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

The Retina01:32

The Retina

69.2K
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.
69.2K

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

DDMPI: Diffusion Denoising for Magnetic Particle Imaging at the Low Concentration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Intelligent detection method for carotid atherosclerotic plaques based on ultrasound imaging.

Brain circulation·2026
Same author

DFMFI: ultrasound breast cancer detection method based on dynamic fusion multi-scale feature interaction model.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same author

Pan-genomic insights into LTP gene family evolution across diploid cotton species.

Frontiers in plant science·2026
Same author

Intermittent Glucocorticoid Pulse Combined With Mycophenolate Mofetil in Juvenile Dermatomyositis.

JAMA dermatology·2025
Same author

ESAM2-BLS: Enhanced segment anything model 2 for efficient breast lesion segmentation in ultrasound imaging.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025

相关实验视频

Updated: Jul 18, 2025

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K

CLRD:使用眼底图像检测视网膜病变的协作学习.

Yuan Gao1, Chenbin Ma1,2, Lishuang Guo1

  • 1Department of Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing 100191, China.

Bioengineering (Basel, Switzerland)
|August 26, 2023
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种协作学习框架,用于使用 fundus 图像检测视网膜病变. 通过结合多种AI模型,CLRD方法提高了诊断准确性,改善了早期疾病识别.

关键词:
协作学习是一种协作式的学习.深度学习是一种深度学习.图片来源: 基金图像基金在线蒸在线蒸视网膜病变检测检测器

更多相关视频

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.6K
Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

11.5K

相关实验视频

Last Updated: Jul 18, 2025

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K
Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.6K
Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

11.5K

科学领域:

  • 眼科医生 眼科 眼科
  • 人工智能的人工智能
  • 医疗成像医学成像

背景情况:

  • 视网膜病变是导致视力丧失的主要原因,需要通过 fundus成像进行早期检测.
  • 有限的基金图像可用性和不平衡的数据集阻碍了开发有效的诊断算法.
  • 先进的算法对于提高视网膜病变诊断的精度和效率至关重要.

研究的目的:

  • 提出一个新的在线知识蒸框架 (CLRD),用于增强视网膜病变的检测.
  • 通过解决有限数据和 fundus成像中的不平衡数据集的挑战来提高诊断性能.
  • 开发一种协作式的学习方法,将多种AI模型结合起来,以进行可靠的视网膜病变识别.

主要方法:

  • 开发了一个协作在线知识蒸 (CLRD) 框架,用于检测视网膜病变.
  • 综合学生模型具有各种规模和架构,包括基于变压器的BEiT和基于CNN的ConvNeXt.
  • 实施了 fundus 图像特异性扭曲信息传输以增强模型不变性.

主要成果:

  • 通过CLRD框架实现了高诊断准确度:BEiT (98.77%) 和ConvNeXt (96.88%).
  • 与先进的视觉模型相比,CLRD显示出显著的改进,具有更高的准确性,精度,回忆,特异性和F1分数.
  • 该框架有效地减少了概括错误,同时保留了学生个人的模型预测.

结论:

  • 该CLRD框架提供了一个有前途的方法,用于使用 fundus图像准确和有效地检测视网膜病变.
  • 协作学习和知识蒸可以克服医疗图像分析中的数据限制.
  • 这项研究为进一步研究AI驱动的视力障碍诊断工具提供了基础.