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

Deep learning-based Desikan-Killiany parcellation of the brain using diffusion MRI.

Scientific reports·2026
Same author

Anatomical effects of ablation of the anterior retina in small animal eyes.

BMC ophthalmology·2026
Same author

Alport Syndrome is a Partial Tubulointerstitial Disease of the Kidney.

Kidney international reports·2026
Same author

Evaluating Cross-Subject and Cross-Device Consistency in Visual Fixation Prediction.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Spatial transcriptomics expression prediction from histopathology based on cross-modal mask reconstruction and contrastive learning.

Medical image analysis·2025
Same author

Continual learning in medical image analysis: A comprehensive review of recent advancements and future prospects.

Medical image analysis·2025

相关实验视频

Updated: Jul 8, 2025

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

1.8K

一个基于深度学习的in silico框架,用于优化视网膜假肢刺激.

Yuli Wu, Ivan Karetic, Johannes Stegmaier

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 12, 2023
    PubMed
    概括

    我们开发了一个神经网络框架,以改善视网膜植入物模拟视觉. 我们的方法提高了图像感知质量,优于传统方法,以获得更好的视觉假肢.

    科学领域:

    • 生物医学工程 生物医学工程
    • 计算神经科学是一种神经科学.
    • 人工智能的人工智能

    背景情况:

    • 视网膜植入物旨在通过刺激剩余的视网膜神经元来恢复视力.
    • 准确模拟视觉感知对于设计有效的视网膜假体至关重要.
    • 像pulse2percept这样的现有模型提供生物仿真模拟,但缺乏针对特定电极配置的优化.

    研究的目的:

    • 开发基于神经网络的框架,以优化通过pulse2percept模型模拟的视觉感知.
    • 为了提高视网膜植入体用户生成的视觉刺激的质量.
    • 通过梯度下降实现端到端微调感知质量.

    主要方法:

    • 一个U-Net卷积神经网络作为可训练的编码器,将原始图像转换为刺激.
    • 一个预先训练好的U-Net模仿了脉冲2感知生物仿真模型.
    • 一个VGG分类器使用原始图像评估了感知质量.
    • 该框架在10,000个MNIST数据集图像上进行了测试,电极配置为6x10.

    主要成果:

    • 神经网络编码器显著超过了微不足道的下方采样方法.
    • 在预训练的分类器中,加权F1-Score的提升达到了36.17%.

    更多相关视频

    Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro
    12:56

    Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro

    Published on: December 19, 2017

    7.8K
    Directed Induction of Retinal Organoids from Human Pluripotent Stem Cells
    06:38

    Directed Induction of Retinal Organoids from Human Pluripotent Stem Cells

    Published on: April 21, 2021

    2.9K

    相关实验视频

    Last Updated: Jul 8, 2025

    Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
    10:50

    Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

    Published on: June 21, 2022

    1.8K
    Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro
    12:56

    Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro

    Published on: December 19, 2017

    7.8K
    Directed Induction of Retinal Organoids from Human Pluripotent Stem Cells
    06:38

    Directed Induction of Retinal Organoids from Human Pluripotent Stem Cells

    Published on: April 21, 2021

    2.9K
  • 该框架展示了模拟视觉感知的有效优化.

    • 结论:

    • 一个完全基于神经网络的编码器可以显著改善视网膜植入物的模拟视觉感知.
    • 使用梯度下降的端到端优化允许微调感知质量.
    • 这一框架为开发更有效的视觉假肢提供了一个有希望的方法.