VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation.

Applying deep learning to images of cropping systems provides new knowledge and insights in research and commercial applications. Semantic segmentation or pixel-wise classification, of RGB images acquired at the ground level, into vegetation and background is a critical step in the estimation of several canopy traits. Current state of the art methodologies based on convolutional neural networks (CNNs) are trained on datasets acquired under controlled or indoor environments. These models are unable to generalize to real-world images and hence need to be fine-tuned using new labelled datasets. This motivated the creation of the VegAnn - Vegetation Annotation - dataset, a collection of 3775 multi-crop RGB images acquired for different phenological stages using different systems and platforms in diverse illumination conditions. We anticipate that VegAnn will help improving segmentation algorithm performances, facilitate benchmarking and promote large-scale crop vegetation segmentation research.

From Prototype to Inference: A Pipeline to Apply Deep Learning in Sorghum Panicle Detection.

Head (panicle) density is a major component in understanding crop yield, especially in crops that produce variable numbers of tillers such as sorghum and wheat. Use of panicle density both in plant breeding and in the agronomy scouting of commercial crops typically relies on manual counts observation, which is an inefficient and tedious process. Because of the easy availability of red-green-blue images, machine learning approaches have been applied to replacing manual counting. However, much of this research focuses on detection per se in limited testing conditions and does not provide a general protocol to utilize deep-learning-based counting. In this paper, we provide a comprehensive pipeline from data collection to model deployment in deep-learning-assisted panicle yield estimation for sorghum. This pipeline provides a basis from data collection and model training, to model validation and model deployment in commercial fields. Accurate model training is the foundation of the pipeline. However, in natural environments, the deployment dataset is frequently different from the training data (domain shift) causing the model to fail, so a robust model is essential to build a reliable solution. Although we demonstrate our pipeline in a sorghum field, the pipeline can be generalized to other grain species. Our pipeline provides a high-resolution head density map that can be utilized for diagnosis of agronomic variability within a field, in a pipeline built without commercial software.

IL16 and factor V gene variations are associated with asparaginase-related thrombosis in childhood acute lymphoblastic leukemia patients.

Aim: We previously conducted exome-wide association study in acute lymphoblastic leukemia patients and identified association of five SNPs with asparaginase-related thrombosis. Here we aimed to replicate these findings in an independent patient cohort and through analyses in vitro. Patients & methods: SNPs located in IL16, MYBBP1A, PKD2L1, RIN3 and MPEG1 genes were analyzed in patients receiving Dana-Farber Cancer Institute acute lymphoblastic leukemia treatment protocols 05-001 and 11-001. Thrombophilia-related variations were also analysed. Results: IL16 rs11556218 conferred higher risk of thrombosis and higher in vitro sensitivity to asparaginase. The association was modulated by the treatment protocol, risk group and immunophenotype. A crosstalk between factor V Leiden, non-O blood groups and higher risk of thrombosis was also seen. Conclusion: IL16 and factor V Leiden variations are implicated in asparaginase-related thrombosis.

This study looked at how certain genetic variations are related to a higher risk of blood clots in children with a type of cancer called acute lymphoblastic leukemia who are receiving a certain treatment (asparaginase). The study found that one specific genetic variation (IL16 rs11556218) was linked to a higher risk of blood clots (thrombosis), and that this risk was influenced by disease and treatment features. The study also found that a certain genetic variation (factor V Leiden), which makes blood more likely to clot, and blood type (non-O) were linked to a higher risk of thrombosis. The conclusion of this study is that genetic variations may play a role in blood clots in children with acute lymphoblastic leukemia receiving asparaginase, and if further confirmed, these variations can serve to advance personalized treatment strategies.

Pharmacodynamic characterization of rytvela, a novel allosteric anti-inflammatory therapeutic, to prevent preterm birth and improve fetal and neonatal outcomes.

BACKGROUND: Preterm birth is the leading cause of neonatal morbidity and mortality. Studies have shown that interleukin 1 plays a major role in the pathophysiology of preterm birth by inducing the production of proinflammatory mediators and uterine activation proteins leading to labor. More importantly, uteroplacental inflammation, associated with preterm birth parturition pathways, is detrimental to fetal tissues and leads to long-term sequelae. Our group has developed an allosteric antagonist of the interleukin 1 receptor, rytvela, found to be potent and safe in preventing preterm birth by suppressing inflammation via the inhibition of the mitogen-activated protein kinase pathway while preserving the Nuclear factor kappa B pathway (important in immune vigilance). Rytvela has been shown to inhibit inflammatory up-regulation and uterine activation while preserving fetal development. OBJECTIVE: This study aimed to further the preclinical development of rytvela by evaluating its optimal dose and minimal duration of treatment to inhibit the inflammatory cascade, prolong gestation, and promote neonatal outcomes. STUDY DESIGN: Pregnant CD-1 mice were administered with lipopolysaccharide (10 µg, intraperitoneal administration) or interleukin 1 (1 µg/kg, intrauterine administration) on gestational day 16 to induce preterm labor. Rytvela was administered at different doses (0.1, 0.5, 1.0, 2.0, 4.0 mg/kg/d subcutaneously) from gestational days 16 to 18.5. To evaluate the minimal duration of treatment, the mice were administered with rytvela (2 mg/kg/d subcutaneously) for 24, 36, or 48 hours. The rate of prematurity (gestational day <18.5) and neonate survival and weight were evaluated. Gestational tissues were collected at gestational day 17.5 to quantify cytokines, proinflammatory mediators, and uterine activating proteins by real-time quantitative polymerase chain reaction and enzyme-linked immunosorbent assay. The neonatal lungs and intestines were collected from postnatal days 5 to 7 and analyzed by histology. RESULTS: Rytvela exhibited a dose-response profile and achieved maximum efficacy at a dose of 2 mg/kg/d by reducing 70% of lipopolysaccharide-induced preterm births and 60% of interleukin 1ß-induced preterm births. In addition, rytvela attained maximum efficacy at a dose of 1 mg/kg/d by increasing neonate survival by up to 65% in both models of preterm birth. Rytvela protected fetuses from inflammatory insult as of 24 hours, preserving lung and intestinal integrity, and prevented preterm birth and fetal mortality by 60% and 50%, respectively, as of 36 hours of treatment. CONCLUSION: The maximum efficacy of rytvela was achieved at 2 mg/kg/d with improved birth outcomes and prevented inflammatory up-regulation upon 36 hours (only) of treatment. Rytvela exhibited desirable properties for the safe prevention of preterm birth and fetal protection.

Global Wheat Head Detection Challenges: Winning Models and Application for Head Counting.

Data competitions have become a popular approach to crowdsource new data analysis methods for general and specialized data science problems. Data competitions have a rich history in plant phenotyping, and new outdoor field datasets have the potential to embrace solutions across research and commercial applications. We developed the Global Wheat Challenge as a generalization competition in 2020 and 2021 to find more robust solutions for wheat head detection using field images from different regions. We analyze the winning challenge solutions in terms of their robustness when applied to new datasets. We found that the design of the competition had an influence on the selection of winning solutions and provide recommendations for future competitions to encourage the selection of more robust solutions.

SegVeg: Segmenting RGB Images into Green and Senescent Vegetation by Combining Deep and Shallow Methods.

Pixel segmentation of high-resolution RGB images into chlorophyll-active or nonactive vegetation classes is a first step often required before estimating key traits of interest. We have developed the SegVeg approach for semantic segmentation of RGB images into three classes (background, green, and senescent vegetation). This is achieved in two steps: A U-net model is first trained on a very large dataset to separate whole vegetation from background. The green and senescent vegetation pixels are then separated using SVM, a shallow machine learning technique, trained over a selection of pixels extracted from images. The performances of the SegVeg approach is then compared to a 3-class U-net model trained using weak supervision over RGB images segmented with SegVeg as groundtruth masks. Results show that the SegVeg approach allows to segment accurately the three classes. However, some confusion is observed mainly between the background and senescent vegetation, particularly over the dark and bright regions of the images. The U-net model achieves similar performances, with slight degradation over the green vegetation: the SVM pixel-based approach provides more precise delineation of the green and senescent patches as compared to the convolutional nature of U-net. The use of the components of several color spaces allows to better classify the vegetation pixels into green and senescent. Finally, the models are used to predict the fraction of three classes over whole images or regularly spaced grid-pixels. Results show that green fraction is very well estimated (R 2 = 0.94) by the SegVeg model, while the senescent and background fractions show slightly degraded performances (R 2 = 0.70 and 0.73, respectively) with a mean 95% confidence error interval of 2.7% and 2.1% for the senescent vegetation and background, versus 1% for green vegetation. We have made SegVeg publicly available as a ready-to-use script and model, along with the entire annotated grid-pixels dataset. We thus hope to render segmentation accessible to a broad audience by requiring neither manual annotation nor knowledge or, at least, offering a pretrained model for more specific use.

The Succinate Receptor SUCNR1 Resides at the Endoplasmic Reticulum and Relocates to the Plasma Membrane in Hypoxic Conditions.

The GPCR SUCNR1/GPR91 exerts proangiogenesis upon stimulation with the Krebs cycle metabolite succinate. GPCR signaling depends on the surrounding environment and intracellular localization through location bias. Here, we show by microscopy and by cell fractionation that in neurons, SUCNR1 resides at the endoplasmic reticulum (ER), while being fully functional, as shown by calcium release and the induction of the expression of the proangiogenic gene for VEGFA. ER localization was found to depend upon N-glycosylation, particularly at position N8; the nonglycosylated mutant receptor localizes at the plasma membrane shuttled by RAB11. This SUCNR1 glycosylation is physiologically regulated, so that during hypoxic conditions, SUCNR1 is deglycosylated and relocates to the plasma membrane. Downstream signal transduction of SUCNR1 was found to activate the prostaglandin synthesis pathway through direct interaction with COX-2 at the ER; pharmacologic antagonism of the PGE2 EP4 receptor (localized at the nucleus) was found to prevent VEGFA expression. Concordantly, restoring the expression of SUCNR1 in the retina of SUCNR1-null mice renormalized vascularization; this effect is markedly diminished after transfection of the plasma membrane-localized SUCNR1 N8A mutant, emphasizing that ER localization of the succinate receptor is necessary for proper vascularization. These findings uncover an unprecedented physiologic process where GPCR resides at the ER for signaling function.

Global Wheat Head Detection 2021: An Improved Dataset for Benchmarking Wheat Head Detection Methods.

The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD_2020 has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience, a few avenues for improvements have been identified regarding data size, head diversity, and label reliability. To address these issues, the 2020 dataset has been reexamined, relabeled, and complemented by adding 1722 images from 5 additional countries, allowing for 81,553 additional wheat heads. We now release in 2021 a new version of the Global Wheat Head Detection dataset, which is bigger, more diverse, and less noisy than the GWHD_2020 version.

Global Wheat Head Detection (GWHD) Dataset: A Large and Diverse Dataset of High-Resolution RGB-Labelled Images to Develop and Benchmark Wheat Head Detection Methods.

The detection of wheat heads in plant images is an important task for estimating pertinent wheat traits including head population density and head characteristics such as health, size, maturity stage, and the presence of awns. Several studies have developed methods for wheat head detection from high-resolution RGB imagery based on machine learning algorithms. However, these methods have generally been calibrated and validated on limited datasets. High variability in observational conditions, genotypic differences, development stages, and head orientation makes wheat head detection a challenge for computer vision. Further, possible blurring due to motion or wind and overlap between heads for dense populations make this task even more complex. Through a joint international collaborative effort, we have built a large, diverse, and well-labelled dataset of wheat images, called the Global Wheat Head Detection (GWHD) dataset. It contains 4700 high-resolution RGB images and 190000 labelled wheat heads collected from several countries around the world at different growth stages with a wide range of genotypes. Guidelines for image acquisition, associating minimum metadata to respect FAIR principles, and consistent head labelling methods are proposed when developing new head detection datasets. The GWHD dataset is publicly available at http://www.global-wheat.com/and aimed at developing and benchmarking methods for wheat head detection.