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

A Bioadhesive Wireless Bioelectric Interface for Single-Dose Prevention of Acute Lung Injury via Piezoelectric Immunomodulation.

Nano letters·2026
Same author

Temporal response characteristics and interplay of energy metabolism-related hormones during fasting in piglets.

Veterinary journal (London, England : 1997)·2026
Same author

MDFAT: Interactive mask decoupling and frequency-adaptive transformer for multi-focus image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

SynReEM: Synapse Reconstruction via Instance Structure Encoding in Anisotropic Electron Microscopic Volumes.

IEEE transactions on medical imaging·2026
Same author

Liver sinusoidal endothelial cell fenestrations in metabolic liver disease: from molecular mechanisms to therapeutic perspectives.

Cell communication and signaling : CCS·2026
Same author

Angiogenesis and Ischemic Stroke.

Current neurovascular research·2026

相关实验视频

Updated: Jun 24, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.7K

深度多切割:深度学习多切割问题从电子显微镜中对神经元进行细分.

Zhenchen Li, Xu Yang, Jiazheng Liu

    IEEE transactions on pattern analysis and machine intelligence
    |June 4, 2024
    PubMed
    概括

    DeepMulticut集成了电子显微镜 (EM) 卷的神经元细分阶段. 这种深度学习框架通过直接优化最小成本的多切割问题来增强超像素聚合,提高细分精度.

    更多相关视频

    A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
    12:49

    A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

    Published on: September 28, 2019

    12.8K
    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

    相关实验视频

    Last Updated: Jun 24, 2025

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    8.7K
    A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
    12:49

    A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

    Published on: September 28, 2019

    12.8K
    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

    科学领域:

    • 神经科学是一个神经科学.
    • 计算机科学 计算机科学
    • 机器学习 机器学习

    背景情况:

    • 超像素聚合对于电子显微镜 (EM) 卷中自动化神经元细分至关重要.
    • 现有的图形分区方法涉及单独的模型估计和解决阶段,导致固有的模型错误.

    研究的目的:

    • 提出一个端到端的深度学习框架,DeepMulticut,用于神经元细分.
    • 整合模型估计和解决阶段,以克服现有方法的局限性.

    主要方法:

    • 开发了DeepMulticut,这是一个深度学习框架,用于最小成本的多切割问题.
    • 将NP-hard的多切割问题放松为连续的Soft-GAEC算法以实现可微分性.
    • 集成边缘-CNNs作为边缘成本估计器在一个可差分的多切割优化系统.
    • 在Edge-CNNs中利用面向决策的损失来进行自适应性歧视性特征学习.

    主要成果:

    • 在三个公共EM数据集上证明了DeepMulticut框架的有效性.
    • 通过将决策质量传送回边缘-CNN,展示了自适应的歧视性特征学习.
    • 通过直接优化分区决策,实现了改进的神经元细分.

    结论:

    • DeepMulticut提供了一个有效的端到端解决方案,用于EM卷中神经元细分.
    • 该框架成功地将深度学习与用于增强细分的组合优化相结合.
    • 该方法解决了传统的两阶段方法中固有的模型错误.