Title |
Using a Structural Root System Model to Evaluate and Improve the Accuracy of Root Image Analysis Pipelines
|
---|---|
Published in |
Frontiers in Plant Science, April 2017
|
DOI | 10.3389/fpls.2017.00447 |
Pubmed ID | |
Authors |
Guillaume Lobet, Iko T. Koevoets, Manuel Noll, Patrick E. Meyer, Pierre Tocquin, Loïc Pagès, Claire Périlleux |
Abstract |
Root system analysis is a complex task, often performed with fully automated image analysis pipelines. However, the outcome is rarely verified by ground-truth data, which might lead to underestimated biases. We have used a root model, ArchiSimple, to create a large and diverse library of ground-truth root system images (10,000). For each image, three levels of noise were created. This library was used to evaluate the accuracy and usefulness of several image descriptors classically used in root image analysis softwares. Our analysis highlighted that the accuracy of the different traits is strongly dependent on the quality of the images and the type, size, and complexity of the root systems analyzed. Our study also demonstrated that machine learning algorithms can be trained on a synthetic library to improve the estimation of several root system traits. Overall, our analysis is a call to caution when using automatic root image analysis tools. If a thorough calibration is not performed on the dataset of interest, unexpected errors might arise, especially for large and complex root images. To facilitate such calibration, both the image library and the different codes used in the study have been made available to the community. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 14 | 23% |
United Kingdom | 6 | 10% |
France | 3 | 5% |
Switzerland | 3 | 5% |
Canada | 2 | 3% |
India | 2 | 3% |
Netherlands | 2 | 3% |
Australia | 2 | 3% |
Brazil | 1 | 2% |
Other | 8 | 13% |
Unknown | 18 | 30% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 37 | 61% |
Scientists | 18 | 30% |
Science communicators (journalists, bloggers, editors) | 4 | 7% |
Practitioners (doctors, other healthcare professionals) | 2 | 3% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Canada | 1 | 1% |
Unknown | 88 | 99% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 19 | 21% |
Researcher | 13 | 15% |
Student > Doctoral Student | 9 | 10% |
Student > Master | 7 | 8% |
Student > Bachelor | 6 | 7% |
Other | 15 | 17% |
Unknown | 20 | 22% |
Readers by discipline | Count | As % |
---|---|---|
Agricultural and Biological Sciences | 37 | 42% |
Engineering | 5 | 6% |
Computer Science | 4 | 4% |
Environmental Science | 4 | 4% |
Biochemistry, Genetics and Molecular Biology | 3 | 3% |
Other | 10 | 11% |
Unknown | 26 | 29% |