MyROOT 2.0: GTM develops computer vision tools for high throughput root phenotyping in plant sciences

The convergence between different science disciplines is one of the most exciting and challenging situations a scientist can face. An example of this is the collaboration between GTM and the research group led by Dr. Ana I. Caño-Delgado  at the Center for Research in Agricultural Genomics, which dates back to 2011.

The most interesting outcome of this collaboration is MyROOT, a software tool of image processing and computer vision algorithms for the accurate measurement of the primary root of Arabidopsis thaliana seedlings grown in laboratory conditions. The interest of MyROOT lies in that plant biologists typically rely on manual work when they need accurate root length measurements, as they find existing software tools inaccurate and hard to use.

The first version of MyROOT was published by The Plant Journal, one of the highest-ranked journals in plant sciences. The article, co-authored by GTM members Alejandro González and Xavier Sevillano, describes MyROOT to an audience with a biology background, highlighting its advantages with respect to other similar available tools, especially in terms of root length measurement accuracy.

The ongoing collaboration between GTM and CRAG has led to the evolution of MyROOT. The latest version of MyROOT, called MyROOT 2.0, takes a step forward towards fully automatic phenotyping. Indeed, its newest features reduce user intervention to a minimum, as it is capable of detecting roots automatically, a process that was tackled manually in the previous version.

This paves the way towards high throughput root phenotyping, making MyROOT 2.0 a suitable tool for processing large batches of images of Arabidopsis seedlings grown in laboratory conditions --a process which is key for plant scientists.

Moreover, MyROOT 2.0 has shown its ability to determine image scale automatically with subpixel accuracy. And also, when compared to state-of-the-art root length measurement software tools, MyROOT 2.0 achieves the highest root detection rate, obtaining measurements which are four times more accurate than its competitors.

This latest work has been recently published by Computers and Electronics in Agriculture, a prestigious journal that publishes advances in the development and application of computer hardware and software for solving problems in agriculture, agronomy, forestry, aquaculture, and livestock farming.

Click here to see MyROOT in action! Both versions of MyROOT are available for download!

Related publications:

Betegón-Putze, I., González, A., Sevillano, X., Blasco-Escámez, D. & Caño-Delgado, A.I. (2019) MyROOT: A method and software for the semi‐automatic measurement of primary root length in Arabidopsis seedlings. The Plant Journal, 98(6):1145-1156

González, A., Sevillano, X., Betegón-Putze, I., Blasco-Escámez, D., Ferrer, M. & Caño-Delgado, A.I. (2020) MyROOT 2.0: An automatic tool for high throughput and accurate primary root length measurement. Computers and Electronics in Agriculture, 168:105125