The Combination of Low-Cost, Red-Green-Blue (RGB) Image Analysis and Machine Learning to Screen for Barley Plant Resistance to Net Blotch.

Challenges of climate change and growth population are exacerbated by noticeable environmental changes, which can increase the range of plant diseases, for instance, net blotch (NB), a foliar disease which significantly decreases barley (Hordeum vulgare L.) grain yield and quality. A resistant germplasm is usually identified through visual observation and the scoring of disease symptoms; however, this is subjective and time-consuming. Thus, automated, non-destructive, and low-cost disease-scoring approaches are highly relevant to barley breeding. This study presents a novel screening method for evaluating NB severity in barley. The proposed method uses an automated RGB imaging system, together with machine learning, to evaluate different symptoms and the severity of NB. The study was performed on three barley cultivars with distinct levels of resistance to NB (resistant, moderately resistant, and susceptible). The tested approach showed mean precision of 99% for various categories of NB severity (chlorotic, necrotic, and fungal lesions, along with leaf tip necrosis). The results demonstrate that the proposed method could be effective in assessing NB from barley leaves and specifying the level of NB severity; this type of information could be pivotal to precise selection for NB resistance in barley breeding.

ScabyNet, a user-friendly application for detecting common scab in potato tubers using deep learning and morphological traits.

Common scab (CS) is a major bacterial disease causing lesions on potato tubers, degrading their appearance and reducing their market value. To accurately grade scab-infected potato tubers, this study introduces "ScabyNet", an image processing approach combining color-morphology analysis with deep learning techniques. ScabyNet estimates tuber quality traits and accurately detects and quantifies CS severity levels from color images. It is presented as a standalone application with a graphical user interface comprising two main modules. One module identifies and separates tubers on images and estimates quality-related morphological features. In addition, it enables the extraction of tubers as standard tiles for the deep-learning module. The deep-learning module detects and quantifies the scab infection into five severity classes related to the relative infected area. The analysis was performed on a dataset of 7154 images of individual tiles collected from field and glasshouse experiments. Combining the two modules yields essential parameters for quality and disease inspection. The first module simplifies imaging by replacing the region proposal step of instance segmentation networks. Furthermore, the approach is an operational tool for an affordable phenotyping system that selects scab-resistant genotypes while maintaining their market standards.

Impacts of heat, drought, and combined heat-drought stress on yield, phenotypic traits, and gluten protein traits: capturing stability of spring wheat in excessive environments.

Wheat production and end-use quality are severely threatened by drought and heat stresses. This study evaluated stress impacts on phenotypic and gluten protein characteristics of eight spring wheat genotypes (Diskett, Happy, Bumble, SW1, SW2, SW3, SW4, and SW5) grown to maturity under controlled conditions (Biotron) using RGB imaging and size-exclusion high-performance liquid chromatography (SE-HPLC). Among the stress treatments compared, combined heat-drought stress had the most severe negative impacts on biomass (real and digital), grain yield, and thousand kernel weight. Conversely, it had a positive effect on most gluten parameters evaluated by SE-HPLC and resulted in a positive correlation between spike traits and gluten strength, expressed as unextractable gluten polymer (%UPP) and large monomeric protein (%LUMP). The best performing genotypes in terms of stability were Happy, Diskett, SW1, and SW2, which should be further explored as attractive breeding material for developing climate-resistant genotypes with improved bread-making quality. RGB imaging in combination with gluten protein screening by SE-HPLC could thus be a valuable approach for identifying climate stress-tolerant wheat genotypes.

Phenotyping Fusarium head blight through seed morphology characteristics using RGB imaging.

Fusarium head blight (FHB) is an economically important disease affecting wheat and thus poses a major threat to wheat production. Several studies have evaluated the effectiveness of image analysis methods to predict FHB using disease-infected grains; however, few have looked at the final application, considering the relationship between cost and benefit, resolution, and accuracy. The conventional screening of FHB resistance of large-scale samples is still dependent on low-throughput visual inspections. This study aims to compare the performance of two cost-benefit seed image analysis methods, the free software "SmartGrain" and the fully automated commercially available instrument "Cgrain Value™" by assessing 16 seed morphological traits of winter wheat to predict FHB. The analysis was carried out on a seed set of FHB which was visually assessed as to the severity. The dataset is composed of 432 winter wheat genotypes that were greenhouse-inoculated. The predictions from each method, in addition to the predictions combined from the results of both methods, were compared with the disease visual scores. The results showed that Cgrain Value™ had a higher prediction accuracy of R 2 = 0.52 compared with SmartGrain for which R 2 = 0.30 for all morphological traits. However, the results combined from both methods showed the greatest prediction performance of R 2 = 0.58. Additionally, a subpart of the morphological traits, namely, width, length, thickness, and color features, showed a higher correlation with the visual scores compared with the other traits. Overall, both methods were related to the visual scores. This study shows that these affordable imaging methods could be effective to predict FHB in seeds and enable us to distinguish minor differences in seed morphology, which could lead to a precise performance selection of disease-free seeds/grains.

Phenocave: An Automated, Standalone, and Affordable Phenotyping System for Controlled Growth Conditions.

Controlled plant growth facilities provide the possibility to alter climate conditions affecting plant growth, such as humidity, temperature, and light, allowing a better understanding of plant responses to abiotic and biotic stresses. A bottleneck, however, is measuring various aspects of plant growth regularly and non-destructively. Although several high-throughput phenotyping facilities have been built worldwide, further development is required for smaller custom-made affordable systems for specific needs. Hence, the main objective of this study was to develop an affordable, standalone and automated phenotyping system called "Phenocave" for controlled growth facilities. The system can be equipped with consumer-grade digital cameras and multispectral cameras for imaging from the top view. The cameras are mounted on a gantry with two linear actuators enabling XY motion, thereby enabling imaging of the entire area of Phenocave. A blueprint for constructing such a system is presented and is evaluated with two case studies using wheat and sugar beet as model plants. The wheat plants were treated with different irrigation regimes or high nitrogen application at different developmental stages affecting their biomass accumulation and growth rate. A significant correlation was observed between conventional measurements and digital biomass at different time points. Post-harvest analysis of grain protein content and composition corresponded well with those of previous studies. The results from the sugar beet study revealed that seed treatment(s) before germination influences germination rates. Phenocave enables automated phenotyping of plants under controlled conditions, and the protocols and results from this study will allow others to build similar systems with dimensions suitable for their custom needs.

El peso de un diagnóstico / The weight of a diagnosis

Introducción: el estado nutricional (EN) infantil requiere adecuada evaluación. Objetivos: Describir el EN de niños de 1-5 años que asistieron a tres centros de atención primaria de una obra social en 2014 y su método de evaluación. Conocer el impacto del diagnóstico en sus familias. Materiales y métodos: Estudio multicéntrico cuali-cuantitativo, n=891. Se revisaron historias clínicas y se entrevistó a padres de niños con diagnóstico de obesidad o bajo peso. Resultados: El 52% de los niños fueron evaluados con percentilos Peso/Edad, hallándose 71% eutrófico, 6% con obesidad, y 4% bajo peso. Utilizando percentilos IMC/Edad, 60% resulto eutrófico, 14 % con obesidad y 1% con bajo peso. En el análisis cualitativo se observaron: naturalización diagnóstico, dificultad de los padres para poner límites, sentimientos de culpa y frustración y déficit en la comunicación médico-familia. Conclusión: El 60% de los niños de 1-5 años que consultaron en tres centros de atención primaria de un obra social en el 2014 resultaron eutróficos, 14% con obesidad y 1% bajo peso. La mayoría de los niños fueron evaluados utilizando percentilos incorrectos. La subestimación del diagnóstico por parte de los padres fue favorecida por el uso de eufemismos y lenguaje diminutivo por parte de los médicos.

Introduction: childhood nutritional status (NS) requires adequate assessment. Objectives: To describe NS of children aged 1-5 that attended three primary care centers of a social security organisation during 2014 and its method of assessment. To know the impact the diagnosis had on their families. Materials and methods: Quali-quantitative multicenter study, n=891. Charts were reviewed and parents of children diagnosed with obesity or low weight were interviewed. Results: 52% of children were assessed using Weight/Age percentiles, being 71% eutrophic, 6% with obesity, and 4% low weight. Using BMI/Age percentiles, 60% were eutrophic, 14% with obesity and 1% with low weight. In the qualitative analysis were observed: naturalization of the diagnosis, parental difficulties in setting limits, feelings of the quilt and frustration, anddeficits in physician-family communication. Conclusion: Using the BMI/Age curve, 60% of the 1-5 year olds who were attended at three primary care centers of a social security organisation in 2014 were eutrophic, 14% were obese and 1% had low weight. Most children were assessed using wrong percentiles. Underestimation of the diagnosis by parents was favored by the use of euphemisms and diminutive language by physicians.

[Child abuse: an interdisciplinary management experience]. / Maltrato infantil: Experiencia de un abordaje interdisciplinario.

INTRODUCTION: Child abuse constitutes one of the most frequent forms of family violence. The following study tries to demonstrate the situation that arises in the city of Mercedes, Corrientes, Argentina, and to establish some associations about that matter. POPULATION, MATERIAL AND METHODS: A series of 128 cases of abused children is presented, between 0 and 19 years old, attended from November 1998 to November 2002, in Moiru, Center of prevention, direction, attendance and qualification in social conducts of risk that works in Mercedes. RESULTS: 56% of physical abuse; 30% of sexual abuse; 10% of neglect; 3% of emotional abuse and 1% of syndrome of Münchaussen was detected, with a similar distribution by sexes in the total population. Demographic variables and certain associations in cases of physical abuse and sexual abuse are indicated. A significant association between mothers victims of domestic violence and physical abuse towards their children was demonstrated. CONCLUSIONS: 128 young boys and girls were seen in our center. It is considered that a significant population was treated where physical abuse and sexual abuse appears as most relevant.

Maltrato infantil. Experiencia de un abordaje interdisciplinario / Child abuse. An interdisciplinary management experience

Introducción. El maltrato infantil constituye una de las formas más frecuentes de violencia familiar.El presente estudio intenta mostrar la situación que, al respecto, existe en la ciudad de Mercedes, Corrientes,Argentina y establecer algunas asociaciones propias de esa roblemática.Población, material y métodos. Se presenta una serie de 128 casos de niños maltratados, de entre 0 y 19 años, entre noviembre de 1998 y noviembre de 2002 asistidos en Moiru, Centro de Prevención, Orientación, Asistencia y Capacitación en conductas sociales de riesgo, que funciona en Mercedes.Resultados. Se detectó 56 por ciento de maltrato físico; 30 por cientode abuso sexual; 10 por ciento de negligencia; 3 por ciento de maltratoemocional y 1 por ciento de síndrome de Münchaussen con una distribución por sexos similares en el total de la casuística.Se señalan variables demográficas y ciertas asociaciones en casos de maltrato físico y abuso sexual. Seevidenció una asociación significativa entre madres víctimas de violencia doméstica y el maltrato físicoque éstas proporcionan a sus hijos.Conclusiones. Fueron asistidos en nuestro servicio 128 niños y niñas maltratados Se considera que setrata de una casuística significativa, donde el maltrato físico y el abuso sexual se presentan como másrelevantes.