AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Plant Phenomics Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa

John Lagergren1( ), Mirko Pavicic1, Hari B. Chhetri1, Larry M. York1, Doug Hyatt1, David Kainer1, Erica M. Rutter2, Kevin Flores3, Jack Bailey-Bale4, Marie Klein4, Gail Taylor4, Daniel Jacobson1( ), Jared Streich1( )
Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
Department of Applied Mathematics, University of California, Merced, CA, USA
Department of Mathematics, North Carolina State University, Raleigh, NC, USA
Department of Plant Sciences, University of California, Davis, CA, USA
Show Author Information

Abstract

Plant phenotyping is typically a time-consuming and expensive endeavor, requiring large groups of researchers to meticulously measure biologically relevant plant traits, and is the main bottleneck in understanding plant adaptation and the genetic architecture underlying complex traits at population scale. In this work, we address these challenges by leveraging few-shot learning with convolutional neural networks to segment the leaf body and visible venation of 2,906 Populus trichocarpa leaf images obtained in the field. In contrast to previous methods, our approach (a) does not require experimental or image preprocessing, (b) uses the raw RGB images at full resolution, and (c) requires very few samples for training (e.g., just 8 images for vein segmentation). Traits relating to leaf morphology and vein topology are extracted from the resulting segmentations using traditional open-source image-processing tools, validated using real-world physical measurements, and used to conduct a genome-wide association study to identify genes controlling the traits. In this way, the current work is designed to provide the plant phenotyping community with (a) methods for fast and accurate image-based feature extraction that require minimal training data and (b) a new population-scale dataset, including 68 different leaf phenotypes, for domain scientists and machine learning researchers. All of the few-shot learning code, data, and results are made publicly available.

References

1

Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Commun ACM. 2017;60(6):84–90.
Crossref Google Scholar
2
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Paper presented at: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27–30; Las Vegas, USA.
Crossref
3
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, editors. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Cham: Springer; 2015. p. 234–241.
Crossref
4

Taylor G, Donnison IS, Murphy-Bokern D, Morgante M, Bogeat-Triboulot MB, Bhalerao R, Hertzberg M, Polle A, Harfouche A, Alasia F, et al. Sustainable bioenergy for climate mitigation: Developing drought-tolerant trees and grasses. Ann Bot. 2019;124(4):513–520.
Crossref Google Scholar
5

Grattapaglia D, Silva-Junior OB, Resende RT, Cappa EP,Müller BSF, Tan B, Isik F, Ratcliffe B, el-Kassaby YA. Quantitative genetics and genomics converge to accelerate forest tree breeding. Front Plant Sci. 2018;9:Article 1693.
Crossref Google Scholar
6

Yang J, Guo X, Li Y, Marinello F, Ercisli S, Zhang Z. A survey of few-shot learning in smart agriculture: Developments, applications, and challenges. Plant Methods. 2022;18(1):Article 28.
Crossref Google Scholar
7
Rutter E, Lagergren J, Flores K. Automated object tracing for biomedical image segmentation using a deep convolutional neural network. Medical Image Computing and Computer Assisted Intervention - MICCAI 2018, Lecture Notes in Computer Science; Cham: Springer; 2018.
Crossref
8
Rutter E, Lagergren J, Flores K. A convolutional neural network method for boundary optimization enables few-shot learning for biomedical image segmentation. Medical Image Computing and Computer Assisted Intervention - MICCAI 2019, Lecture Notes in Computer Science; Cham: Springer; 2019.
Crossref
9

Januszewski M, Kornfeld J, Li PH, Pope A, Blakely T, Lindsey L, Maitin-Shepard J, Tyka M, Denk W, Jain V. High-precision automated reconstruction of neurons with flood-filling networks. Nat Methods. 2018;15(8):605–610.
Crossref Google Scholar
10
Lagergren J, Rutter E, Flores K. Region growing with convolutional neural networks for biomedical image segmentation. ArXiv. 2020. https://doi.org/10.48550/arXiv.2009.11717
11

Tuskan GA, Difazio S, Jansson S, Bohlmann J, Grigoriev I, Hellsten U, Putnam N, Ralph S, Rombauts S, Salamov A, et al. The genome of black cottonwood, populus trichocarpa (Torr. & Gray). Science. 2006;313(5793):1596–1604.
Crossref Google Scholar
12

García-Lorenzo M, Sjödin A, Jansson S, Funk C. Protease gene families in populus and arabidopsis. BMC Plant Biol. 2006;6:Article 30.
Crossref Google Scholar
13

Geraldes A, Pang J, Thiessen N, Cezard T, Moore R, Zhao Y, Tam A, Wang S, Friedmann M, Birol I, et al. Snp discovery in black cottonwood (populus trichocarpa) by population transcriptome resequencing. Mol Ecol Resour. 2011; 11 Suppl 1:81–92.
Crossref Google Scholar
14

Zhang J, Yang Y, Zheng K, Xie M, Feng K, Jawdy SS, Gunter LE, Ranjan P, Singan VR, Engle N, et al. Genome-wide association studies and expression-based quantitative trait loci analyses reveal roles of hct 2 in caffeoylquinic acid biosynthesis and its regulation by defense-responsive transcription factors in populus. New Phytol. 2018;220(2):502–516.
Crossref Google Scholar
15

Slavov GT, DiFazio SP, Martin J, Schackwitz W, Muchero W, Rodgers-Melnick E, Lipphardt MF, Pennacchio CP, Hellsten U, Pennacchio LA, et al. Genome resequencing reveals multiscale geographic structure and extensive linkage disequilibrium in the forest tree populus trichocarpa. New Phytol. 2012;196(3):713–725.
Crossref Google Scholar
16

Evans LM, Slavov GT, Rodgers-Melnick E, Martin J, Ranjan P, Muchero W, Brunner AM, Schackwitz W, Gunter L, Chen JG, et al. Population genomics of populus trichocarpa identifies signatures of selection and adaptive trait associations. Nat Genet. 2014;46(10):1089–1096.
Crossref Google Scholar
17

Chhetri HB, Macaya-Sanz D, Kainer D, Biswal AK, Evans LM,Chen JG, Collins C, Hunt K, Mohanty SS, Rosenstiel T, et al. Multitrait genome-wide association analysis of populus trichocarpa identifies key polymorphisms controlling morphological and physiological traits. New Phytol. 2019;223(1):293–309.
Crossref Google Scholar
18

Chhetri HB, Furches A, Macaya-Sanz D, Walker AR, Kainer D,Jones P, Harman-Ware AE, Tschaplinski TJ, Jacobson D, Tuskan GA, et al. Genome-wide association study of wood anatomical and morphological traits in populus trichocarpa. Front Plant Sci. 2020;11:Article 545748.
Crossref Google Scholar
19

Jansson S, Douglas CJ. Populus: A model system for plant biology. Annu Rev Plant Biol. 2007;58:435–458.
Crossref Google Scholar
20

Rubin EM. Genomics of cellulosic biofuels. Nature. 2008;454(7206):841–845.
Crossref Google Scholar
21

McKown AD, Klápště J, Guy RD, Geraldes A, Porth I, Hannemann J, Friedmann M, Muchero W, Tuskan GA, Ehlting J,et al. Genome-wide association implicates numerous genes underlying ecological trait variation in natural populations of populus trichocarpa. New Phytol. 2014;203(2):535–553.
Crossref Google Scholar
22

Sack L, Scoffoni C. Leaf venation: Structure, function, development, evolution, ecology and applications in the past, present and future. New Phytol. 2013;198(4):983–1000.
Crossref Google Scholar
23

Bühler J, Rishmawi L, Pflugfelder D, Huber G, Scharr H, Hülskamp M, Koornneef M, Schurr U, Jahnke S. Phenovein–a tool for leaf vein segmentation and analysis. Plant Physiol. 2015;169(4):2359–2370.
Crossref Google Scholar
24

Xu H, Blonder B, Jodra M, Malhi Y, Fricker M. Automated and accurate segmentation of leaf venation networks via deep learning. New Phytol. 2021;229(1):631–648.
Crossref Google Scholar
25
Katyal V, Aviral. Leaf vein segmentation using odd gabor filters and morphological operations. ArXiv. 2012. https://doi.org/10.48550/arXiv.1206.5157
26
Larese MG, Craviotto RM, Arango MR, Gallo C, Granitto PM. Iberoamerican Congress on Pattern Recognition; Springer; 2012.
27
Salima A, Herdiyeni Y, Douady S. Paper presented at: International Conference on Advanced Computer Science and Information Systems (ICACSIS); 2015 Oct 10–11; Depok, Indonesia.
28

Zhu J, Yao J, Yu Q, He W, Xu C, Qin G, Zhu Q, Fan D, Zhu H. A fast and automatic method for leaf vein network extraction and vein density measurement based on object-oriented classification. Front Plant Sci. 2020;11:Article 499.
Crossref Google Scholar
29

Jiang Y, Li C. Convolutional neural networks for image-based high-throughput plant phenotyping: A review. Plant Phenomics. 2020;2020:Article 4152816.
Crossref Google Scholar
30

Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al. Pytorch: An imperative style, high-performance deep learning library. Adv Neural Inf Proces Syst. 2019;32:Article 721.
Google Scholar
31
Lagergren J, Pavicic M, Chhetri HB, Larry M, Hyatt D, Kainer D, Rutter EM, Flores K, Bailey-Bale J, Klein M, et al. Few-shot leaf segmentation, Tech. rep., Oak Ridge National Lab. (ORNL); United States; 2023.
32

Schindelin J, Arganda-Carreras I, Frise E, Kaynig V, Longair M,Pietzsch T, Preibisch S, Rueden C, Saalfeld S, Schmid B, et al. Fiji: An open-source platform for biological-image analysis. Nat Methods. 2012;9(7):676.
Crossref Google Scholar
33
Seethepalli A, York L. Rhizovision explorer-interactive software for generalized root image analysis designed for everyone (version 2.0.2). Zenodo. 2020 Oct 16.
34

Seethepalli A, Dhakal K, Griffiths M, Guo H, Freschet GT, York LM. Rhizovision explorer: Open-source software for root image analysis and measurement standardization. AoB plants. 2021;13(6):plab056.
Crossref Google Scholar
35

Wang J, Zhang Z. Gapit version 3: Boosting power and accuracy for genomic association and prediction. Genom Proteom Bioinform. 2021;19(4):629–640.
Crossref Google Scholar
36
Lagergren J, Pavicic M, Chhetri HB, Larry M, Hyatt D, Kainer D, Rutter EM, Flores K, Bailey-Bale J, Klein M, et al. Supporting information for "Few-shot learning enables population-scale analysis of leaf traits in Populus trichocarpa", Tech. rep. Oak Ridge National Lab. (ORNL), Oak Ridge, USA; 2023. https://doi.org/10.13139/ORNLNCCS/1908723
Crossref
37
Lagergren J, Pavicic M, Chhetri HB, Larry M, Hyatt D, Kainer D, Rutter EM, Flores K, Bailey-Bale J, Klein M, et al. Supporting information for "Few-shot learning enables population-scale analysis of leaf traits in Populus trichocarpa", Tech. rep. Oak Ridge National Lab. (ORNL), Oak Ridge, USA; 2023. https://doi.org/10.5281/zenodo.7908197
Crossref
38
Bailey-Bale J, Freer-Smith P, Suvocarev K, Chen J, Muchero W, DiFazio S, Tuskan G, Tschaplinski T, Taylor G. Genomic sciences program (GSP). Annual PI Meeting. 2021 Feb 22.
39
Perfection v19/v39 user’s guide.
40
Swiss precision instruments.
41
The GIMP. Development team. Gimp.
42
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. ArXiv. 2014. https://doi.org/10.48550/arXiv.1409.1556
43
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. Paper presented at: International Conference on Machine Learning (PMLR); 2015 Jul 7–9; Lille, France.
44
Maas AL, Hannun AY, Ng AY. Rectifier nonlinearities improve neural network acoustic models. Paper presented at: Proceedings of the 30th International Conference on Machine Learning; 2013 June 16–21; Georgia, USA.
45
Kingma DP, Ba J. Adam: A method for stochastic optimization. ArXiv. 2014. https://doi.org/10.48550/arXiv.1412.6980
46
Lin T-Y, Goyal P, Girshick R, He K, Dollár P. Focal loss for dense object detection. Paper presented at: Proceedings of the IEEE International Conference on Computer Vision; 2017 Jun 20–23; Cambridge, USA.
Crossref
47
Nychka D, Furrer R, Paige J, Sain S, fields: Tools for spatial data. 2021.
48

Bates D, Mächler M, Bolker B, Walker S. Fitting linear mixed-effects models using lme4. J Stat Softw. 2015;67(1):1–48.
Crossref Google Scholar
49

Nordberg H, Cantor M, Dusheyko S, Hua S, Poliakov A, Shabalov I, Smirnova T, Grigoriev IV, Dubchak I. The genome portal of the department of energy joint genome institute: 2014 updates. Nucleic Acids Res. 2014;42:D26–D31.
Crossref Google Scholar
50
Li H. Aligning sequence reads, clone sequences and assembly contigs with bwa-mem. ArXiv. 2013. https://doi.org/10.48550/arXiv.1303.3997
51

Van der Auwera GA et al. From fastq data to high-confidence variant calls: The genome analysis toolkit best practices pipeline. Curr Protoc Bioinformatics. 2013;43(1110):11.10.1–11.10.33.
Crossref Google Scholar
52

Huang M, Liu X, Zhou Y, Summers RM, Zhang Z. Blink: A package for the next level of genome-wide association studies with both individuals and markers in the millions. Gigascience. 2019;8:giy154.
Crossref Google Scholar
53
He K, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. Paper presented at: Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2017 Oct 22–29; Venice, Italy.
Crossref
54
Ciresan DC, Giusti A, Gambardella LM, Schmidhuber J. Deep neural networks segment neuronal membranes in electron microscopy images. Paper presented at: Proceedings of the 25th International Conference on Neural Information Processing Systems; 2012 Dec 3–6; NY, USA.
55

Smith AG, Han E, Petersen J, Olsen NAF, Giese C, Athmann M, Dresbøll DB, Thorup-Kristensen K. Rootpainter: Deep learning segmentation of biological images with corrective annotation. New Phytol. 2022;236(2):774–791.
Crossref Google Scholar
56
Sreedasyam A, Plott C, Hossain MS, Lovell JT, Grimwood J, Carlson J, Shu S, Phillips J, Amirebrahimi M, Zane M, et al. Jgi plant gene atlas: An updateable transcriptome resource to improve structural annotations and functional gene descriptions across the plant kingdom. bioRxiv. 2022. https://www.biorxiv.org/content/10.1101/2022.09.30.510380v1
Crossref
57

de Vries H, Rüegsegger U, Hübner W, Friedlein A, Langen H, Keller W. Human pre-mrna cleavage factor iim contains homologs of yeast proteins and bridges two other cleavage factors. EMBO J. 2000;19(21):5895–5904.
Crossref Google Scholar
58

Xing D, Zhao H, Li QQ. Arabidopsis clp1-similar protein3, an ortholog of human polyadenylation factor clp1, functions in gametophyte, embryo, and postembryonic development. Plant Physiol. 2008;148(4):2059–2069.
Crossref Google Scholar
59

Ki H, Karim MR, Takada S, Ki T, Furutani M, Aida M, Tasaka M. Arabidopsis cup-shaped cotyledon3 regulates postembryonic shoot meristem and organ boundary formation. Plant Cell. 2006;18(11):2946–2957.
Crossref Google Scholar
60

Spinelli SV, Martin AP, Viola IL, Gonzalez DH, Palatnik JF. A mechanistic link between stm and cuc1 during arabidopsis development. Plant Physiol. 2011;156(4):1894–1904.
Crossref Google Scholar
61

Nikovics K, Blein T, Peaucelle A, Ishida T, Morin H, Aida M, Laufs P. The balance between the mir164a and cuc2 genes controls leaf margin serration in arabidopsis. Plant Cell. 2006;18(11):2929–2945.
Crossref Google Scholar
62

Klepikova AV, Kasianov AS, Gerasimov ES, Logacheva MD, Penin AA. A high resolution map of the arabidopsis thaliana developmental transcriptome based on rna-seq profiling. Plant J. 2016;88(6):1058–1070.
Crossref Google Scholar
63

Lemberg MK, Freeman M. Functional and evolutionary implications of enhanced genomic analysis of rhomboid intramembrane proteases. Genome Res. 2007;17(11):1634–1646.
Crossref Google Scholar
64

Kmiec-Wisniewska B, Krumpe K, Urantowka A, Sakamoto W, Pratje E, Janska H. Plant mitochondrial rhomboid, atrbl12, has different substrate specificity from its yeast counterpart. Plant Mol Biol. 2008;68(1-2):159–171.
Crossref Google Scholar
65

Simpson PJ, Tantitadapitak C, Reed AM, Mather OC, Bunce CM, White SA, Ride JP. Characterization of two novel aldo–keto reductases from arabidopsis: Expression patterns, broad substrate specificity, and an open active-site structure suggest a role in toxicant metabolism following stress. J Mol Biol. 2009;392(2):465–480.
Crossref Google Scholar
66

Sengupta D, Naik D, Reddy AR. Plant aldo-keto reductases (akrs) as multi-tasking soldiers involved in diverse plant metabolic processes and stress defense: A structure-function update. J Plant Physiol. 2015;179:40–55.
Crossref Google Scholar
67

Luo X, Wu W, Liang Y, Xu N, Wang Z, Zou H, Liu J. Tyrosine phosphorylation of the lectin receptor-like kinase lore regulates plant immunity. EMBO J. 2020;39:Article e102856.
Crossref Google Scholar
68

Wang W, Hu C, Li X, Zhu Y, Tao L, Cui Y, Deng D, Fan X,Zhang H, Li J, et al. Receptor-like cytoplasmic kinases pbl34/35/36 are required for cle peptide-mediated signaling to maintain shoot apical meristem and root apical meristem homeostasis in arabidopsis. Plant Cell. 2022;34(4):1289–1307.
Crossref Google Scholar
69

Sherson SM, Alford HL, Forbes SM, Wallace G, Smith SM. Roles of cell-wall invertases and monosaccharide transporters in the growth and development of arabidopsis. J Exp Bot. 2003;54(382):525–531.
Crossref Google Scholar
Plant Phenomics
Volume 5,
2023
Article number: 0072
DOI: 10.34133/plantphenomics.0072
Cite this article:
Lagergren J, Pavicic M, Chhetri HB, et al. Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa. Plant Phenomics, 2023, 5: 0072. https://doi.org/10.34133/plantphenomics.0072

179

Views

5

Crossref

2

Web of Science

2

Scopus

0

CSCD

Altmetrics
Received: 30 December 2022
Accepted: 27 June 2023
Published: 28 July 2023
© 2023 John Lagergren et al. Exclusive licensee Nanjing Agricultural University. No claim to original U.S. Government Works.

Distributed under a Creative Commons Attribution License (CC BY 4.0).
Return