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

Photoreceptors and Visual Pathways01:22

Photoreceptors and Visual Pathways

6.0K
At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...
6.0K

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

Predicting the prognosis of Wilms tumor by peripheral blood cells: a real-world study of more than 30 years.

Italian journal of pediatrics·2024
Same author

CT assessment of liver fat fraction and abdominal fat composition can predict postoperative liver metastasis of colorectal cancer.

European journal of radiology·2024
Same author

Model design and exponential state estimation for discrete-time delayed memristive spiking neural P systems.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

NDRG1 Regulates Iron Metabolism and Inhibits Pathologic Cardiac Hypertrophy.

The Canadian journal of cardiology·2024
Same author

Acinetobacter corruptisaponis sp. nov., Isolated from a Spoiled Bath Lotion.

Current microbiology·2024
Same author

Antisocial Behavior and Antisocial Personality Disorder Among Youth in Ethnic Minority Areas in China: A Cross-sectional Study.

Alpha psychiatry·2024

相关实验视频

Updated: Jun 27, 2025

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

325

在有限的资源下,集体学习以识别视网膜疾病.

Jiahao Wang1, Hong Peng1, Shengchao Chen2

  • 1School of Information and Communication Engineering, Hainan University, Haikou, 570228, China.

Medical & biological engineering & computing
|May 2, 2024
PubMed
概括

本研究引入了一种集体学习方法,用于使用有限的数据和计算资源识别视网膜疾病. 这种新的方法以更少的参数实现了高精度,超过了传统的深度学习模型.

关键词:
深度学习是一种深度学习.知识转移知识的转移.有限的资源 有限的资源视网膜疾病的识别识别

更多相关视频

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

2.7K
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: Jun 27, 2025

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

325
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

2.7K
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
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 视网膜光学连贯性断层扫描 (OCT) 成像对于诊断后眼段疾病至关重要.
  • 对OCT图像的自动化分析对于临床决策至关重要,但深度学习 (DL) 模型需要大量的数据和计算能力.
  • 数据采集挑战 (隐私,标签) 和资源限制阻碍了医疗AI中的DL模型开发.

研究的目的:

  • 开发一种用于视网膜疾病识别的全新集体学习机制.
  • 为了应对医疗人工智能的有限数据和计算资源的挑战.
  • 为了提高DL模型的性能,用于视网膜OCT图像分析.

主要方法:

  • 提出了一种新的集体学习机制,利用预训练模型将知识传输到视网膜的OCT图像.
  • 与从头开始训练DL模型相比,开发了一种需要更少参数的方法.
  • 利用多个预训练模型来创建疾病识别的整体模型.

主要成果:

  • 拟议的组合方法在稀疏的标记数据上表现出比基线模型更好的性能.
  • 三重组合模型的准确率为92.06%,比基线模型的准确率高出8.27%至11.14%.
  • 与从头开始训练的基线模型相比,三元组合模型需要更少的可训练参数 (3.677M).

结论:

  • 这种新的集体学习机制有效地识别视网膜疾病,但数据和计算资源有限.
  • 这种方法为开发高性能医疗AI提供了强大的解决方案,特别是在资源有限的环境中.
  • 这些发现突出了集合学习的潜力,以克服医疗图像分析中的数据和计算局限性.