scholarly journals aradeepopsis: From images to phenotypic traits using deep transfer learning

2020 ◽  
Author(s):  
Patrick Hüther ◽  
Niklas Schandry ◽  
Katharina Jandrasits ◽  
Ilja Bezrukov ◽  
Claude Becker
Keyword(s):  
High Performance ◽  
Developmental Stages ◽  
Leaf Tissue ◽  
Semantic Segmentation ◽  
Plant Phenotyping ◽  
Phenotypic Traits ◽  
Leaf Color ◽  
Phenotypic Data ◽  
Association Analyses ◽  
Gregor Mendel

AbstractLinking 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. aradeepopsis 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, anthocyanin-rich, and senescent. This makes aradeepopsis 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 aradeepopsis 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, aradeepopsis can be used independently of bioinformatics expertise and computing resources. aradeepopsis is available at https://github.com/Gregor-Mendel-Institute/aradeepopsis.

scholarly journals The Performances of Hyperspectral Sensors for Proximal Sensing of Nitrogen Levels in Wheat

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4550
Author(s):  
Huajian Liu ◽  
Brooke Bruning ◽  
Trevor Garnett ◽  
Bettina Berger
Keyword(s):  
Hyperspectral Imaging ◽  
High Throughput ◽  
Management Practices ◽  
Leaf Tissue ◽  
Plant Phenotyping ◽  
Proximal Sensing ◽  
N Content ◽  
Hyperspectral Sensors ◽  
Wheat Leaves ◽  
Non Destructive

The accurate and high throughput quantification of nitrogen (N) content in wheat using non-destructive methods is an important step towards identifying wheat lines with high nitrogen use efficiency and informing agronomic management practices. Among various plant phenotyping methods, hyperspectral sensing has shown promise in providing accurate measurements in a fast and non-destructive manner. Past applications have utilised non-imaging instruments, such as spectrometers, while more recent approaches have expanded to hyperspectral cameras operating in different wavelength ranges and at various spectral resolutions. However, despite the success of previous hyperspectral applications, some important research questions regarding hyperspectral sensors with different wavelength centres and bandwidths remain unanswered, limiting wide application of this technology. This study evaluated the capability of hyperspectral imaging and non-imaging sensors to estimate N content in wheat leaves by comparing three hyperspectral cameras and a non-imaging spectrometer. This study answered the following questions: (1) How do hyperspectral sensors with different system setups perform when conducting proximal sensing of N in wheat leaves and what aspects have to be considered for optimal results? (2) What types of photonic detectors are most sensitive to N in wheat leaves? (3) How do the spectral resolutions of different instruments affect N measurement in wheat leaves? (4) What are the key-wavelengths with the highest correlation to N in wheat? Our study demonstrated that hyperspectral imaging systems with satisfactory system setups can be used to conduct proximal sensing of N content in wheat with sufficient accuracy. The proposed approach could reduce the need for chemical analysis of leaf tissue and lead to high-throughput estimation of N in wheat. The methodologies here could also be validated on other plants with different characteristics. The results can provide a reference for users wishing to measure N content at either plant- or leaf-scales using hyperspectral sensors.

scholarly journals Opportunities and limits of controlled-environment plant phenotyping for climate response traits

2021 ◽  
Author(s):  
Anna Langstroff ◽  
Marc C. Heuermann ◽  
Andreas Stahl ◽  
Astrid Junker
Keyword(s):  
Crop Production ◽  
Field Trials ◽  
Plant Phenotyping ◽  
Controlled Environment ◽  
Climate Response ◽  
Negative Effects ◽  
Phenotypic Data ◽  
Non Invasive ◽  
Controlled Environments ◽  
Response Traits

AbstractRising temperatures and changing precipitation patterns will affect agricultural production substantially, exposing crops to extended and more intense periods of stress. Therefore, breeding of varieties adapted to the constantly changing conditions is pivotal to enable a quantitatively and qualitatively adequate crop production despite the negative effects of climate change. As it is not yet possible to select for adaptation to future climate scenarios in the field, simulations of future conditions in controlled-environment (CE) phenotyping facilities contribute to the understanding of the plant response to special stress conditions and help breeders to select ideal genotypes which cope with future conditions. CE phenotyping facilities enable the collection of traits that are not easy to measure under field conditions and the assessment of a plant‘s phenotype under repeatable, clearly defined environmental conditions using automated, non-invasive, high-throughput methods. However, extrapolation and translation of results obtained under controlled environments to field environments is ambiguous. This review outlines the opportunities and challenges of phenotyping approaches under controlled environments complementary to conventional field trials. It gives an overview on general principles and introduces existing phenotyping facilities that take up the challenge of obtaining reliable and robust phenotypic data on climate response traits to support breeding of climate-adapted crops.

scholarly journals EasyIDP: A Python Package for Intermediate Data Processing in UAV-Based Plant Phenotyping

2021 ◽  
Vol 13 (13) ◽  
pp. 2622
Author(s):  
Haozhou Wang ◽  
Yulin Duan ◽  
Yun Shi ◽  
Yoichiro Kato ◽  
Seish Ninomiya ◽  
...  
Keyword(s):  
Data Processing ◽  
Plant Phenotyping ◽  
Phenotypic Traits ◽  
Data Annotation ◽  
Intermediate Data ◽  
Reconstruction Quality ◽  
Open Source Software Package ◽  
Machine Learning Applications ◽  
Data Processor ◽  
Uav Images

Unmanned aerial vehicle (UAV) and structure from motion (SfM) photogrammetry techniques are widely used for field-based, high-throughput plant phenotyping nowadays, but some of the intermediate processes throughout the workflow remain manual. For example, geographic information system (GIS) software is used to manually assess the 2D/3D field reconstruction quality and cropping region of interests (ROIs) from the whole field. In addition, extracting phenotypic traits from raw UAV images is more competitive than directly from the digital orthomosaic (DOM). Currently, no easy-to-use tools are available to implement previous tasks for commonly used commercial SfM software, such as Pix4D and Agisoft Metashape. Hence, an open source software package called easy intermediate data processor (EasyIDP; MIT license) was developed to decrease the workload in intermediate data processing mentioned above. The functions of the proposed package include 1) an ROI cropping module, assisting in reconstruction quality assessment and cropping ROIs from the whole field, and 2) an ROI reversing module, projecting ROIs to relative raw images. The result showed that both cropping and reversing modules work as expected. Moreover, the effects of ROI height selection and reversed ROI position on raw images to reverse calculation were discussed. This tool shows great potential for decreasing workload in data annotation for machine learning applications.

scholarly journals Research on Distance Transform and Neural Network Lidar Information Sampling Classification-Based Semantic Segmentation of 2D Indoor Room Maps

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1365
Author(s):  
Tao Zheng ◽  
Zhizhao Duan ◽  
Jin Wang ◽  
Guodong Lu ◽  
Shengjie Li ◽  
...  
Keyword(s):  
Neural Network ◽  
High Speed ◽  
High Performance ◽  
High Efficiency ◽  
Semantic Segmentation ◽  
Raspberry Pi ◽  
Distance Transform ◽  
Testing Stage ◽  
Sampling Points ◽  
Information Sampling

Semantic segmentation of room maps is an essential issue in mobile robots’ execution of tasks. In this work, a new approach to obtain the semantic labels of 2D lidar room maps by combining distance transform watershed-based pre-segmentation and a skillfully designed neural network lidar information sampling classification is proposed. In order to label the room maps with high efficiency, high precision and high speed, we have designed a low-power and high-performance method, which can be deployed on low computing power Raspberry Pi devices. In the training stage, a lidar is simulated to collect the lidar detection line maps of each point in the manually labelled map, and then we use these line maps and the corresponding labels to train the designed neural network. In the testing stage, the new map is first pre-segmented into simple cells with the distance transformation watershed method, then we classify the lidar detection line maps with the trained neural network. The optimized areas of sparse sampling points are proposed by using the result of distance transform generated in the pre-segmentation process to prevent the sampling points selected in the boundary regions from influencing the results of semantic labeling. A prototype mobile robot was developed to verify the proposed method, the feasibility, validity, robustness and high efficiency were verified by a series of tests. The proposed method achieved higher scores in its recall, precision. Specifically, the mean recall is 0.965, and mean precision is 0.943.

scholarly journals Supervised Domain Adaptation for Automated Semantic Segmentation of the Atrial Cavity

Entropy ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. 898
Author(s):  
Marta Saiz-Vivó ◽  
Adrián Colomer ◽  
Carles Fonfría ◽  
Luis Martí-Bonmatí ◽  
Valery Naranjo
Keyword(s):  
High Performance ◽  
Computational Models ◽  
Domain Adaptation ◽  
Semantic Segmentation ◽  
Patient Specific ◽  
Mr Images ◽  
Training Samples ◽  
Volumetric Images ◽  
Acquisition Costs ◽  
Left And Right

Atrial fibrillation (AF) is the most common cardiac arrhythmia. At present, cardiac ablation is the main treatment procedure for AF. To guide and plan this procedure, it is essential for clinicians to obtain patient-specific 3D geometrical models of the atria. For this, there is an interest in automatic image segmentation algorithms, such as deep learning (DL) methods, as opposed to manual segmentation, an error-prone and time-consuming method. However, to optimize DL algorithms, many annotated examples are required, increasing acquisition costs. The aim of this work is to develop automatic and high-performance computational models for left and right atrium (LA and RA) segmentation from a few labelled MRI volumetric images with a 3D Dual U-Net algorithm. For this, a supervised domain adaptation (SDA) method is introduced to infer knowledge from late gadolinium enhanced (LGE) MRI volumetric training samples (80 LA annotated samples) to a network trained with balanced steady-state free precession (bSSFP) MR images of limited number of annotations (19 RA and LA annotated samples). The resulting knowledge-transferred model SDA outperformed the same network trained from scratch in both RA (Dice equals 0.9160) and LA (Dice equals 0.8813) segmentation tasks.

scholarly journals Phenotyping plants: genes, phenes and machines

2012 ◽  
Vol 39 (11) ◽  
pp. 813 ◽  
Author(s):  
Roland Pieruschka ◽  
Hendrik Poorter
Keyword(s):  
Structural Information ◽  
Plant Phenotyping ◽  
Phenotypic Traits ◽  
Special Issue ◽  
Non Invasive ◽  
The Core ◽  
The Relationship ◽  
Non Destructive ◽  
Major Progress ◽  
Meaningful Data

No matter how fascinating the discoveries in the field of molecular biology are, in the end it is the phenotype that matters. In this paper we pay attention to various aspects of plant phenotyping. The challenges to unravel the relationship between genotype and phenotype are discussed, as well as the case where ‘plants do not have a phenotype’. More emphasis has to be placed on automation to match the increased output in the molecular sciences with analysis of relevant traits under laboratory, greenhouse and field conditions. Currently, non-destructive measurements with cameras are becoming widely used to assess plant structural properties, but a wider range of non-invasive approaches and evaluation tools has to be developed to combine physiologically meaningful data with structural information of plants. Another field requiring major progress is the handling and processing of data. A better e-infrastructure will enable easier establishment of links between phenotypic traits and genetic data. In the final part of this paper we briefly introduce the range of contributions that form the core of a special issue of this journal on plant phenotyping.

A Hyperspectral Library of Foliar Diseases of Wheat

2021 ◽  
Author(s):  
David Bohnenkamp ◽  
Jan Behmann ◽  
Stefan Paulus ◽  
Ulrike Steiner ◽  
Anne-Katrin Mahlein
Keyword(s):  
Developmental Stages ◽  
Leaf Tissue ◽  
Plant Diseases ◽  
Identification System ◽  
Spectral Library ◽  
Foliar Diseases ◽  
Robust Detection ◽  
Analysis Methods ◽  
Detection And Identification ◽  
Biotrophic Fungi

This work established a hyperspectral library of important foliar diseases of wheat in time series to detect spectral changes from infection to symptom appearance induced by different pathogens. The data was generated under controlled conditions at the leaf-scale. The transition from healthy to diseased leaf tissue was assessed, spectral shifts were identified and used in combination with histological investigations to define developmental stages in pathogenesis for each disease. The spectral signatures of each plant disease that are indicative of a certain developmental stage during pathogenesis - defined as turning points - were combined into a spectral library. Different machine learning analysis methods were applied and compared to test the potential of this library for the detection and quantification of foliar diseases in hyperspectral images. All evaluated classifiers provided a high accuracy for the detection and identification for both the biotrophic fungi and the necrotrophic fungi of up to 99%. The potential of applying spectral analysis methods, in combination with a spectral library for the detection and identification of plant diseases is demonstrated. Further evaluation and development of these algorithms should contribute to a robust detection and identification system for plant diseases at different developmental stages and the promotion and development of site-specific management techniques of plant diseases under field conditions.

scholarly journals Genetic control of agronomic traits in an oat population of recombinant lines

2010 ◽  
Vol 10 (4) ◽  
pp. 305-311 ◽  
Author(s):  
Itamar Cristiano Nava ◽  
Ismael Tiago de Lima Duarte ◽  
Marcelo Teixeira Pacheco ◽  
Luiz Carlos Federizzi
Keyword(s):  
Grain Yield ◽  
Genetic Control ◽  
Plant Height ◽  
Agronomic Traits ◽  
Test Weight ◽  
Phenotypic Traits ◽  
Phenotypic Data ◽  
Plant Growth Habit ◽  
Vegetative Cycle ◽  
Efficiency Of Selection

Understanding the genetic control of phenotypic traits is essential to increase the efficiency of selection for adapted, high-yielding genotypes. The purpose of this study was to determine the genetic control of nine traits of hexaploid oat. Phenotypic data were collected from a population of 162 recombinant lines derived from the cross 'UFRGS17 x UFRGS 930598-6'. For the traits plant growth habit, hairs on leaf edges and panicle type, monogenic genetic control was observed. A quantitative and/or polygenic genetic control was stated for the traits panicle weight, panicle length, vegetative cycle, plant height, test weight and grain yield. High heritability was estimated for the traits vegetative cycle (h² = 0.89) and plant height (h² = 0.79), while moderate heritability was determined for test weight (h² = 0.51) and grain yield (h² = 0.48).

scholarly journals L-DOPA Trends in Different Tissues at Early Stages of Vicia faba Growth: Effect of Tyrosine Treatment

2018 ◽  
Vol 8 (12) ◽  
pp. 2431 ◽  
Author(s):  
Claudia Oviedo-Silva ◽  
Mhartyn Elso-Freudenberg ◽  
Mario Aranda-Bustos
Keyword(s):  
Amino Acid ◽  
Vicia Faba ◽  
High Performance ◽  
Developmental Stages ◽  
Growth Effect ◽  
Guaiacol Peroxidase ◽  
Nonprotein Amino Acid ◽  
Early Seedling ◽  
Gpx Activity ◽  
Different Tissues

The nonprotein amino acid Levo-3,4-dihydroxyphenylalanine (L-DOPA) has insecticidal, allelochemical, and antiparkinsonian effects. The aim of this research was to assess L-DOPA content in different tissues of Vicia faba (cv. Super Agua Dulce), and to verify if treatment with the phenolic amino acid L-4-hydroxyphenylalanine (tyrosine) had an effect on such content. Under light germination, control and tyrosine-treated early seedling stages of V. faba were studied and L-DOPA was quantified spectrophotometrically (Arnow’s method) and by high-performance thin-layer chromatography (HPTLC), as well. Additionally, tyrosinase (TYROX) and guaiacol peroxidase (GPX) activities (considered markers of a phenolic compounds metabolism) were quantified as germination proceeded. Different organs (roots, sprouts, and seeds) and different developmental stages were considered. Steady high L-DOPA concentrations were found in untreated sprouts and roots compared to seeds, as time progressed. While TYROX activity was not detected in these experiments, GPX had diverse trends. In control tissues, GPX increased in seed tissue as germination progressed, whereas in roots and sprouts, a decreasing GPX activity was observed. Tyrosine exposure decreased L-DOPA content, and decreased or did not change GPX activity (depending on the organ). Both Arnow’s and HPTLC methods were consistent in terms of tendencies, except for the scarce contents found in seeds, in which HPTLC was more sensitive. The richest source of L-DOPA was found in shoots (untreated), reaching as high as 125 mg g−1 DW (12% in DW) (the highest content reported in fava bean seedlings until now), whereas the smallest L-DOPA content was found in seeds. The importance of light germination conditions is discussed in terms of L-DOPA yield and from a physiological perspective. It is concluded that V. faba (cv. Super Agua Dulce) shoots are a good source of L-DOPA and that tyrosine addition (0.55 mM) decreases L-DOPA content in actively growing tissues (shoots and roots).

Genetic diversity among Italian melon inodorus (Cucumis melo L.) germplasm revealed by ISSR analysis and agronomic traits

2011 ◽  
Vol 9 (2) ◽  
pp. 214-217 ◽  
Author(s):  
S. Sestili ◽  
A. Giardini ◽  
N. Ficcadenti
Keyword(s):  
Agronomic Traits ◽  
Genetic Relationships ◽  
Molecular Data ◽  
Inter Simple Sequence Repeat ◽  
Phenotypic Traits ◽  
Phenotypic Data ◽  
Morphological And Molecular Data ◽  
And Cluster Analysis ◽  
Almost All ◽  
Issr Primers

The genetic relationships among 13 melon inodorus populations that were collected in southern Italy were assessed using 100 inter-simple-sequence repeat (ISSR) primers and 15 morphological traits. The dihaploid line Nad-1 and the cultivar Charentais-T, both of which belong to the botanical variety cantalupensis, were used as reference accessions in the molecular analysis. A total of 358 polymorphic bands were obtained from 39 of the 100 ISSR primers used, and 15 phenotypic traits were scored and used for genetic-similarity calculations and cluster analysis. The resulting dendrograms based on the ISSR and phenotypic data allowed almost all of the melon genotypes to be distinguished on the basis of the skin colour of the fruits. Mantel's test revealed a good correlation between the morphological and molecular data in their ability to detect genetic relationships among melon ecotypes (r = 0.50, P = 0.99). The data obtained confirm the effectiveness of this approach, and open new perspectives to reveal possible molecular associations with the phenotypic traits analysed.

Sign in / Sign up

Export Citation Format

Share Document