• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于机器学习的计算机视觉植物表型分析：人工智能/机器学习概论及气孔模式案例研究。

Machine learning-enabled computer vision for plant phenotyping: a primer on AI/ML and a case study on stomatal patterning.

机构信息

Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA.

Program in Ecology, Evolution, and Conservation, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA.

出版信息

J Exp Bot. 2024 Nov 15;75(21):6683-6703. doi: 10.1093/jxb/erae395.

DOI:10.1093/jxb/erae395
PMID:39363775
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11565210/
Abstract

Artificial intelligence and machine learning (AI/ML) can be used to automatically analyze large image datasets. One valuable application of this approach is estimation of plant trait data contained within images. Here we review 39 papers that describe the development and/or application of such models for estimation of stomatal traits from epidermal micrographs. In doing so, we hope to provide plant biologists with a foundational understanding of AI/ML and summarize the current capabilities and limitations of published tools. While most models show human-level performance for stomatal density (SD) quantification at superhuman speed, they are often likely to be limited in how broadly they can be applied across phenotypic diversity associated with genetic, environmental, or developmental variation. Other models can make predictions across greater phenotypic diversity and/or additional stomatal/epidermal traits, but require significantly greater time investment to generate ground-truth data. We discuss the challenges and opportunities presented by AI/ML-enabled computer vision analysis, and make recommendations for future work to advance accelerated stomatal phenotyping.

摘要

人工智能和机器学习 (AI/ML) 可用于自动分析大型图像数据集。这种方法的一个有价值的应用是估计图像中包含的植物性状数据。在这里，我们回顾了 39 篇描述此类模型的开发和/或应用的论文，这些模型用于从表皮显微照片估计气孔性状。通过这样做，我们希望为植物生物学家提供对 AI/ML 的基本理解，并总结已发表工具的当前功能和局限性。虽然大多数模型在超人类速度下对气孔密度 (SD) 的量化表现出人类水平的性能，但它们通常可能受到限制，无法广泛应用于与遗传、环境或发育变化相关的表型多样性。其他模型可以在更大的表型多样性和/或其他气孔/表皮性状上进行预测，但需要投入大量时间来生成真实数据。我们讨论了由 AI/ML 支持的计算机视觉分析带来的挑战和机遇，并为推进加速气孔表型分析提出了未来工作的建议。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/5c3791e97b55/erae395_fig7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/97e2cb7226f2/erae395_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/b638fd8e7e75/erae395_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/cc7ed319038f/erae395_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/27071aea5dde/erae395_fig4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/6a0681916367/erae395_fig5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/452e0b956c6f/erae395_fig6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/5c3791e97b55/erae395_fig7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/97e2cb7226f2/erae395_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/b638fd8e7e75/erae395_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/cc7ed319038f/erae395_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/27071aea5dde/erae395_fig4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/6a0681916367/erae395_fig5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/452e0b956c6f/erae395_fig6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9412/11565210/5c3791e97b55/erae395_fig7.jpg

相似文献

1
Machine learning-enabled computer vision for plant phenotyping: a primer on AI/ML and a case study on stomatal patterning.基于机器学习的计算机视觉植物表型分析：人工智能/机器学习概论及气孔模式案例研究。
J Exp Bot. 2024 Nov 15;75(21):6683-6703. doi: 10.1093/jxb/erae395.
2
Optical topometry and machine learning to rapidly phenotype stomatal patterning traits for maize QTL mapping.光学拓扑测量学和机器学习在玉米数量性状定位中快速表型化气孔模式特征。
Plant Physiol. 2021 Nov 3;187(3):1462-1480. doi: 10.1093/plphys/kiab299.
3
Classical phenotyping and deep learning concur on genetic control of stomatal density and area in sorghum.经典表型分析和深度学习在高粱气孔密度和面积的遗传控制方面达成一致。
Plant Physiol. 2021 Jul 6;186(3):1562-1579. doi: 10.1093/plphys/kiab174.
4
Review: Application of Artificial Intelligence in Phenomics.综述：人工智能在表型组学中的应用。
Sensors (Basel). 2021 Jun 25;21(13):4363. doi: 10.3390/s21134363.
5
Application of deep learning for the analysis of stomata: a review of current methods and future directions.深度学习在气孔分析中的应用：当前方法与未来方向综述。
J Exp Bot. 2024 Nov 15;75(21):6704-6718. doi: 10.1093/jxb/erae207.
6
StomaAI: an efficient and user-friendly tool for measurement of stomatal pores and density using deep computer vision.StomaAI：一种利用深度学习计算机视觉进行气孔和密度测量的高效、用户友好的工具。
New Phytol. 2023 Apr;238(2):904-915. doi: 10.1111/nph.18765. Epub 2023 Feb 18.
7
Deep Transfer Learning-Based Multi-Object Detection for Plant Stomata Phenotypic Traits Intelligent Recognition.基于深度迁移学习的植物气孔表型特征智能识别的多目标检测
IEEE/ACM Trans Comput Biol Bioinform. 2023 Jan-Feb;20(1):321-329. doi: 10.1109/TCBB.2021.3137810. Epub 2023 Feb 3.
8
Revolutionizing Digital Pathology With the Power of Generative Artificial Intelligence and Foundation Models.利用生成式人工智能和基础模型推动数字病理学革命。
Lab Invest. 2023 Nov;103(11):100255. doi: 10.1016/j.labinv.2023.100255. Epub 2023 Sep 26.
9
Computer vision and machine learning for robust phenotyping in genome-wide studies.计算机视觉和机器学习在全基因组研究中的稳健表型分析。
Sci Rep. 2017 Mar 8;7:44048. doi: 10.1038/srep44048.
10
SLPA-Net: A Real-Time Recognition Network for Intelligent Stomata Localization and Phenotypic Analysis.SLPA-Net：一种用于智能气孔定位和表型分析的实时识别网络。
IEEE/ACM Trans Comput Biol Bioinform. 2024 May-Jun;21(3):372-382. doi: 10.1109/TCBB.2024.3364208. Epub 2024 Jun 5.

引用本文的文献

1
Shining light on photosynthesis.揭示光合作用
J Exp Bot. 2025 Aug 21;76(12):3243-3246. doi: 10.1093/jxb/eraf096.
2
Plant Microbe Interaction-Predicting the Pathogen Internalization Through Stomata Using Computational Neural Network Modeling.植物-微生物相互作用——利用计算神经网络模型预测病原体通过气孔的内化
Foods. 2024 Nov 28;13(23):3848. doi: 10.3390/foods13233848.
3
Stomata: custodians of leaf gaseous exchange.气孔：叶片气体交换的守护者。

本文引用的文献

1
Reducing stomatal density by expression of a synthetic epidermal patterning factor increases leaf intrinsic water use efficiency and reduces plant water use in a C4 crop.通过表达合成的表皮图案形成因子降低气孔密度，可提高 C4 作物叶片内在水分利用效率并减少植物耗水量。
J Exp Bot. 2024 Nov 15;75(21):6823-6836. doi: 10.1093/jxb/erae289.
2
Greater aperture counteracts effects of reduced stomatal density on water use efficiency: a case study on sugarcane and meta-analysis.大孔径抵消了减少气孔密度对水分利用效率的影响：以甘蔗为例的案例研究和荟萃分析。
J Exp Bot. 2024 Nov 15;75(21):6837-6849. doi: 10.1093/jxb/erae271.
3
Segment anything in medical images.
J Exp Bot. 2024 Nov 15;75(21):6677-6682. doi: 10.1093/jxb/erae425.
在医学图像中分割任何内容。
Nat Commun. 2024 Jan 22;15(1):654. doi: 10.1038/s41467-024-44824-z.
4
Scientific discovery in the age of artificial intelligence.人工智能时代的科学发现。
Nature. 2023 Aug;620(7972):47-60. doi: 10.1038/s41586-023-06221-2. Epub 2023 Aug 2.
5
StomaAI: an efficient and user-friendly tool for measurement of stomatal pores and density using deep computer vision.StomaAI：一种利用深度学习计算机视觉进行气孔和密度测量的高效、用户友好的工具。
New Phytol. 2023 Apr;238(2):904-915. doi: 10.1111/nph.18765. Epub 2023 Feb 18.
6
Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics.保卫细胞的自动化三维分割可实现气孔生物力学的体积分析。
Patterns (N Y). 2022 Nov 9;3(12):100627. doi: 10.1016/j.patter.2022.100627. eCollection 2022 Dec 9.
7
LeafNet: a tool for segmenting and quantifying stomata and pavement cells.叶网：一种用于分割和量化气孔和铺石细胞的工具。
Plant Cell. 2022 Mar 29;34(4):1171-1188. doi: 10.1093/plcell/koac021.
8
Optimizing the Experimental Method for Stomata-Profiling Automation of Soybean Leaves Based on Deep Learning.基于深度学习优化大豆叶片气孔分析自动化的实验方法
Plants (Basel). 2021 Dec 10;10(12):2714. doi: 10.3390/plants10122714.
9
Deep Transfer Learning-Based Multi-Object Detection for Plant Stomata Phenotypic Traits Intelligent Recognition.基于深度迁移学习的植物气孔表型特征智能识别的多目标检测
IEEE/ACM Trans Comput Biol Bioinform. 2023 Jan-Feb;20(1):321-329. doi: 10.1109/TCBB.2021.3137810. Epub 2023 Feb 3.
10
A Deep Learning Method for Fully Automatic Stomatal Morphometry and Maximal Conductance Estimation.一种用于全自动气孔形态测量和最大导度估计的深度学习方法。
Front Plant Sci. 2021 Dec 2;12:780180. doi: 10.3389/fpls.2021.780180. eCollection 2021.