skip to main content


Title: Deep learning-based high-throughput phenotyping can drive future discoveries in plant reproductive biology
Abstract Key message Advances in deep learning are providing a powerful set of image analysis tools that are readily accessible for high-throughput phenotyping applications in plant reproductive biology. High-throughput phenotyping systems are becoming critical for answering biological questions on a large scale. These systems have historically relied on traditional computer vision techniques. However, neural networks and specifically deep learning are rapidly becoming more powerful and easier to implement. Here, we examine how deep learning can drive phenotyping systems and be used to answer fundamental questions in reproductive biology. We describe previous applications of deep learning in the plant sciences, provide general recommendations for applying these methods to the study of plant reproduction, and present a case study in maize ear phenotyping. Finally, we highlight several examples where deep learning has enabled research that was previously out of reach and discuss the future outlook of these methods.  more » « less
Award ID(s):
1832186
NSF-PAR ID:
10252261
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Plant Reproduction
Volume:
34
Issue:
2
ISSN:
2194-7953
Page Range / eLocation ID:
81 to 89
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    The genomic revolution has fundamentally changed how we survey biodiversity on earth. High‐throughput sequencing (“HTS”) platforms now enable the rapid sequencing ofDNAfrom diverse kinds of environmental samples (termed “environmentalDNA” or “eDNA”). CouplingHTSwith our ability to associate sequences fromeDNAwith a taxonomic name is called “eDNAmetabarcoding” and offers a powerful molecular tool capable of noninvasively surveying species richness from many ecosystems. Here, we review the use ofeDNAmetabarcoding for surveying animal and plant richness, and the challenges in usingeDNAapproaches to estimate relative abundance. We highlighteDNAapplications in freshwater, marine and terrestrial environments, and in this broad context, we distill what is known about the ability of differenteDNAsample types to approximate richness in space and across time. We provide guiding questions for study design and discuss theeDNAmetabarcoding workflow with a focus on primers and library preparation methods. We additionally discuss important criteria for consideration of bioinformatic filtering of data sets, with recommendations for increasing transparency. Finally, looking to the future, we discuss emerging applications ofeDNAmetabarcoding in ecology, conservation, invasion biology, biomonitoring, and howeDNAmetabarcoding can empower citizen science and biodiversity education.

     
    more » « less
  2. Raza, Mudassar (Ed.)
    Cosegmentation is a newly emerging computer vision technique used to segment an object from the background by processing multiple images at the same time. Traditional plant phenotyping analysis uses thresholding segmentation methods which result in high segmentation accuracy. Although there are proposed machine learning and deep learning algorithms for plant segmentation, predictions rely on the specific features being present in the training set. The need for a multi-featured dataset and analytics for cosegmentation becomes critical to better understand and predict plants’ responses to the environment. High-throughput phenotyping produces an abundance of data that can be leveraged to improve segmentation accuracy and plant phenotyping. This paper introduces four datasets consisting of two plant species, Buckwheat and Sunflower, each split into control and drought conditions. Each dataset has three modalities (Fluorescence, Infrared, and Visible) with 7 to 14 temporal images that are collected in a high-throughput facility at the University of Nebraska-Lincoln. The four datasets (which will be collected under the CosegPP data repository in this paper) are evaluated using three cosegmentation algorithms: Markov random fields-based, Clustering-based, and Deep learning-based cosegmentation, and one commonly used segmentation approach in plant phenotyping. The integration of CosegPP with advanced cosegmentation methods will be the latest benchmark in comparing segmentation accuracy and finding areas of improvement for cosegmentation methodology. 
    more » « less
  3. Remote health monitoring is a powerful tool to provide preventive care and early intervention for populations-at-risk. Such monitoring systems are becoming available nowadays due to recent advancements in Internet-of-Things (IoT) paradigms, enabling ubiquitous monitoring. These systems require a high level of quality in attributes such as availability and accuracy due to patients critical conditions in the monitoring. Deep learning methods are very promising in such health applications to obtain a satisfactory performance, where a considerable amount of data is available. These methods are perfectly positioned in the cloud servers in a centralized cloud-based IoT system. However, the response time and availability of these systems highly depend on the quality of Internet connection. On the other hand, smart gateway devices are unable to implement deep learning methods (such as training models) due to their limited computational capacities. In our previous work, we proposed a hierarchical computing architecture (HiCH), where both edge and cloud computing resources were efficiently exploited, allocating heavy tasks of a conventional machine learning method to the cloud servers and outsourcing the hypothesis function to the edge. Due to this local decision making, the availability of the system was highly improved. In this paper, we investigate the feasibility of deploying the Convolutional Neural Network (CNN) based classification model as an example of deep learning methods in this architecture. Therefore, the system benefits from the features of the HiCH and the CNN, ensuring a high-level availability and accuracy. We demonstrate a real-time health monitoring for a case study on ECG classifications and evaluate the performance of the system in terms of response time and accuracy. 
    more » « less
  4. SUMMARY

    High‐throughput phenotyping systems are powerful, dramatically changing our ability to document, measure, and detect biological phenomena. Here, we describe a cost‐effective combination of a custom‐built imaging platform and deep‐learning‐based computer vision pipeline. A minimal version of the maize (Zea mays) ear scanner was built with low‐cost and readily available parts. The scanner rotates a maize ear while a digital camera captures a video of the surface of the ear, which is then digitally flattened into a two‐dimensional projection. Segregating GFP and anthocyanin kernel phenotypes are clearly distinguishable in ear projections and can be manually annotated and analyzed using image analysis software. Increased throughput was attained by designing and implementing an automated kernel counting system using transfer learning and a deep learning object detection model. The computer vision model was able to rapidly assess over 390 000 kernels, identifying male‐specific transmission defects across a wide range of GFP‐marked mutant alleles. This includes a previously undescribed defect putatively associated with mutation of Zm00001d002824, a gene predicted to encode a vacuolar processing enzyme. Thus, by using this system, the quantification of transmission data and other ear and kernel phenotypes can be accelerated and scaled to generate large datasets for robust analyses.

     
    more » « less
  5. Proximal remote sensing offers a powerful tool for high-throughput phenotyping of plants for assessing stress response. Bean plants, an important legume for human consumption, are often grown in regions with limited rainfall and irrigation and are therefore bred to further enhance drought tolerance. We assessed physiological (stomatal conductance and predawn and midday leaf water potential) and ground- and tower-based hyperspectral remote sensing (400 to 2,400 nm and 400 to 900 nm, respectively) measurements to evaluate drought response in 12 common bean and 4 tepary bean genotypes across 3 field campaigns (1 predrought and 2 post-drought). Hyperspectral data in partial least squares regression models predicted these physiological traits ( R 2 = 0.20 to 0.55; root mean square percent error 16% to 31%). Furthermore, ground-based partial least squares regression models successfully ranked genotypic drought responses similar to the physiologically based ranks. This study demonstrates applications of high-resolution hyperspectral remote sensing for predicting plant traits and phenotyping drought response across genotypes for vegetation monitoring and breeding population screening. 
    more » « less