-based behaviour change interventions.

Health education research·2025
Same author

Implicitly Selected Transform for AVS3.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

Application and prospects of single cell sequencing in tumors.

Biomarker research·2021
Same author

Residual Spatial and Channel Attention Networks for Single Image Dehazing.

Sensors (Basel, Switzerland)·2021
Same author

Stenting techniques for coronary bifurcation disease: a systematic review and network meta-analysis demonstrates superiority of double-kissing crush in complex lesions.

Clinical research in cardiology : official journal of the German Cardiac Society·2021
Same journal

Paired longitudinal tear proteomics reveals persistent ocular surface dysregulation after teprotumumab therapy in thyroid eye disease.

Communications medicine·2026
Same journal

In vitro development of the Autonomous Colonoscope Robot System (ACRS) for fully automated colonoscope insertion.

Communications medicine·2026
Same journal

Dynamic contrast-enhanced ultrasound predicts microsphere biodistribution in real-time during transarterial radioembolization.

Communications medicine·2026
Same journal

Circulating monocyte gene expression profiles associated with cardiac remodeling and incident heart failure in the Multi-Ethnic Study of Atherosclerosis.

Communications medicine·2026
Same journal

Impact of methicillin resistance on mortality in Staphylococcus aureus endocarditis: a systematic review and meta-analysis.

Communications medicine·2026
Same journal

Clinical benefits of tirzepatide in patients with steatotic liver disease and cardiometabolic dysfunction.

Communications medicine·2026
查看所有相关文章

相关实验视频

Updated: Mar 14, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.6K

一种基于零射击学习的通用眼病检测方法.

Chengchang Pan1, Yudian Wang1, Yixuan Jiang1

  • 1School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China.

Communications medicine
|March 13, 2026
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种新的零射击学习 (ZSL) 框架,用于检测轻度糖尿病视网膜病变 (DR1),而无需标记数据. 该方法有效地模仿临床推理,在早期检测眼部疾病方面表现优于监督方法.

更多相关视频

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

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

Published on: April 11, 2025

1.0K
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

1.3K

相关实验视频

Last Updated: Mar 14, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.6K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

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

Published on: April 11, 2025

1.0K
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

1.3K

科学领域:

  • 眼科医生 眼科 眼科
  • 医学图像分析 医学图像分析
  • 人工智能的人工智能

背景情况:

  • 医学成像中的深度学习受到大型,专家注释的数据集的需求的阻碍,特别是在眼科中,用于早期检测疾病,如轻度糖尿病视网膜病变 (DR1).
  • 对微妙的DR1病变进行注释的稀缺性限制了传统监督学习方法的有效性.

研究的目的:

  • 利用模拟临床推理的零射击学习 (ZSL) 开发一种可泛化的眼睛疾病检测框架.
  • 为了实现无人监督的DR1检测,而不需要任何标记的DR1病例.

主要方法:

  • 利用了LCFP-14M数据集,这是一个新的大规模 fundus 图像资源.
  • 采用语网络来识别疾病相关性,并通过从相关源疾病中对DR1特异性病变进行细分来转移知识.
  • 实施了一个ResNet-Agglomerative集群管道,用于无监督的DR1检测.

主要成果:

  • 拟议的ZSL框架实现了有效的DR1检测,没有注释DR1数据.
  • 性能指标包括准确性 (0.8337),精度 (0.8700),回忆 (0.7456),F1得分 (0.8030) 和ROC-AUC (0.9226).
  • 该框架在外部测试数据集上表现优于大多数监督基线.

结论:

  • 零射击学习 (ZSL) 可以有效模拟眼睛疾病的临床诊断逻辑.
  • 该方法展示了用于检测看不见的眼睛疾病的概括能力.
  • 这为在具有有限标记数据的场景中进行自动选提供了有希望的途径.