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

3D U-Net Segmentation Improves Root System Reconstruction from 3D MRI Images in Automated and Manual Virtual Reality Work Flows

Tobias Selzner1( ), Jannis Horn2, Magdalena Landl1, Andreas Pohlmeier1, Dirk Helmrich3, Katrin Huber1, Jan Vanderborght1, Harry Vereecken1, Sven Behnke2, Andrea Schnepf1
Forschungszentrum Juelich GmbH, Agrosphere (IBG-3), Juelich, Germany
Autonomous Intelligence Systems Group, University of Bonn, Bonn, Germany
Forschungszentrum Juelich GmbH, Juelich Supercomputing Center, Juelich, Germany
Show Author Information

Abstract

Magnetic resonance imaging (MRI) is used to image root systems grown in opaque soil. However, reconstruction of root system architecture (RSA) from 3-dimensional (3D) MRI images is challenging. Low resolution and poor contrast-to-noise ratios (CNRs) hinder automated reconstruction. Hence, manual reconstruction is still widely used. Here, we evaluate a novel 2-step work flow for automated RSA reconstruction. In the first step, a 3D U-Net segments MRI images into root and soil in super-resolution. In the second step, an automated tracing algorithm reconstructs the root systems from the segmented images. We evaluated the merits of both steps for an MRI dataset of 8 lupine root systems, by comparing the automated reconstructions to manual reconstructions of unaltered and segmented MRI images derived with a novel virtual reality system. We found that the U-Net segmentation offers profound benefits in manual reconstruction: reconstruction speed was doubled (+97%) for images with low CNR and increased by 27% for images with high CNR. Reconstructed root lengths were increased by 20% and 3%, respectively. Therefore, we propose to use U-Net segmentation as a principal image preprocessing step in manual work flows. The root length derived by the tracing algorithm was lower than in both manual reconstruction methods, but segmentation allowed automated processing of otherwise not readily usable MRI images. Nonetheless, model-based functional root traits revealed similar hydraulic behavior of automated and manual reconstructions. Future studies will aim to establish a hybrid work flow that utilizes automated reconstructions as scaffolds that can be manually corrected.

References

1

Schmidhuber J, Tubiello FN. Global food security under climate change. Proc Natl Acad Sci. 2007;104(50):19703–19708.
Crossref Google Scholar
2
Food and Agriculture Organization of the United Nations (FAO), The future of food and agriculture - Trends and challenges. 2017. [accessed 12 Oct 2022] https://www.fao.org/3/i6583e/i6583e.pdf
3

Tilman D, Balzer C, Hill J, Befort BL. Global food demand and the sustainable intensification of agriculture. Proc Natl Acad Sci U S A. 2011;108(50):20260–20264.
Crossref Google Scholar
4
Food and Agriculture Organization of the United Nations (FAO), Climate-smart agriculture sourcebook. 2013. [accessed 12 Oct 2022] https://www.fao.org/3/i3325e/i3325e.pdf
5

Osmont KS, Sibout R, Hardtke CS. Hidden branches: Developments in root system architecture. Annu Rev Plant Biol. 2007;58(1):93–113.
Crossref Google Scholar
6

Lynch JP. Harnessing root architecture to address global challenges. Plant J. 2022;109(2):415–431.
Crossref Google Scholar
7

Atkinson JA, Pound MP, Bennett MJ, Wells DM. Uncovering the hidden half of plants using new advances in root phenotyping. Curr Opin Biotechnol. 2019;55:1–8.
Crossref Google Scholar
8

Lynch J. Root architecture and plant productivity. Plant Physiol. 1995;109(1):7–13.
Crossref Google Scholar
9
Pohlmeier A, Haber-Pohlmeier S, Javaux M, Vereecken H. Magnetic resonance imaging techniques for visualization of root growth and root water uptake processes. In: Anderson SH, Hopmans JW, editors. Soil–water–root processes: Advances in tomography and imaging. Madison (WI): Soil Science Society of America; 2013. p. 137–156.
Crossref
10

Pohlmeier A, Garré S, Roose T. Noninvasive imaging of processes in natural porous media: From pore to field scale. Vadose Zone J. 2018;17(1):1–3.
Crossref Google Scholar
11

Koestel J. SoilJ: An ImageJ plugin for the semiautomatic processing of three-dimensional X-ray images of soils. Vadose Zone J. 2018;17(1):1–7.
Crossref Google Scholar
12

Gerth S, Clauße J, Eggert A, Wörlein N, Waininger M, Wittenberg T, Uhlmann N. Semiautomated 3D root segmentation and evaluation based on X-ray CT imagery. Plant Phenomics. 2021;2021:Article 8747930.
Crossref Google Scholar
13

Wei G, Schlüter S, Blaser S, Shen J, Vetterlein D. A shape-based method for automatic and rapid segmentation of roots in soil from X-ray computed tomography images: Rootine. Plant Soil. 2019;441:643–655.
Crossref Google Scholar
14
Schulz H, Postma JA, van Dusschoten D, Scharr H, Behnke S. Plant root system analysis from MRI images. In: Csurka G, Kraus M, Laramee RS, Richard P, Braz J, editors. Computer vision, imaging and computer graphics. Theory and applications. Berlin, Heidelberg (Germany): Springer; 2013. p. 441–425.
Crossref
15

Stingaciu L, Schulz H, Pohlmeier A, Behnke S, Zilken H, Javaux M, Vereecken H. In situ root system architecture extraction from magnetic resonance imaging for water uptake modeling. Vadose Zone J. 2013;12:1–9.
Crossref Google Scholar
16

van Dusschoten D, Metzner R, Kochs J, Postma JA, Pflugfelder D, Bühler J, Schurr U, Jahnke S. Quantitative 3D analysis of plant roots growing in soil using magnetic resonance imaging. Plant Physiol. 2016;170(3):1176–1188.
Crossref Google Scholar
17

Metzner R, Eggert A, van Dusschoten D, Pflugfelder D,Gerth S, Schurr U, Uhlmann N, Jahnke S. Direct comparison of MRI and X-ray CT technologies for 3D imaging of root systems in soil: Potential and challenges for root trait quantification. Plant Methods. 2015;11:Article 17.
Crossref Google Scholar
18

Rascher US, Blossfeld S, Fiorani F, Jahnke S, Jansen M, Kuhn AJ, Matsubara S, Märtin LLA, Merchant A, Metzner R, et al. Non-invasive approaches for phenotyping of enhanced performance traits in bean. Funct Plant Biol. 2011;38(12):968–983.
Crossref Google Scholar
19

Metzner R, van Dusschoten D, Bühler J, Schurr U, Jahnke S. Belowground plant development measured with magnetic resonance imaging (MRI): Exploiting the potential for non-invasive trait quantification using sugar beet as a proxy. Front Plant Sci. 2014;5:Article 469.
Crossref Google Scholar
20

Pflugfelder D, Metzner R, van Dusschoten D, Reichel R,Jahnke S, Koller R. Non-invasive imaging of plant roots in different soils using magnetic resonance imaging (MRI). Plant Methods. 2017;13:Article 102.
Crossref Google Scholar
21

Menzel MI, Oros-Peusquens AM, Pohlmeier A, Shah NJ, Schurr U, Schneider HU. Comparing 1H-NMR imaging and relaxation mapping of German white asparagus from five different cultivation sites. J Plant Nutr Soil Sci. 2007;170(1):24–38.
Crossref Google Scholar
22

Jiang N, Floro E, Bray AL, Laws B, Duncan KE, Topp CN. Three-dimensional time-lapse analysis reveals multiscale relationships in maize root systems with contrasting architectures. Plant Cell. 2019;31:1708–1722.
Crossref Google Scholar
23

McKay Fletcher DM, Ruiz S, Dias T, Petroselli C, Roose T. Linking root structure to functionality: The impact of root system architecture on citrate-enhanced phosphate uptake. New Phytol. 2020;227(2):376–391.
Crossref Google Scholar
24

Koch A, Meunier F, Vanderborght J, Garré S, Pohlmeier A, Javaux M. Functional-structural root-system model validation using a soil MRI experiment. J Exp Bot. 2019;70(10):2797–2809.
Crossref Google Scholar
25

Daly KR, Tracy SR, Crout NMJ, Mairhofer S, Pridmore TP, Mooney SJ, Roose T. Quantification of root water uptake in soil using X-ray computed tomography and image-based modelling. Plant Cell Environ. 2018;41(1):121–133.
Crossref Google Scholar
26

Postma JA, Kuppe C, Owen MR, Mellor N, Griffiths M, Bennett MJ, Lynch JP, Watt M. OpenSimRoot: Widening the scope and application of root architectural models. New Phytol. 2017;215(3):1274–1276.
Crossref Google Scholar
27

Koebernick N, Huber K, Kerkhofs E, Vanderborght J, Javaux M, Vereecken H, Vetterlein D. Unraveling the hydrodynamics of split root water uptake experiments using CT scanned root architectures and three dimensional flow simulations. Front Plant Sci. 2015;6:Article 370.
Crossref Google Scholar
28

Khare D, Selzner T, Leitner D, Vanderborght J, Vereecken H, Schnepf A. Root system scale models significantly overestimate root water uptake at drying soil conditions. Front Plant Sci. 2022;13:Article 798741.
Crossref Google Scholar
29

Mairhofer S, Zappala S, Tracy SR, Sturrock C, Bennett M, Mooney SJ, Pridmore T. RooTrak: Automated recovery of three-dimensional plant root architecture in soil from X-ray microcomputed tomography images using visual tracking. Plant Physiol. 2012;158(2):561–569.
Crossref Google Scholar
30

Plenge E, Poot DHJ, Bernsen M, Kotek G, Houston G, Wielopolski P, van der Weerd L, Niessen WJ, Meijering E. Super-resolution methods in MRI: Can they improve the trade-off between resolution, signal-to-noise ratio, and acquisition time? Magn Reson Med. 2012;68(6):1983–1993.
Crossref Google Scholar
31

Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI. Z Med Phys. 2019;29(2):102–127.
Crossref Google Scholar
32
Ronneberger O, Fischer P, Brox T. Brox. U-Net: Convolutional networks for biomedical image segmentation. ArXiv. 2015. https://doi.org/10.48550/arXiv.1505.0459
Crossref
33
He Y, Yu H, Liu X, Yang Z, SunW, Wang Y, Fu Q, Zou Y, Mian A. Deep learning based 3D segmentation: A survey. ArXiv. 2021. https://doi.org/10.48550/arXiv.2103.05423
34

Al-Kofahi Y, Zaltsman A, Graves R, Marshall W, Rusu M. A deep learning-based algorithm for 2-D cell segmentation in microscopy images. BMC Bioinformatics. 2018;19(1):Article 365.
Crossref Google Scholar
35

Smith A, Petersen J, Selvan R, Rasmussen C. Segmentation of roots in soil with U-net. Plant Methods. 2020;16:Article 13.
Crossref Google Scholar
36

Alvarez-Borges FJ, King ONF, Madhusudhan BN, Connolley T, Basham M, Ahmed SI. Comparison of methods to segment variablecontrast XCT images of methane-bearing sand using U-Nets trained on single dataset sub-volumes. Methane. 2023;2(1):1–23.
Crossref Google Scholar
37

Alalwan N, Abozeid A, ElHabshy AA, Alzahrani A. Efficient 3D deep learning model for medical image semantic segmentation. Alex Eng J. 2021;60(1):1231–1239.
Crossref Google Scholar
38
O. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, O. Ronneberger, 3D U-Net: Learning dense volumetric segmentation from sparse annotation. ArXiv. 2016. https://doi.org/10.48550/arXiv.1606.06650
39
MMilletari F, Navab N, Ahmadi S-A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. Paper presented at: 2016 Fourth International Conference on 3D Vision (3DV); 2016 Oct 25–28; Stanford, CA.
Crossref
40

Kamnitsas K, Ledig C, Newcombe VF, Simpson JP, Kane AD, Menon DK, Rueckert D, Glocker B. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal. 2017;36:61–78.
Crossref Google Scholar
41

Smith AG, Petersen J, Terrones-Campos C, Berthelsen AK, Forbes NJ, Darkner S, Specht L, Vogelius IR. RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy. Med Phys. 2022;49(1):461–473.
Crossref Google Scholar
42
Zhao Y, Wandel N, Landl M, Schnepf A, Behnke S. 28th European symposium on artificial neural networks. Computational Intelligence and Machine Learning (ESANN). 2020.
43

Behnke S. Learning iterative image reconstruction in the neural abstraction pyramid. Int J Comput Intell Appl. 2001;1(4):427–438.
Crossref Google Scholar
44
Dong C, Loy CC, He K, Tang X. Computer Vision ECCV 2014. 13th European Conference on Computer Vision (ECCV); Springer; 2014.
45
Uzman AO, Horn J, Behnke S, Learning super-resolution 3D segmentation of plant root MRI images from few examples. 27th European Symposium on Artificial Neural Networks(ESANN); 2019.
46
Horn J. 25th International Conference on Pattern Recognition (ICPR); 2021 Jan 10–15.
47

Dijkstra EW. A note on two problems in connexion with graphs. Numer Math. 1959;1:269–271.
Crossref Google Scholar
48

Jin D, Iyer KS, Chen C, Hoffman EA, Saha PK. A robust and efficient curve skeletonization algorithm for tree-like objects using minimum cost paths. Pattern Recogn Lett. 2016;76:32–40.
Crossref Google Scholar
49

Lobet G, Pound MP, Diener J, Pradal C, Draye X, Godin C,Javaux M, Leitner D, Meunier F, Nacry P, et al. Root system markup language: Toward a unified root architecture description language. Plant Physiol. 2015;167(3):617–627.
Crossref Google Scholar
50

Schnepf A, Huber K, Landl M, Meunier F, Petrich L, Schmidt V. Statistical characterization of the root system architecture model CRootBox. Vadose Zone J. 2018;17:Article 170212.
Crossref Google Scholar
51

Schnepf A, Leitner D, Landl M, Lobet G, Mai TH, Morandage S, Sheng C, Zörner M, Vanderborght J, Vereecken H. CRootBox: A structural-functional modelling framework for root systems. Ann Bot. 2018;121(5):1033–1053.
Crossref Google Scholar
52

Zhou X-R, Schnepf A, Vanderborght J, Leitner D, Lacointe A, Vereecken H, Lobet G. CPlantBox, a whole-plant modelling framework for the simulation of water- and carbon-related processes. in silico Plants. 2020;2(1):diaa001.
Crossref Google Scholar
53
R Core Team, R: A language and environment for statistical computing. 2022.
54
RStudio: Integrated development environment for R; 2022.
55
Kassambara A, rstatix: Pipe-friendly framework for basic statistical tests. R package version 0.7.0. 2021.
56
Kassambara A, ggpubr: ‘ggplot2’ based publication ready plots. R package version 0.4.0. 2020.
57

Bauer F, Lärm L, Morandage S, Lobet G, Vanderborght J, Vereecken H, Schnepf A. Development and validation of a deep learning based automated minirhizotron image analysis pipeline. Plant Phenomics. 2022;2022:Article 9758532.
Crossref Google Scholar
58

Pflugfelder D, Kochs J, Koller R, Jahnke S, Mohl C, Pariyar S,Fassbender H, Nagel KA, Watt M, van Dusschoten D. The root system architecture of wheat establishing in soil is associated with varying elongation rates of seminal roots: Quantification using 4D magnetic resonance imaging. J Exp Bot. 2021;73(7):2050–2060.
Crossref Google Scholar
59

Pohlmeier A, Haber-Pohlmeier S, Stapf S. A fast field cycling nuclear magnetic resonance relaxometry study of natural soils. Vadose Zone J. 2009;8(3):735–743.
Crossref Google Scholar
60
Heinrichs MA, Siemens Aktiengesellschaft. Magnets, spins, and resonances: An introduction into the basics of magnetic resonance imaging. Erlangen (Germany): Siemens; 1992.
61

Douglas DH, Peucker TK. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica International J Geographic Inf. Geovisualization. 1973;10(2):112–122.
Crossref Google Scholar
62

Newman EI. Resistance to water flow in soil and plant. Ⅰ. Soil resistance in relation to amounts of root: Theoretical estimates. J Appl Ecol. 1969;68:1051–1058.
Crossref Google Scholar
63

Meunier F, Draye X, Vanderborght J, Javaux M, Couvreur V. A hybrid analytical-numerical method for solving water flow equations in root hydraulic architectures. Appl Math Model. 2017;52:648–663.
Crossref Google Scholar
64

Zarebanadkouki M, Meunier F, Couvreur V, Cesar J,Javaux M, Carminati A. Estimation of the hydraulic conductivities of lupine roots by inverse modelling of high-resolution measurements of root water uptake. Ann Bot. 2016;118(4):853–864.
Crossref Google Scholar
65

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):Article 676.
Crossref Google Scholar
Plant Phenomics
Volume 5,
2023
Article number: 0076
DOI: 10.34133/plantphenomics.0076
Cite this article:
Selzner T, Horn J, Landl M, et al. 3D U-Net Segmentation Improves Root System Reconstruction from 3D MRI Images in Automated and Manual Virtual Reality Work Flows. Plant Phenomics, 2023, 5: 0076. https://doi.org/10.34133/plantphenomics.0076

144

Views

8

Crossref

6

Web of Science

6

Scopus

0

CSCD

Altmetrics
Received: 20 October 2022
Accepted: 10 July 2023
Published: 28 July 2023
© 2023 Tobias Selzner 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