Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Phylogenetic analysis and machine learning identify signatures of selection and predict deleterious mutations in common bean (Phaseolus vulgaris L.).

BMC biology·2026

Same author

Macroporous Resin-Based Adsorption Separation of Ginsenosides From American Ginseng Fibrous Roots: Process Optimization and Mechanistic Insights.

Journal of separation science·2026

Same author

Simulations of genomic selection implementation pathways in common bean (Phaseolus vulgaris L.) using parametric and nonparametric models.

The plant genome·2025

Same author

Environment ensemble models for genomic prediction in common bean (Phaseolus vulgaris L.).

The plant genome·2025

Same author

Genetic architecture of ideotype-related traits in middle American beans through single trait, multi-trait and epistatic genome-wide analyses.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2025

Same author

Probing Biological Nitrogen Fixation in Legumes Using Raman Spectroscopy.

Sensors (Basel, Switzerland)·2024

Search research articles

相关实验视频

Updated: Jul 20, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Eff-3DPSeg:使用注释效率高的深度学习进行3D器官级植物射击细分.

Liyi Luo¹, Xintong Jiang¹, Yu Yang^1,2

¹Bioresource Engineering Department, McGill University, Montreal, QC, Canada.

Plant phenomics (Washington, D.C.)

|August 4, 2023

概括

此摘要是机器生成的。

本研究介绍了Eff-3DPSeg,这是一种弱监督的深度学习方法,用于3D植物发芽细分. 它显著减少了注释工作,同时在提取植物特征方面实现了高精度,有助于植物育种.

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Jul 20, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

科学领域:

计算机视觉计算机视觉
植物科学植物科学
机器学习机器学习

背景情况:

精确的3D植物芽细分对于提取器官水平的表型特征至关重要.
完全监督的深度学习需要大量的,耗时的点对点注释.
开发高效的注释策略对于推进植物表型化至关重要.

研究的目的:

提出一种新的弱监督框架,Eff-3DPSeg,用于自动化3D植物生长细分.
为了减少植物器官细分的深度学习模型中的注释负担.
为了能够准确地提取植物表型特征,以改善植物育种.

主要方法:

使用低成本的摄像度重建了大豆的高分辨率3D点云.
开发了一个基于Meshlab的植物注释器,用于高效的点云注释.
实施了一种弱监督的深度学习方法,涉及自我监督的预训和最小的微调 (0.5%注释积分).

主要成果:

对于大豆茎叶细分,Eff-3DPSeg实现了高精度 (95.1%),回忆 (96.6%),F1得分 (95.8%) 和mIoU (92.2%).
证明了与完全监督的方法可比的性能,注释工作显著减少.
成功提取了关键的表型特征,包括茎直径,叶子宽度和叶子长度.

结论:

低监督的深度学习为3D植物芽分割提供了有效的解决方案,最大限度地降低了注释成本.
该Eff-3DPSeg框架提供了一个可扩展的方法来表征3D工厂架构.
这种方法有可能通过详细的表型定型来提高选择过程,从而加速植物育种.