Supporting data for "Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping"
Dataset type: Imaging, Software
Data released on August 24, 2017
Pound MP; Atkinson JA; Burgess AJ; Wilson MH; Griffiths M; Jackson AS; Bulat A; Tzimiropoulos G; Wells DM; Murchie EH; Pridmore TP; French AP (2017): Supporting data for "Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping" GigaScience Database. https://doi.org/10.5524/100343
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 localisation. 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 QTL were also discovered using our automated approach based on the deep learning detection to locate plant features.
We have shown deep-learning-based phenotyping to have very good detection and localisation 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 QTL 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.
Additional details
Read the peer-reviewed publication(s):
- Pound, M. P., Atkinson, J. A., Townsend, A. J., Wilson, M. H., Griffiths, M., Jackson, A. S., Bulat, A., Tzimiropoulos, G., Wells, D. M., Murchie, E. H., Pridmore, T. P., & French, A. P. (2017). Deep machine learning provides state-of-the-art performance in image-based plant phenotyping. GigaScience, 6(10). https://doi.org/10.1093/gigascience/gix083 (PubMed:29020747)
Related datasets:
doi:10.5524/100343 Cites doi:10.5524/100346
Click on a table column to sort the results.
Table SettingsSample ID | Common Name | Scientific Name | Sample Attributes | Taxonomic ID | Genbank Name |
---|---|---|---|---|---|
Root Images | Spring wheat | Triticum aestivum | Age:11 |
4565 | bread wheat |
Shoot Images | Spring wheat | Triticum aestivum | Life stage:anthesis |
4565 | bread wheat |
Click on a table column to sort the results.
Table SettingsFile Name | Description | Sample ID | Data Type | File Format | Size | Release Date | File Attributes | Download |
---|---|---|---|---|---|---|---|---|
Readme | TEXT | 4.38 kB | 2017-08-16 | MD5 checksum: 49a5a28236bba8b03373373bb22fdb9b |
||||
LMDB image database files | Mixed archive | TAR | 33.63 MB | 2017-08-16 | MD5 checksum: 5bee8b9a53775bab60ab809ce98e300f |
|||
LMDB image database files | Mixed archive | TAR | 134.33 MB | 2017-08-16 | MD5 checksum: 3c755ea5d7799b2d2b22449caf3855a5 |
|||
Caffe mean image file | Other | UNKNOWN | 21.18 kB | 2017-08-16 | MD5 checksum: d4a12f8ba0a324f50a5492b99025f26c |
|||
Source images for the root dataset | Mixed archive | archive | 940.37 MB | 2017-08-16 | MD5 checksum: 70ad6df1c4272bab4deafdafad0e0c02 |
|||
mixed archive: Unseen testing images and network output for the root dataset. | Mixed archive | TAR | 156.64 MB | 2017-08-16 | MD5 checksum: 8630e9823d7faa2d71a71a02e9560d66 |
|||
Helper bash script | Script | UNKNOWN | 186 B | 2017-08-16 | MD5 checksum: 35b20722002ced0ec59558f0c08ea55e |
|||
Helper bash script | Script | UNKNOWN | 115 B | 2017-08-16 | MD5 checksum: 5d21932cfb73363bd19233c3db0549a9 |
|||
Python code to scan an image using the CNN | Script | Python | 2.14 kB | 2017-08-16 | MD5 checksum: e4609d2f6cedeb0058a1cb0512a7b05d |
|||
Python code to combine an input image npy array into an output image | Script | Python | 839 B | 2017-08-16 | MD5 checksum: 48f6efd2a4846876c616f884447fedfd |
Funding body | Awardee | Award ID | Comments |
---|---|---|---|
European Research Council | MJ Bennett | 294729 | FP7 Ideas |
Protocols.io:
Date | Action |
---|---|
August 25, 2017 | Dataset publish |
October 17, 2017 | Manuscript Link added : 10.1093/gigascience/gix083 |
November 9, 2022 | Manuscript Link updated : 10.1093/gigascience/gix083 |
May 23, 2023 | External Link updated : https://www.protocols.io/widgets/doi?uri=dx.doi.org/10.17504/protocols.io.jcncive |