👤 Benoit De Solan

Computer vision is increasingly used in farmers' fields and agricultural experiments to quantify important traits. Imaging setups with a sub-millimeter ground sampling distance enable the detection and tracking of plant features, including size, shape, and colour. Although today's AI-driven foundation models segment almost any object in an image, they still fail for complex plant canopies. To improve model performance, the global wheat dataset consortium assembled a diverse set of images from experiments around the globe. After the head detection dataset (GWHD), the new dataset targets a full semantic segmentation (GWFSS) of organs (leaves, stems and spikes) covering all developmental stages. Images were collected by 11 institutions using a wide range of imaging setups. Two datasets are provided: i) a set of 1096 diverse images in which all organs were labelled at the pixel level, and (ii) a dataset of 52,078 images without annotations available for additional training. The labelled set was used to train segmentation models based on DeepLabV3Plus and Segformer. Our Segformer model performed slightly better than DeepLabV3Plus with a mIOU for leaves and spikes of ca. 90 ​%. However, the precision for stems with 54 ​% was rather lower. The major advantages over published models are: i) the exclusion of weeds from the wheat canopy, ii) the detection of all wheat features including necrotic and senescent tissues and its separation from crop residues. This facilitates further development in classifying healthy vs. unhealthy tissue to address the increasing need for accurate quantification of senescence and diseases in wheat canopies. Show less

Liver X receptor α (LXRα) is a nuclear transcription factor that regulates lipid metabolism. Recently, it has been shown that activation of LXRα with synthetic ligands has anti-inflammatory effects in atherosclerosis and chemical-induced dermatitis. We investigated the effect of the LXRα agonist, T0901317, on lung inflammation in a rodent model of hemorrhagic shock. Hemorrhagic shock was induced in male rats by withdrawing blood to a goal mean arterial blood pressure of 50 mmHg. Blood pressure was maintained at this level for 3 h, at which point rats were rapidly resuscitated with shed blood. Animals were then treated with T0901317 (50 mg · kg) or vehicle i.p. and sacrificed at 1, 2, and 3 h after resuscitation. Treatment with T0901317 significantly improved the cardiac and stroke volume indices as well as the heart rate of rats during the resuscitation period as compared with vehicle-treated rats. The T0901317-treated animals showed significant improvement in the plasma level of lactate, whereas base deficit and bicarbonate levels both trended toward improvement. The T0901317-treated animals also showed lower levels of plasma cytokines and chemokines monocyte chemoattractant protein 1, macrophage inflammatory protein 1α, TNF-α, KC, and IL-6. Lung injury and neutrophil infiltration were reduced by treatment with T0901317, as evaluated by histology and myeloperoxidase assay. At molecular analysis, treatment with T0901317 increased nuclear LXRα expression and DNA binding while also inhibiting activation of nuclear factor κB, a proinflammatory transcription factor, in the lung. Thus, our data suggest that LXRα is an important modulator of the inflammatory response and lung injury after severe hemorrhagic shock, likely through the inhibition of the nuclear factor κB pathway. Show less