High-throughput method for ear phenotyping and kernel weight estimation in maize using ear digital imaging

Digital techniques and trends for seed phenotyping using optical sensors

BACKGROUND

The breeding of high-quality, high-yield, and disease-resistant varieties is closely related to food security. The investigation of breeding results relies on the evaluation of seed phenotype, which is a key step in the process of breeding. In the global digitalization trend, digital technology based on optical sensors can perform the digitization of seed phenotype in a non-contact, high throughput way, thus significantly improving breeding efficiency.

AIM OF REVIEW

This paper provides a comprehensive overview of the principles, characteristics, data processing methods, and bottlenecks associated with three digital technique types based on optical sensors: spectroscopy, digital imaging, and three-dimensional (3D) reconstruction techniques. In addition, the applicability and adaptability of digital techniques based on the optical sensors of maize seed phenotype traits, namely external visible phenotype (EVP) and internal invisible phenotype (IIP), are investigated. Furthermore, trends in future equipment, platform, phenotype data, and processing algorithms are discussed. This review offers conceptual and practical support for seed phenotype digitization based on optical sensors, which will provide reference and guidance for future research.

KEY SCIENTIFIC CONCEPTS OF REVIEW

The digital techniques based on optical sensors can perform non-contact and high-throughput seed phenotype evaluation. Due to the distinct characteristics of optical sensors, matching suitable digital techniques according to seed phenotype traits can greatly reduce resource loss, and promote the efficiency of seed evaluation as well as breeding decision-making. Future research in phenotype equipment and platform, phenotype data, and processing algorithms will make digital techniques better meet the demands of seed phenotype evaluation, and promote automatic, integrated, and intelligent evaluation of seed phenotype, further helping to lessen the gap between digital techniques and seed phenotyping.

Genetic resources and breeding of maize for Striga resistance: a review

The potential yield of maize (Zea mays L.) and other major crops is curtailed by several biotic, abiotic, and socio-economic constraints. Parasitic weeds, Striga spp., are major constraints to cereal and legume crop production in sub-Saharan Africa (SSA). Yield losses reaching 100% are reported in maize under severe Striga infestation. Breeding for Striga resistance has been shown to be the most economical, feasible, and sustainable approach for resource-poor farmers and for being environmentally friendly. Knowledge of the genetic and genomic resources and components of Striga resistance is vital to guide genetic analysis and precision breeding of maize varieties with desirable product profiles under Striga infestation. This review aims to present the genetic and genomic resources, research progress, and opportunities in the genetic analysis of Striga resistance and yield components in maize for breeding. The paper outlines the vital genetic resources of maize for Striga resistance, including landraces, wild relatives, mutants, and synthetic varieties, followed by breeding technologies and genomic resources. Integrating conventional breeding, mutation breeding, and genomic-assisted breeding [i.e., marker-assisted selection, quantitative trait loci (QTL) analysis, next-generation sequencing, and genome editing] will enhance genetic gains in Striga resistance breeding programs. This review may guide new variety designs for Striga-resistance and desirable product profiles in maize.

Identifying yield-related genes in maize based on ear trait plasticity

BACKGROUND

Phenotypic plasticity is defined as the phenotypic variation of a trait when an organism is exposed to different environments, and it is closely related to genotype. Exploring the genetic basis behind the phenotypic plasticity of ear traits in maize is critical to achieve climate-stable yields, particularly given the unpredictable effects of climate change. Performing genetic field studies in maize requires development of a fast, reliable, and automated system for phenotyping large numbers of samples.

RESULTS

Here, we develop MAIZTRO as an automated maize ear phenotyping platform for high-throughput measurements in the field. Using this platform, we analyze 15 common ear phenotypes and their phenotypic plasticity variation in 3819 transgenic maize inbred lines targeting 717 genes, along with the wild type lines of the same genetic background, in multiple field environments in two consecutive years. Kernel number is chosen as the primary target phenotype because it is a key trait for improving the grain yield and ensuring yield stability. We analyze the phenotypic plasticity of the transgenic lines in different environments and identify 34 candidate genes that may regulate the phenotypic plasticity of kernel number.

CONCLUSIONS

Our results suggest that as an integrated and efficient phenotyping platform for measuring maize ear traits, MAIZTRO can help to explore new traits that are important for improving and stabilizing the yield. This study indicates that genes and alleles related with ear trait plasticity can be identified using transgenic maize inbred populations.

Incorporating male sterility increases hybrid maize yield in low input African farming systems

Maize is a staple crop in sub-Saharan Africa, but yields remain sub-optimal. Improved breeding and seed systems are vital to increase productivity. We describe a hybrid seed production technology that will benefit seed companies and farmers. This technology improves efficiency and integrity of seed production by removing the need for detasseling. The resulting hybrids segregate 1:1 for pollen production, conserving resources for grain production and conferring a 200 kg ha⁻¹ benefit across a range of yield levels. This represents a 10% increase for farmers operating at national average yield levels in sub-Saharan Africa. The yield benefit provided by fifty-percent non-pollen producing hybrids is the first example of a single gene technology in maize conferring a yield increase of this magnitude under low-input smallholder farmer conditions and across an array of hybrid backgrounds. Benefits to seed companies will provide incentives to improve smallholder farmer access to higher quality seed. Demonstrated farmer preference for these hybrids will help drive their adoption.

Seed hybridization technology improves maize yield in African smallholder farming conditions.

Earbox, an open tool for high-throughput measurement of the spatial organization of maize ears and inference of novel traits

BACKGROUND

Characterizing plant genetic resources and their response to the environment through accurate measurement of relevant traits is crucial to genetics and breeding. Spatial organization of the maize ear provides insights into the response of grain yield to environmental conditions. Current automated methods for phenotyping the maize ear do not capture these spatial features.

RESULTS

We developed EARBOX, a low-cost, open-source system for automated phenotyping of maize ears. EARBOX integrates open-source technologies for both software and hardware that facilitate its deployment and improvement for specific research questions. The imaging platform consists of a customized box in which ears are repeatedly imaged as they rotate via motorized rollers. With deep learning based on convolutional neural networks, the image analysis algorithm uses a two-step procedure: ear-specific grain masks are first created and subsequently used to extract a range of trait data per ear, including ear shape and dimensions, the number of grains and their spatial organisation, and the distribution of grain dimensions along the ear. The reliability of each trait was validated against ground-truth data from manual measurements. Moreover, EARBOX derives novel traits, inaccessible through conventional methods, especially the distribution of grain dimensions along grain cohorts, relevant for ear morphogenesis, and the distribution of abortion frequency along the ear, relevant for plant response to stress, especially soil water deficit.

CONCLUSIONS

The proposed system provides robust and accurate measurements of maize ear traits including spatial features. Future developments include grain type and colour categorisation. This method opens avenues for high-throughput genetic or functional studies in the context of plant adaptation to a changing environment.

Genomic Regions Associated With Salinity Stress Tolerance in Tropical Maize (Zea Mays L.)

Being a widely cultivated crop globally under diverse climatic conditions and soil types, maize is often exposed to an array of biotic and abiotic stresses. Soil salinity is one of the challenges for maize cultivation in many parts of lowland tropics that significantly affects crop growth and reduces economic yields. Breeding strategies integrated with molecular approach might accelerate the process of identifying and developing salinity-tolerant maize cultivars. In this study, an association mapping panel consisting of 305 diverse maize inbred lines was phenotyped in a managed salinity stress phenotyping facility at International Center for Biosaline Agriculture (ICBA), Dubai, United Arab Emirates (UAE). Wide genotypic variability was observed in the panel under salinity stress for key phenotypic traits viz., grain yield, days to anthesis, anthesis-silking interval, plant height, cob length, cob girth, and kernel number. The panel was genotyped following the genome-based sequencing approach to generate 955,690 SNPs. Total SNPs were filtered to 213,043 at a call rate of 0.85 and minor allele frequency of 0.05 for association analysis. A total of 259 highly significant (P ≤ 1 × 10^-5) marker-trait associations (MTAs) were identified for seven phenotypic traits. The phenotypic variance for MTAs ranged between 5.2 and 9%. A total of 64 associations were found in 19 unique putative gene expression regions. Among them, 12 associations were found in gene models with stress-related biological functions.

Integrating Genomic and Phenomic Approaches to Support Plant Genetic Resources Conservation and Use

Plant genebanks provide genetic resources for breeding and research programs worldwide. These programs benefit from having access to high-quality, standardized phenotypic and genotypic data. Technological advances have made it possible to collect phenomic and genomic data for genebank collections, which, with the appropriate analytical tools, can directly inform breeding programs. We discuss the importance of considering genebank accession homogeneity and heterogeneity in data collection and documentation. Citing specific examples, we describe how well-documented genomic and phenomic data have met or could meet the needs of plant genetic resource managers and users. We explore future opportunities that may emerge from improved documentation and data integration among plant genetic resource information systems.

DeepCob: precise and high-throughput analysis of maize cob geometry using deep learning with an application in genebank phenomics

BACKGROUND

Maize cobs are an important component of crop yield that exhibit a high diversity in size, shape and color in native landraces and modern varieties. Various phenotyping approaches were developed to measure maize cob parameters in a high throughput fashion. More recently, deep learning methods like convolutional neural networks (CNNs) became available and were shown to be highly useful for high-throughput plant phenotyping. We aimed at comparing classical image segmentation with deep learning methods for maize cob image segmentation and phenotyping using a large image dataset of native maize landrace diversity from Peru.

RESULTS

Comparison of three image analysis methods showed that a Mask R-CNN trained on a diverse set of maize cob images was highly superior to classical image analysis using the Felzenszwalb-Huttenlocher algorithm and a Window-based CNN due to its robustness to image quality and object segmentation accuracy ([Formula: see text]). We integrated Mask R-CNN into a high-throughput pipeline to segment both maize cobs and rulers in images and perform an automated quantitative analysis of eight phenotypic traits, including diameter, length, ellipticity, asymmetry, aspect ratio and average values of red, green and blue color channels for cob color. Statistical analysis identified key training parameters for efficient iterative model updating. We also show that a small number of 10-20 images is sufficient to update the initial Mask R-CNN model to process new types of cob images. To demonstrate an application of the pipeline we analyzed phenotypic variation in 19,867 maize cobs extracted from 3449 images of 2484 accessions from the maize genebank of Peru to identify phenotypically homogeneous and heterogeneous genebank accessions using multivariate clustering.

CONCLUSIONS

Single Mask R-CNN model and associated analysis pipeline are widely applicable tools for maize cob phenotyping in contexts like genebank phenomics or plant breeding.

Heterotic Patterns of Temperate and Tropical Maize by Ear Photometry

As the plant variety protection (PVP) of commercial inbred lines expire, public breeding programs gain a wealth of genetic materials that have undergone many years of intense selection; however, the value of these inbred lines is only fully realized when they have been well characterized and are used in hybrid combinations. Additionally, while yield is the primary trait by which hybrids are evaluated, new phenotyping technologies, such as ear photometry (EP), may provide an assessment of yield components that can be scaled to breeding programs. The objective of this experiment was to use EP to describe the testcross performance of inbred lines from temperate and tropical origins. We evaluated the performance of 298 public and ex-PVP inbred lines and 274 Drought Tolerant Maize for Africa (DTMA) inbred lines when crossed to Iodent (PHP02) and/or Stiff Stalk (2FACC) testers for 25 yield-related traits. Kernel weight, kernels per ear, and grain yield predicted by EP were correlated with their reference traits with r = 0.49, r = 0.88, and r = 0.75, respectively. The testcross performance of each maize inbred line was tester dependent. When lines were crossed to a tester within the heterotic group, many yield components related to ear size and kernels per ear were significantly reduced, but kernel size was rarely impacted. Thus, the effect of heterosis was more noticeable on traits that increased kernels per ear rather than kernel size. Hybrids of DTMA inbred lines crossed to PHP02 exhibited phenotypes similar to testcrosses of Stiff Stalk and Non-Stiff Stalk heterotic groups for yield due to significant increases in kernel size to compensate for a reduction in kernels per ear. Kernels per ear and ear length were correlated (r = 0.89 and r = 0.84, respectively) with and more heritable than yield, suggesting these traits could be useful for inbred selection.

Beat the stress: breeding for climate resilience in maize for the tropical rainfed environments

Intensive public sector breeding efforts and public-private partnerships have led to the increase in genetic gains, and deployment of elite climate-resilient maize cultivars for the stress-prone environments in the tropics. Maize (Zea mays L.) plays a critical role in ensuring food and nutritional security, and livelihoods of millions of resource-constrained smallholders. However, maize yields in the tropical rainfed environments are now increasingly vulnerable to various climate-induced stresses, especially drought, heat, waterlogging, salinity, cold, diseases, and insect pests, which often come in combinations to severely impact maize crops. The International Maize and Wheat Improvement Center (CIMMYT), in partnership with several public and private sector institutions, has been intensively engaged over the last four decades in breeding elite tropical maize germplasm with tolerance to key abiotic and biotic stresses, using an extensive managed stress screening network and on-farm testing system. This has led to the successful development and deployment of an array of elite stress-tolerant maize cultivars across sub-Saharan Africa, Asia, and Latin America. Further increasing genetic gains in the tropical maize breeding programs demands judicious integration of doubled haploidy, high-throughput and precise phenotyping, genomics-assisted breeding, breeding data management, and more effective decision support tools. Multi-institutional efforts, especially public-private alliances, are key to ensure that the improved maize varieties effectively reach the climate-vulnerable farming communities in the tropics, including accelerated replacement of old/obsolete varieties.

Scaling up high-throughput phenotyping for abiotic stress selection in the field

High-throughput phenotyping (HTP) is in its infancy for deployment in large-scale breeding programmes. With the ability to measure correlated traits associated with physiological ideotypes, in-field phenotyping methods are available for screening of abiotic stress responses. As cropping environments become more hostile and unpredictable due to the effects of climate change, the need to characterise variability across spatial and temporal scales will become increasingly important. The sensor technologies that have enabled HTP from macroscopic through to satellite sensors may also be utilised here to complement spatial characterisation using envirotyping, which can improve estimations of genotypic performance across environments by better accounting for variation at the plot, trial and inter-trial levels. Climate change is leading to increased variation at all physical and temporal scales in the cropping environment. Maintaining yield stability under circumstances with greater levels of abiotic stress while capitalising upon yield potential in good years, requires approaches to plant breeding that target the physiological limitations to crop performance in specific environments. This requires dynamic modelling of conditions within target populations of environments, GxExM predictions, clustering of environments so breeding trajectories can be defined, and the development of screens that enable selection for genetic gain to occur. High-throughput phenotyping (HTP), combined with related technologies used for envirotyping, can help to address these challenges. Non-destructive analysis of the morphological, biochemical and physiological qualities of plant canopies using HTP has great potential to complement whole-genome selection, which is becoming increasingly common in breeding programmes. A range of novel analytic techniques, such as machine learning and deep learning, combined with a widening range of sensors, allow rapid assessment of large breeding populations that are repeatable and objective. Secondary traits underlying radiation use efficiency and water use efficiency can be screened with HTP for selection at the early stages of a breeding programme. HTP and envirotyping technologies can also characterise spatial variability at trial and within-plot levels, which can be used to correct for spatial variations that confound measurements of genotypic values. This review explores HTP for abiotic stress selection through a physiological trait lens and additionally investigates the use of envirotyping and EC to characterise spatial variability at all physical scales in METs.

A cost-effective maize ear phenotyping platform enables rapid categorization and quantification of kernels

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.

A cost-effective maize ear phenotyping platform enables rapid categorization and quantification of kernels

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.

Maize Kernel Abortion Recognition and Classification Using Binary Classification Machine Learning Algorithms and Deep Convolutional Neural Networks

Maize kernel traits such as kernel length, kernel width, and kernel number determine the total kernel weight and, consequently, maize yield. Therefore, the measurement of kernel traits is important for maize breeding and the evaluation of maize yield. There are a few methods that allow the extraction of ear and kernel features through image processing. We evaluated the potential of deep convolutional neural networks and binary machine learning (ML) algorithms (logistic regression (LR), support vector machine (SVM), AdaBoost (ADB), Classification tree (CART), and the K-Neighbor (kNN)) for accurate maize kernel abortion detection and classification. The algorithms were trained using 75% of 66 total images, and the remaining 25% was used for testing their performance. Confusion matrix, classification accuracy, and precision were the major metrics in evaluating the performance of the algorithms. The SVM and LR algorithms were highly accurate and precise (100%) under all the abortion statuses, while the remaining algorithms had a performance greater than 95%. Deep convolutional neural networks were further evaluated using different activation and optimization techniques. The best performance (100% accuracy) was reached using the rectifier linear unit (ReLu) activation procedure and the Adam optimization technique. Maize ear with abortion were accurately detected by all tested algorithms with minimum training and testing time compared to ear without abortion. The findings suggest that deep convolutional neural networks can be used to detect the maize ear abortion status supplemented with the binary machine learning algorithms in maize breading programs. By using a convolution neural network (CNN) method, more data (big data) can be collected and processed for hundreds of maize ears, accelerating the phenotyping process.

Genebank Phenomics: A Strategic Approach to Enhance Value and Utilization of Crop Germplasm

Genetically diverse plant germplasm stored in ex-situ genebanks are excellent resources for breeding new high yielding and sustainable crop varieties to ensure future food security. Novel alleles have been discovered through routine genebank activities such as seed regeneration and characterization, with subsequent utilization providing significant genetic gains and improvements for the selection of favorable traits, including yield, biotic, and abiotic resistance. Although some genebanks have implemented cost-effective genotyping technologies through advances in DNA technology, the adoption of modern phenotyping is lagging. The introduction of advanced phenotyping technologies in recent decades has provided genebank scientists with time and cost-effective screening tools to obtain valuable phenotypic data for more traits on large germplasm collections during routine activities. The utilization of these phenotyping tools, coupled with high-throughput genotyping, will accelerate the use of genetic resources and fast-track the development of more resilient food crops for the future. In this review, we highlight current digital phenotyping methods that can capture traits during annual seed regeneration to enrich genebank phenotypic datasets. Next, we describe strategies for the collection and use of phenotypic data of specific traits for downstream research using high-throughput phenotyping technology. Finally, we examine the challenges and future perspectives of genebank phenomics.

Automatic kernel counting on maize ear using RGB images

BACKGROUND

The number of kernels per ear is one of the major agronomic yield indicators for maize. Manual assessment of kernel traits can be time consuming and laborious. Moreover, manually acquired data can be influenced by subjective bias of the observer. Existing methods for counting of kernel number are often unstable and costly. Machine vision technology allows objective extraction of features from image sensor data, offering high-throughput and low-cost advantages.

RESULTS

Here, we propose an automatic kernel recognition method which has been applied to count the kernel number based on digital colour photos of the maize ears. Images were acquired under both LED diffuse (indoors) and natural light (outdoor) conditions. Field trials were carried out at two sites in China using 8 maize varieties. This method comprises five steps: (1) a Gaussian Pyramid for image compression to improve the processing efficiency, (2) separating the maize fruit from the background by Mean Shift Filtering algorithm, (3) a Colour Deconvolution (CD) algorithm to enhance the kernel edges, (4) segmentation of kernel zones using a local adaptive threshold, (5) an improved Find-Local-Maxima to recognize the local grayscale peaks and determine the maize kernel number within the image. The results showed good agreement (> 93%) in terms of accuracy and precision between ground truth (manual counting) and the image-based counting.

CONCLUSIONS

The proposed algorithm has robust and superior performance in maize ear kernel counting under various illumination conditions. In addition, the approach is highly-efficient and low-cost. The performance of this method makes it applicable and satisfactory for real-world breeding programs.

The Senescence (Stay-Green)—An Important Trait to Exploit Crop Residuals for Bioenergy

In this review, we present a comprehensive revisit of past research and advances developed on the stay-green (SG) paradigm. The study aims to provide an application-focused review of the SG phenotypes as crop residuals for bioenergy. Little is known about the SG trait as a germplasm enhancer resource for energy storage as a system for alternative energy. Initially described as a single locus recessive trait, SG was shortly after reported as a quantitative trait governed by complex physiological and metabolic networks including chlorophyll efficiency, nitrogen contents, nutrient remobilization and source-sink balance. Together with the fact that phenotyping efforts have improved rapidly in the last decade, new approaches based on sensing technologies have had an impact in SG identification. Since SG is linked to delayed senescence, we present a review of the term senescence applied to crop residuals and bioenergy. Firstly, we discuss the idiosyncrasy of senescence. Secondly, we present biological processes that determine the fate of senescence. Thirdly, we present the genetics underlying SG for crop-trait improvement in different crops. Further, this review explores the potential uses of senescence for bioenergy crops. Finally, we discuss how high-throughput phenotyping methods assist new technologies such as genomic selection in a cost-efficient manner.

Crop Phenomics and High-Throughput Phenotyping: Past Decades, Current Challenges, and Future Perspectives

Since whole-genome sequencing of many crops has been achieved, crop functional genomics studies have stepped into the big-data and high-throughput era. However, acquisition of large-scale phenotypic data has become one of the major bottlenecks hindering crop breeding and functional genomics studies. Nevertheless, recent technological advances provide us potential solutions to relieve this bottleneck and to explore advanced methods for large-scale phenotyping data acquisition and processing in the coming years. In this article, we review the major progress on high-throughput phenotyping in controlled environments and field conditions as well as its use for post-harvest yield and quality assessment in the past decades. We then discuss the latest multi-omics research combining high-throughput phenotyping with genetic studies. Finally, we propose some conceptual challenges and provide our perspectives on how to bridge the phenotype-genotype gap. It is no doubt that accurate high-throughput phenotyping will accelerate plant genetic improvements and promote the next green revolution in crop breeding.

Correction to: High-throughput method for ear phenotyping and kernel weight estimation in maize using ear digital imaging

[This corrects the article DOI: 10.1186/s13007-018-0317-4.].