Automated early detection of acute retinal necrosis from ultra-widefield color fundus photography using deep learning.

BACKGROUND: Acute retinal necrosis (ARN) is a relatively rare but highly damaging and potentially sight-threatening type of uveitis caused by infection with the human herpesvirus. Without timely diagnosis and appropriate treatment, ARN can lead to severe vision loss. We aimed to develop a deep learning framework to distinguish ARN from other types of intermediate, posterior, and panuveitis using ultra-widefield color fundus photography (UWFCFP). METHODS: We conducted a two-center retrospective discovery and validation study to develop and validate a deep learning model called DeepDrARN for automatic uveitis detection and differentiation of ARN from other uveitis types using 11,508 UWFCFPs from 1,112 participants. Model performance was evaluated with the area under the receiver operating characteristic curve (AUROC), the area under the precision and recall curves (AUPR), sensitivity and specificity, and compared with seven ophthalmologists. RESULTS: DeepDrARN for uveitis screening achieved an AUROC of 0.996 (95% CI: 0.994-0.999) in the internal validation cohort and demonstrated good generalizability with an AUROC of 0.973 (95% CI: 0.956-0.990) in the external validation cohort. DeepDrARN also demonstrated excellent predictive ability in distinguishing ARN from other types of uveitis with AUROCs of 0.960 (95% CI: 0.943-0.977) and 0.971 (95% CI: 0.956-0.986) in the internal and external validation cohorts. DeepDrARN was also tested in the differentiation of ARN, non-ARN uveitis (NAU) and normal subjects, with sensitivities of 88.9% and 78.7% and specificities of 93.8% and 89.1% in the internal and external validation cohorts, respectively. The performance of DeepDrARN is comparable to that of ophthalmologists and even exceeds the average accuracy of seven ophthalmologists, showing an improvement of 6.57% in uveitis screening and 11.14% in ARN identification. CONCLUSIONS: Our study demonstrates the feasibility of deep learning algorithms in enabling early detection, reducing treatment delays, and improving outcomes for ARN patients.

Application of machine learning in the study of development, behavior, nerve, and genotoxicity of zebrafish.

Machine learning (ML) as a novel model-based approach has been used in studying aquatic toxicology in the environmental field. Zebrafish, as an ideal model organism in aquatic toxicology research, has been widely used to study the toxic effects of various pollutants. However, toxicity testing on organisms may cause significant harm, consume considerable time and resources, and raise ethical concerns. Therefore, ML is used in related research to reduce animal experiments and assist researchers in conducting toxicological research. Although ML techniques have matured in various fields, research on ML-based aquatic toxicology is still in its infancy due to the lack of comprehensive large-scale toxicity databases for environmental pollutants and model organisms. Therefore, to better understand the recent research progress of ML in studying the development, behavior, nerve, and genotoxicity of zebrafish, this review mainly focuses on using ML modeling to assess and predict the toxic effects of zebrafish exposure to different toxic chemicals. Meanwhile, the opportunities and challenges faced by ML in the field of toxicology were analyzed. Finally, suggestions and perspectives were proposed for the toxicity studies of ML on zebrafish in future applications.

Cucurbitane triterpenes from Hemsleya chinensis tubers and their anti-inflammatory activities.

Six new cucurbitane-type triterpenes, hemchinins A-F (1-6), together with thirteen known ones (7-19) were isolated from ethyl acetate extraction of Hemsleya chinensis tubers. Compounds 1-2 were a group of cucurbitane triterpenes possessing an infrequent pentacyclic framework. Their structures were established by comprehensive UV, IR, HRMS, 1D/2D NMR, and ECD analyses. Bioassay results showed that most isolated compounds exhibited anti-inflammatory actions, in which compounds 13 and 15 exhibited stronger activities at 6.25 µM, with NO inhibition rates of 49.00 ± 0.05% and 48.40 ± 0.10%, respectively.

Effect of Eucommia ulmoides leaves on hyperuricemia and kidney injury induced by a high-fat/high-fructose diet in rats.

Objectives: To investigate the protective and preventive treatment effects of Eucommia ulmoides leaves on a rat model of high-fat and high-fructose diet (HFFD) induced hyperuricemia and renal injury. Materials and Methods: Network pharmacology and molecular-docking methods were used to predict the effects and action mechanisms of the major components of E. ulmoides leaves on hyperuricemia. Combining literature collection, we used SciFinder and the Traditional Chinese Medicine Systems Pharmacology Database (TCMSP) and Analysis Platform to collect E. ulmoides leaf flavonoid and iridoid components. Swiss Target Prediction, Similarity ensemble approach (SEA), GeneCards, and the Online Mendelian Inheritance in Man (OMIM) database were used to obtain core targets, and the Search Tool for Recurring Instances of Neighbouring Genes (STRING) protein database was used as core target for gene ontology enrichment Set and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses. Molecular docking was applied to predict the pathways regulating the metabolism of uric acid. The selected targets and targeting efficacy were validated using a rat model of hyperuricemia and renal injury induced by a high-fat and high-fructose diet. Results: A total of 32 chemical components with effective targets, which regulated the PI3K-AKT pathway and endocrine resistance, were collected. Molecular docking results showed that iridoids and flavonoids are bound to proteins related to inflammation and uric acid metabolism. In addition, it was verified via animal experiments that an E. ulmoides leaf extract ameliorated hyperuricemia, renal injury, and inflammation, which are closely related to the targets Interleukin- 6 (IL-6), Tumor necrosis factor-α (TNF-α), Toll-Like Receptor 4 (TLR4), and Glucose transporter 9 (GLUT9). Conclusion: E. ulmoides leaf flavonoids and iridoids ameliorate hyperuricemia and uric-acid-induced inflammation through a multi-component, multi-target, and multi-pathway mechanism, which provides a theoretical basis for the development of therapeutics from E. ulmoides leaf components.

A turn on fluorescent assay for real time determination of ß-galactosidase and its application in living cell imaging.

In recent years, fluorescent probes based on chemical reactions have been widely investigated as a powerful and noninvasive method for the diagnosis of diseases. ß-Galactosidase (ß-gal), a typical lysosomal glycosidase, over expressed in senescent cells and primary ovarian cancer cells, which has been considered as an important biomarker cell senescence and primary ovarian cancers. Fluorescent probes for the determination of ß-gal provide an excellent choice for visualization of cell senescence. In this work, a turn on fluorescent probe (HBT-gal) for ß-gal activity was developed based on the enzymatic hydrolysis of glycosidic bonds. HBT-gal showed little fluorescence in aqueous buffer excited at 415 nm, while emitted green fluorescence centered at ∼ 492 nm upon incubated with ß-gal. The sensing scheme showed high selectivity and sensitivity for ß-gal activity with a limit of detection calculated as low as 0.19 mU/mL. Moreover, HBT-gal was successfully applied to image ß-gal activity in senescent Hep G2 cells treated with H2O2. Therefore, probe HBT-gal demonstrated a potential usage for the determination of cell senescence using ß-gal as a biomarker.