Deep machine learning provides state-of-the-art performance in image-based plant phenotyping

Abstract

In plant phenotyping, it has become important to be able to measure many features on large image sets in order to aid genetic discovery. The size of the datasets, now often captured robotically, often precludes manual inspection, hence the motivation for finding a fully automated approach. Deep learning is an emerging field that promises unparalleled results on many data analysis problems. Building on artificial neural networks, deep approaches have many more hidden layers in the network, and hence have greater discriminative and predictive power. We demonstrate the use of such approaches as part of a plant phenotyping pipeline. We show the success offered by such techniques when applied to the challenging problem of image-based plant phenotyping and demonstrate state-of-the-art results (>97% accuracy) for root and shoot feature identification and localization. We use fully automated trait identification using deep learning to identify quantitative trait loci in root architecture datasets. The majority (12 out of 14) of manually identified quantitative trait loci were also discovered using our automated approach based on deep learning detection to locate plant features. We have shown deep learning–based phenotyping to have very good detection and localization accuracy in validation and testing image sets. We have shown that such features can be used to derive meaningful biological traits, which in turn can be used in quantitative trait loci discovery pipelines. This process can be completely automated. We predict a paradigm shift in image-based phenotyping bought about by such deep learning approaches, given sufficient training sets.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 31

1. 1.
   Plant phenotyping: from bean weighing to image analysis · 2015

   No notice
2. 2.

   Wilf P, Zhang S, Chikkerur S Computer vision cracks the leaf code. Proc Natl Acad Sci U S A2016;113(12):3305–10.

   Not in our library10.1073/pnas.1524473113

3. 3.

   Ho. TK Random decision forests. In: Proceedings of the Third International Conference on Document Analysis and Recognition, vol. 1, 1995 p. 278–82.

   Not in our library

4. 4.

   Singh A, Ganapathysubramanian B, Singh AK Machine learning for high-throughput stress phenotyping in plants. Trends Plant Sci2016;21(2):110–24.

   Not in our library10.1016/j.tplants.2015.10.015

5. 5.

   Lecun Y, Bottou L, Bengio Y Gradient-based learning applied to document recognition. Proc IEEE1998;86(11):2278–324.

   Not in our library

6. 6.

   Hubel DH, Wiesel TN Receptive fields and functional architecture of monkey striate cortex. J Physiol1968;195(1):215–43.

   Not in our library10.1113/jphysiol.1968.sp008455

7. 7.

   Zhou J, Troyanskaya OG Predicting effects of noncoding variants with deep learning-based sequence model. Nat Methods2015;12(10):931–4.

   Not in our library10.1038/nmeth.3547

8. 8.

   Esteva A, Kuprel B, Novoa RA Dermatologist-level classification of skin cancer with deep neural networks. Nature2017;542(7639):115–8.

   Not in our library10.1038/nature21056

9. 9.

   Zeiler MD, Fergus R Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T, eds. Computer Vision – ECCV 2014. Cham, Switzerland: Springer International Publishing, 2014:818–33.

   Not in our library

10. 10.

    Krizhevsky A, Sutskever I, Hinton GE ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, eds. Advances in Neural Information Processing Systems 25. New York, USA: Curran Associates, Inc., 2012:1097–105.

    Not in our library

11. 11.

    Long J, Shelhamer E, Darrell T Fully convolutional networks for semantic segmentation. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, p. 3431–40.

    Not in our library10.1109/tpami.2016.2572683

12. 12.
    Deep machine learning provides state-of-the-art performance in image-based plant phenotyping · 2017

    No notice
13. 13.

    Rajpal VR, Rao SR, Raina SN, eds. Molecular Breeding for Sustainable Crop Improvement. Cham, Switzerland: Springer International Publishing, 2016.

    Not in our library

14. 14.
    Phenotyping pipeline reveals major seedling root growth QTL in hexaploid wheat · 2015

    No notice
15. 15.

    Pound MP, French AP, Atkinson JA RootNav: navigating images of complex root architectures. Plant Physiol2013;162(4):1802–14.

    Not in our library10.1104/pp.113.221531

16. 16.

    Burgess AJ, Retkute R, Pound MP High-resolution three-dimensional structural data quantify the impact of photoinhibition on long-term carbon gain in wheat canopies in the field. Plant Physiol2015;169(2):1192–204.

    Not in our library10.1104/pp.15.00722

17. 17.

    Pound MP, French AP, Murchie EH Automated recovery of three-dimensional models of plant shoots from multiple color images. Plant Physiol2014;166(4):1688–98.

    Not in our library10.1104/pp.114.248971

18. 18.

    Neumann B, Walter T, Hériché J Phenotypic profiling of the human genome by time-lapse microscopy reveals cell division genes. Nature2010;464(7289):721–7.

    Not in our library10.1038/nature08869

19. 19.

    French A, Ubeda-Tomas S, Holman TJ High-throughput quantification of root growth using a novel image-analysis tool. Plant Physiol2009;150(4):1784–95.

    Not in our library10.1104/pp.109.140558

20. 20.
    Characterization of polyploid wheat genomic diversity using a high‐density 90 000 single nucleotide polymorphism array · 2014

    No notice
21. 21.

    Broman KW, Wu H, Sen S R/qtl: QTL mapping in experimental crosses. Bioinformatics2003;19(7):889–90.

    Not in our library10.1093/bioinformatics/btg112

22. 22.

    Atkinson JA, Lobet G, Noll M, Meyer PE, Griffiths M, Wells DM Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large scale genetic studies. GigaScience2017 Oct 1;6(10):1–7. doi:.

    Not in our library10.1093/gigascience/gix084

23. 23.

    Romera-Paredes B, Torr PHS Recurrent instance segmentation. Computer Vision – ECCV.2016;312–29.

    Not in our library

24. 24.

    Kilian J, Whitehead D, Horak J The AtGenExpress global stress expression data set: protocols, evaluation and model data analysis of UV-B light, drought and cold stress responses. Plant J Cell Mol Biol2007;50(2):347–63.

    Not in our library10.1111/j.1365-313x.2007.03052.x

25. 25.

    Brenchley R, Spannagl M, Pfeifer M Analysis of the bread wheat genome using whole-genome shotgun sequencing. Nature2012;491(7426):705–10.

    Not in our library10.1038/nature11650

26. 26.

    Felzenszwalb PF, Girshick RB, Mcallester D Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell2010;32(9):1627–45.

    Not in our library10.1109/tpami.2009.167

27. 27.

    Harris C, Stephens M A combined corner and edge detector. In: Proceedings of the Fourth Alvey Vision Conference. 1988;147–51.

    Not in our library

28. 28.

    Jia Y Caffe: convolutional architecture for fast feature embedding. ArXiv Preprint2014 arXiv:14085093.

    Not in our library

29. 29.

    Simonyan K, Zisserman A Very deep convolutional networks for large-scale image recognition. ArXiv Preprint2014 arXiv:14091556Cs.

    Not in our library

30. 30.

    Srivastava N, Hinton G, Krizhevsky A Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res2014;15(1):1929–58.

    Not in our library

31. 31.

    Pound MP, French AP Deep learning for plant phenotyping. protocols.io.2017 https://dx.doi.org/10.17504/protocols.io.jcncive.

    Not in our library

Cited by papers we hold 4

• Maize Tassel Detection From UAV Imagery Using Deep Learning · 2021
  Not checked
• A review of deep learning applications for genomic selection · 2021
  No notice
• Leveraging Image Analysis for High-Throughput Plant Phenotyping · 2019
  Not checked
• PlantCV v2: Image analysis software for high-throughput plant phenotyping · 2017
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.