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

Functional system-specific brain aging across the Alzheimer's disease continuum.

Translational psychiatry·2026
Same author

Shared genetic architecture between the topology of brain white matter structural connectome and fluid intelligence.

Communications biology·2026
Same author

An ophthalmic video foundation model for surgical recognition and navigation with wet-lab porcine eye validation.

Nature biomedical engineering·2026
Same author

Comparative Performance Evaluation of Large Language Models and Human Teachers in Answering Optometry Questions from Medical Undergraduates.

Journal of medical education and curricular development·2026
Same author

Association of polymorphisms in 17 loci with primary open-angle glaucoma in Chinese and Japanese.

The British journal of ophthalmology·2025
Same author

Foundation Model With Uncertainty Estimation-Based Active Learning for Retinal Image Classification.

IEEE journal of biomedical and health informatics·2025

相关实验视频

Updated: Jul 12, 2025

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

2.8K

以不确定性为灵感的开放式学习,用于视网膜异常识别.

Meng Wang1, Tian Lin2, Lianyu Wang3,4

  • 1Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, #16-16 Connexis, Singapore, 138632, Republic of Singapore.

Nature communications
|October 24, 2023
PubMed
概括

这项研究引入了一个以不确定性为灵感的开放集 (UIOS) 模型,以改善用于检测视网膜异常的人工智能. UIOS模型准确地识别出未见的条件,并标记不确定的情况进行手动审查,增强现实世界的选.

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

405
Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

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

Published on: July 28, 2023

2.5K

相关实验视频

Last Updated: Jul 12, 2025

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

2.8K
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

405
Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
06:16

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

Published on: July 28, 2023

2.5K

科学领域:

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

背景情况:

  • 人工智能 (AI) 模型难以识别新的或未见的视网膜疾病.
  • 对视网膜异常的准确分类对于早期诊断和治疗至关重要.
  • 当前的人工智能系统缺乏强大的机制来处理视网膜成像中的分布外样本.

研究的目的:

  • 开发一种以不确定性为灵感的开放集 (UIOS) 模型,以改进视网膜异常的识别和分类.
  • 通过解决看不见的课程的挑战,提高AI在现实世界的临床环境中的可靠性.
  • 为了在视网膜底图像的分类预测之外提供一种信心指标.

主要方法:

  • 开发了一个以不确定性为灵感的开放集 (UIOS) 模型,该模型在9种视网膜疾病的 fundus 图像上进行训练.
  • 结合了不确定性得分计算以及类别概率评估.
  • 实施了值策略,以评估模型在不同数据集上的表现.

主要成果:

  • 与标准AI模型 (92.20%, 80.69%, 64.74%) 相比,UIOS模型获得了显著更高的F1分数 (99.55%的内部,97.01%的外部TC,91.91%的隐形TC).
  • UIOS正确预测了非目标类别的高不确定性得分,包括视网膜疾病,低质量的图像和非基金图像.
  • 该模型在区分已知的和未知的视网膜疾病方面表现出强大.

结论:

  • UIOS模型提供了一个强大的解决方案,通过有效地处理看不见的类来对视网膜异常进行现实查.
  • 不确定性得分为识别需要手动专家审查的情况提供了有价值的工具,提高了诊断安全性.
  • 这种方法提高了人工智能在眼科中用于异常检测的实际适用性.