aradeepopsis: From images to phenotypic traits using deep transfer learning

Abstract

Linking plant phenotype to genotype, i.e., identifying genetic determinants of phenotypic traits, is a common goal of both plant breeders and geneticists. While the ever-growing genomic resources and rapid decrease of sequencing costs have led to enormous amounts of genomic data, collecting phenotypic data for large numbers of plants remains a bottleneck. Many phenotyping strategies rely on imaging plants, which makes it necessary to extract phenotypic measurements from these images rapidly and robustly. Common image segmentation tools for plant phenotyping mostly rely on color information, which is error-prone when either background or plant color deviate from the underlying expectations. We have developed a versatile, fully open-source pipeline to extract phenotypic measurements from plant images in an unsupervised manner. ᴀʀᴀᴅᴇᴇᴘᴏᴘsɪs was built around the deep-learning model DeepLabV3+ that was re-trained for segmentation of Arabidopsis thaliana rosettes. It uses semantic segmentation to classify leaf tissue into up to three categories: healthy, anthocyaninrich, and senescent. This makes ᴀʀᴀᴅᴇᴇᴘᴏᴘsɪs particularly powerful at quantitative phenotyping from early to late developmental stages, of mutants with aberrant leaf color and/or phenotype, and of plants growing in stressful conditions where leaf color may deviate from green. Using our tool on a panel of 210 natural Arabidopsis accessions, we were able to not only accurately segment images of phenotypically diverse genotypes but also to map known loci related to anthocyanin production and early necrosis using the ᴀʀᴀᴅᴇᴇᴘᴏᴘsɪs output in genome-wide association analyses. Our pipeline is able to handle images of diverse origins, image quality, and background composition, and could even accurately segment images of a distantly related Brassicaceae. Because it can be deployed on virtually any common operating system and is compatible with several high-performance computing environments, ᴀʀᴀᴅᴇᴇᴘᴏᴘsɪs can be used independently of bioinformatics expertise and computing resources. ᴀʀᴀᴅᴇᴇᴘᴏᴘsɪs is available at https://github.com/Gregor-Mendel-Institute/aradeepopsis.

Got Rosettes? Phenotype Them Fast, Accurately, and Easily with ARADEEPOPSIS!

“…Michigan State University acr32@cornell.edu ORCID: 0000-0002-2996-5709 ARADEEPOPSIS can discriminate among different plant states. Three models that differ with respect to categorization and complexity successfully segment phenotypically diverse rosettes: model A segments green/healthy tissue and excludes senescent tissue, model B segments tissue into "senescent" and "nonsenescent" classes, and model C into "senescent," "anthocyanin-rich," and "green" classes (Adapted from Hüther et al [2020], Figure 2A).…”

“…(3) Will you need to photograph the plants? If so, ARADEEPOPSIS, introduced by co-first authors Patrick Hüther and Niklas Schandry et al (Hüther et al, 2020) may be in your future, and it could change your research outlook or trajectory! ARADEEPOPSIS (for Arabidopsis deeplearning-based optimal semantic image segmentation) is more than just a cool play on words; it is a novel, user-friendly deep-learning pipeline designed to assess phenotypes from top-view images of rosettes while eliminating a plethora of issues encountered in plant phenotyping, which is largely image based.…”

Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework

“…Phenotypic morphological traits such as height, leaf area and biomass, can be obtained by measurement and weighing, which is helpful for quantifying plant growth (Watt et al, 2020). The traditional methods of manual trait measurement are simple and accurate, but they are difficult to meet the demand of high-throughput trait acquisition in large quantities, and usually require destructive sampling, which is time-consuming and laborious (Hüther et al, 2020). The estimation of plant growth is a non-negligible element in the intelligent development of plant factories; thus it is of great practical significance to develop rapid, accurate and automatic methods for obtaining plant growth-related traits to replace some tedious manual measurements.…”

Research of intelligent reasoning system of Arabidopsis thaliana phenotype based on automated multi-task machine learning

“…Currently, Zhou et al (2021) introduced a deep learning-based maize image analysis software that can automatically solve a variety of image-based maize phenotyping tasks, such as internal length, stem diameter, and leaf count, for high-throughput plant phenotyping. Similarly, P. Hüther et al (Hüther et al, 2020). analyze the phenotype of Arabidopsis thaliana using transfer learning by centering our pipeline around the well-established deep-learning model DeepLabV3+ for batch automated plant leaf state analysis, and no automated generation of the model was implemented.…”