From Laboratory to Field: Unsupervised Domain Adaptation for Plant Disease Recognition in the Wild.

Plant disease recognition is of vital importance to monitor plant development and predicting crop production. However, due to data degradation caused by different conditions of image acquisition, e.g., laboratory vs. field environment, machine learning-based recognition models generated within a specific dataset (source domain) tend to lose their validity when generalized to a novel dataset (target domain). To this end, domain adaptation methods can be leveraged for the recognition by learning invariant representations across domains. In this paper, we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via uncertainty regularization, namely, Multi-Representation Subdomain Adaptation Network with Uncertainty Regularization for Cross-Species Plant Disease Classification (MSUN). Our simple but effective MSUN makes a breakthrough in plant disease recognition in the wild by using a large amount of unlabeled data and via nonadversarial training. Specifically, MSUN comprises multirepresentation, subdomain adaptation modules and auxiliary uncertainty regularization. The multirepresentation module enables MSUN to learn the overall structure of features and also focus on capturing more details by using the multiple representations of the source domain. This effectively alleviates the problem of large interdomain discrepancy. Subdomain adaptation is used to capture discriminative properties by addressing the issue of higher interclass similarity and lower intraclass variation. Finally, the auxiliary uncertainty regularization effectively suppresses the uncertainty problem due to domain transfer. MSUN was experimentally validated to achieve optimal results on the PlantDoc, Plant-Pathology, Corn-Leaf-Diseases, and Tomato-Leaf-Diseases datasets, with accuracies of 56.06%, 72.31%, 96.78%, and 50.58%, respectively, surpassing other state-of-the-art domain adaptation techniques considerably.

Silencing miRNA-324-3p protects against cerebral ischemic injury via regulation of the GATA2/A1R axis.

Previous studies have suggested that miR-324-3p is related to the pathophysiology of cerebral ischemia, but the mechanism underlying this relationship is unclear. In this study, we found that miR-324-3p expression was decreased in patients with acute ischemic stroke and in in vitro and in vivo models of ischemic stroke. miR-324-3p agomir potentiated ischemic brain damage in rats subjected to middle cerebral artery occlusion, as indicated by increased infarct volumes and cell apoptosis rates and greater neurological deficits. In a PC12 cell oxygen-glucose deprivation/reoxygenation model, a miR-324-3p mimic decreased cell viability and expression of the anti-apoptotic protein BCL2 and increased expression of the pro-apoptotic protein BAX and rates of cell apoptosis, whereas treatment with a miR-324-3p inhibitor had the opposite effects. Silencing miR-324-3p increased adenosine A1 receptor (A1R) expression through regulation of GATA binding protein 2 (GATA2). These findings suggest that silencing miR-324-3p reduces ischemic brain damage via the GATA2/A1R axis.

Analgesia with 5' extracellular nucleotidase-mediated electroacupuncture for neuropathic pain.

BACKGROUND: Acupuncture is a treatment for neuropathic pain, but its mechanism remains unclear. Previous studies showed that analgesia was induced in rats with neuropathic pain when their spinal cord adenosine content increased after electroacupuncture (EA); however, the mechanism behind this electroacupuncture-induced increase has not been clarified. OBJECTIVE: This study aimed to determine the role that ecto-5'-nucleotidase plays in EA-induced analgesia for neuropathic pain. METHODS: We performed electroacupuncture at the Zusanli acupoint on the seventh day after establishing a rat model of neuropathic pain induced through chronic constriction injuries. We observed the mechanical withdrawal threshold and thermal pain threshold and detected the expression of ecto-5'-nucleotidase in the spinal cord using Western blot. Chronic constriction injury rat models were intraperitoneally injected with α,ß-methyleneadenosine 5'-diphosphate, an ecto-5'-nucleotidase inhibitor, 30 min before electroacupuncture. The adenosine content of the spinal cord was detected using high-performance liquid chromatography. Lastly, the adenosine A1 receptor agonist N6-cyclopentyladenosine was intrathecally injected into the lumbar swelling of the rats, and the mechanical withdrawal and thermal pain thresholds were reevaluated. RESULTS: Analgesia and increased ecto-5'-nucleotidase expression and adenosine content in the spinal cord were observed 1 h after electroacupuncture. α,ß-methyleneadenosine 5'-diphosphate was able to inhibit upregulation of adenosine content and electroacupuncture-induced analgesia. After administration of N6-cyclopentyladenosine, electroacupuncture-induced analgesia was restored. CONCLUSIONS: Our results suggest that electroacupuncture at Zusanli can produce analgesia in chronic constriction injury rat models, possibly via the increased ecto-5'-nucleotidase expression induced through electroacupuncture, thus leading to increased adenosine expression in the spinal cord.