叶气孔行为分析的新维度:采用机器学习方法的稳健方法

IF 1.7 4区 生物学 Q4 BIOTECHNOLOGY & APPLIED MICROBIOLOGY
Ki-Bon Ku, Anh Tuan Le, Thanh Tuan Thai, Sheikh Mansoor, Piya Kittipadakul, Janejira Duangjit, Ho-Min Kang, San Su Min Oh, Ngo Hoang Phan, Yong Suk Chung
{"title":"叶气孔行为分析的新维度:采用机器学习方法的稳健方法","authors":"Ki-Bon Ku, Anh Tuan Le, Thanh Tuan Thai, Sheikh Mansoor, Piya Kittipadakul, Janejira Duangjit, Ho-Min Kang, San Su Min Oh, Ngo Hoang Phan, Yong Suk Chung","doi":"10.1007/s11816-024-00902-8","DOIUrl":null,"url":null,"abstract":"<p>Stomata are specialized pores that play a vital role in gas exchange and photosynthesis. Microscopic images are often used to assess stomatal characteristics in plants; however, this can be a challenging task. By utilizing Matterport’s Mask R-CNN implementation as the foundational model, fine-tuning was conducted on a dataset of 810 microscopic images of <i>Hedyotis corymbosa</i> leaves’ surfaces for automated stomatal pores detection. The outcomes were promising, with the model achieving a convergence of 98% mean average precision (mAP) for both detection and segmentation. The training loss and validation loss values converged around 0.18 and 0.37, respectively. Regression analyses demonstrated the statistical significance (<i>p</i> values ≤ 0.05) of predictor parameters. Notably, the tightest cluster of data points was observed in stomata pore area measurements, followed by width and length. This highlights the precision of the stomatal pore area in characterizing stomatal traits. Despite challenges posed by the original dataset’s low-resolution images and artifacts like dust, bubbles, and blurriness, our innovative utilization of the Mask R-CNN algorithm yielded commendable outcomes. This research introduces a robust approach for stomatal phenotyping with broad applications in plant biology and environmental studies.</p>","PeriodicalId":20216,"journal":{"name":"Plant Biotechnology Reports","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"New dimension in leaf stomatal behavior analysis: a robust method with machine learning approach\",\"authors\":\"Ki-Bon Ku, Anh Tuan Le, Thanh Tuan Thai, Sheikh Mansoor, Piya Kittipadakul, Janejira Duangjit, Ho-Min Kang, San Su Min Oh, Ngo Hoang Phan, Yong Suk Chung\",\"doi\":\"10.1007/s11816-024-00902-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Stomata are specialized pores that play a vital role in gas exchange and photosynthesis. Microscopic images are often used to assess stomatal characteristics in plants; however, this can be a challenging task. By utilizing Matterport’s Mask R-CNN implementation as the foundational model, fine-tuning was conducted on a dataset of 810 microscopic images of <i>Hedyotis corymbosa</i> leaves’ surfaces for automated stomatal pores detection. The outcomes were promising, with the model achieving a convergence of 98% mean average precision (mAP) for both detection and segmentation. The training loss and validation loss values converged around 0.18 and 0.37, respectively. Regression analyses demonstrated the statistical significance (<i>p</i> values ≤ 0.05) of predictor parameters. Notably, the tightest cluster of data points was observed in stomata pore area measurements, followed by width and length. This highlights the precision of the stomatal pore area in characterizing stomatal traits. Despite challenges posed by the original dataset’s low-resolution images and artifacts like dust, bubbles, and blurriness, our innovative utilization of the Mask R-CNN algorithm yielded commendable outcomes. This research introduces a robust approach for stomatal phenotyping with broad applications in plant biology and environmental studies.</p>\",\"PeriodicalId\":20216,\"journal\":{\"name\":\"Plant Biotechnology Reports\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-05-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Plant Biotechnology Reports\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s11816-024-00902-8\",\"RegionNum\":4,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Plant Biotechnology Reports","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s11816-024-00902-8","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

气孔是一种特殊的孔隙,在气体交换和光合作用中发挥着重要作用。显微图像通常用于评估植物气孔的特征,但这可能是一项具有挑战性的任务。通过使用 Matterport 的 Mask R-CNN 实现作为基础模型,对 810 张 Hedyotis corymbosa 叶子表面的显微图像数据集进行了微调,以实现气孔的自动检测。结果令人欣喜,该模型在检测和分割方面的收敛平均精度(mAP)达到了 98%。训练损失和验证损失值分别趋近于 0.18 和 0.37。回归分析表明,预测参数具有统计学意义(p 值小于 0.05)。值得注意的是,在气孔孔面积测量中观察到了最紧密的数据点群,其次是宽度和长度。这凸显了气孔面积在描述气孔特征方面的精确性。尽管原始数据集的低分辨率图像以及灰尘、气泡和模糊等人为因素带来了挑战,但我们创新性地使用了 Mask R-CNN 算法,取得了值得称赞的成果。这项研究为气孔表型分析引入了一种稳健的方法,可广泛应用于植物生物学和环境研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

New dimension in leaf stomatal behavior analysis: a robust method with machine learning approach

New dimension in leaf stomatal behavior analysis: a robust method with machine learning approach

Stomata are specialized pores that play a vital role in gas exchange and photosynthesis. Microscopic images are often used to assess stomatal characteristics in plants; however, this can be a challenging task. By utilizing Matterport’s Mask R-CNN implementation as the foundational model, fine-tuning was conducted on a dataset of 810 microscopic images of Hedyotis corymbosa leaves’ surfaces for automated stomatal pores detection. The outcomes were promising, with the model achieving a convergence of 98% mean average precision (mAP) for both detection and segmentation. The training loss and validation loss values converged around 0.18 and 0.37, respectively. Regression analyses demonstrated the statistical significance (p values ≤ 0.05) of predictor parameters. Notably, the tightest cluster of data points was observed in stomata pore area measurements, followed by width and length. This highlights the precision of the stomatal pore area in characterizing stomatal traits. Despite challenges posed by the original dataset’s low-resolution images and artifacts like dust, bubbles, and blurriness, our innovative utilization of the Mask R-CNN algorithm yielded commendable outcomes. This research introduces a robust approach for stomatal phenotyping with broad applications in plant biology and environmental studies.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Plant Biotechnology Reports
Plant Biotechnology Reports 生物-生物工程与应用微生物
CiteScore
4.10
自引率
4.20%
发文量
72
审稿时长
>12 weeks
期刊介绍: Plant Biotechnology Reports publishes original, peer-reviewed articles dealing with all aspects of fundamental and applied research in the field of plant biotechnology, which includes molecular biology, genetics, biochemistry, cell and tissue culture, production of secondary metabolites, metabolic engineering, genomics, proteomics, and metabolomics. Plant Biotechnology Reports emphasizes studies on plants indigenous to the Asia-Pacific region and studies related to commercialization of plant biotechnology. Plant Biotechnology Reports does not exclude studies on lower plants including algae and cyanobacteria if studies are carried out within the aspects described above.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信