PhenoTrack3D: an automatic high-throughput phenotyping pipeline to track maize organs over time

Abstract

Background High-throughput phenotyping platforms allow the study of the form and function of a large number of genotypes subjected to different growing conditions (GxE). A number of image acquisition and processing pipelines have been developed to automate this process, for micro-plots in the field and for individual plants in controlled conditions. Capturing shoot development requires extracting from images both the evolution of the 3D plant architecture as a whole, and a temporal tracking of the growth of its organs. Results We propose PhenoTrack3D, a new pipeline to extract a 3D + t reconstruction of maize. It allows the study of plant architecture and individual organ development over time during the entire growth cycle. The method tracks the development of each organ from a time-series of plants whose organs have already been segmented in 3D using existing methods, such as Phenomenal [Artzet et al. in BioRxiv 1:805739, 2019] which was chosen in this study. First, a novel stem detection method based on deep-learning is used to locate precisely the point of separation between ligulated and growing leaves. Second, a new and original multiple sequence alignment algorithm has been developed to perform the temporal tracking of ligulated leaves, which have a consistent geometry over time and an unambiguous topological position. Finally, growing leaves are back-tracked with a distance-based approach. This pipeline is validated on a challenging dataset of 60 maize hybrids imaged daily from emergence to maturity in the PhenoArch platform (ca. 250,000 images). Stem tip was precisely detected over time (RMSE < 2.1 cm). 97.7% and 85.3% of ligulated and growing leaves respectively were assigned to the correct rank after tracking, on 30 plants × 43 dates. The pipeline allowed to extract various development and architecture traits at organ level, with good correlation to manual observations overall, on random subsets of 10–355 plants. Conclusions We developed a novel phenotyping method based on sequence alignment and deep-learning. It allows to characterise the development of maize architecture at organ level, automatically and at a high-throughput. It has been validated on hundreds of plants during the entire development cycle, showing its applicability on GxE analyses of large maize datasets.

Life Science Workflow Services (LifeSWS): Motivations and Architecture

“…For instance, the Phenomenal workflow supports the reconstruction in 3D and the segmentation of plant organs [2]. The PhenoTrack workflow, which is based on Phenomenal, allows the 3D reconstruction of plants with the temporal tracking of the growth of each organ for the entire developmental cycle [9]. Finally, RootSystemTracker provides a workflow for the automatic structural and developmental 2D root phenotyping of Arabidopsis plants in Petri dishes [10].…”

“…Figure 1 shows a) the Phenomenal workflow implemented in OpenAlea; b) 3D organ tracking of a maize plant with PhenoTrack3D [9]; and c) a reconstructed root system architecture through time using RootSystemTracker [10]. These workflows need to process large volumes of data on distributed infrastructures.…”

MIPDB: A maize image-phenotype database with multi-angle and multi-time characteristics

“…As a major crop in the globe, maize ( Zea Mays L.) is a plant with a distinct skeleton that grows easily in fields and is used for bioenergy, animal feed, and human food (29,30). One great example of the use of crossfusion research between AI and plant phenotypes is the use of deep learning to predict the number of leaves on maize plants in fields (31). Here, we created a maize imagephenotype database (MIPDB, http://phenomics.agis.org.cn) containing 17,631 highresolution images collected in outdoor filed, which were meticulously annotated with dot lines.…”