Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Ophthalmol Glaucoma ; 7(1): 8-15, 2024.
Artigo em Inglês | MEDLINE | ID: mdl-37437884

RESUMO

PURPOSE: To assess the performance and generalizability of a convolutional neural network (CNN) model for objective and high-throughput identification of primary angle-closure disease (PACD) as well as PACD stage differentiation on anterior segment swept-source OCT (AS-OCT). DESIGN: Cross-sectional. PARTICIPANTS: Patients from 3 different eye centers across China and Singapore were recruited for this study. Eight hundred forty-one eyes from the 2 Chinese centers were divided into 170 control eyes, 488 PACS, and 183 PAC + PACG eyes. An additional 300 eyes were recruited from Singapore National Eye Center as a testing data set, divided into 100 control eyes, 100 PACS, and 100 PAC + PACG eyes. METHODS: Each participant underwent standardized ophthalmic examination and was classified by the presiding physician as either control, primary angle-closure suspect (PACS), primary angle closure (PAC), or primary angle-closure glaucoma (PACG). Deep Learning model was used to train 3 different CNN classifiers: classifier 1 aimed to separate control versus PACS versus PAC + PACG; classifier 2 aimed to separate control versus PACD; and classifier 3 aimed to separate PACS versus PAC + PACG. All classifiers were evaluated on independent validation sets from the same region, China and further tested using data from a different country, Singapore. MAIN OUTCOME MEASURES: Area under receiver operator characteristic curve (AUC), precision, and recall. RESULTS: Classifier 1 achieved an AUC of 0.96 on validation set from the same region, but dropped to an AUC of 0.84 on test set from a different country. Classifier 2 achieved the most generalizable performance with an AUC of 0.96 on validation set and AUC of 0.95 on test set. Classifier 3 showed the poorest performance, with an AUC of 0.83 and 0.64 on test and validation data sets, respectively. CONCLUSIONS: Convolutional neural network classifiers can effectively distinguish PACD from controls on AS-OCT with good generalizability across different patient cohorts. However, their performance is moderate when trying to distinguish PACS versus PAC + PACG. FINANCIAL DISCLOSURES: The authors have no proprietary or commercial interest in any materials discussed in this article.


Assuntos
Aprendizado Profundo , Glaucoma de Ângulo Fechado , Humanos , Pressão Intraocular , Tomografia de Coerência Óptica/métodos , Estudos Transversais , Glaucoma de Ângulo Fechado/diagnóstico
2.
Plant Dis ; 107(7): 2070-2080, 2023 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-36691277

RESUMO

The distribution range of root-knot nematode Meloidogyne graminicola is rapidly expanding, posing a severe threat to rice production. In this study, the sequences of cytochrome oxidase subunit I (COI) genes of rice M. graminicola populations from all reported provinces in China were amplified and sequenced by PCR. The distribution pattern and phylogenetic tree showed that all 54 M. graminicola populations in China have distinct geographical distribution characteristics; specifically, cluster 1 (southern China), cluster 2 (central south and southwest China), and cluster 3 (central and eastern China). The high haplotype diversity (Hd = 0.646) and low nucleotide diversity (π = 0.00682), combined with the negative value of Tajima's D (-1.252) and Fu's Fs (-3.06764), suggested that all nematode populations were expanding. The existence of high genetic differentiation (Fst = 0.5933) and low gene flow (Nm = 0.3333) indicated that there was a block of gene exchange between most populations. Mutation accumulation with population expansion might be directly responsible for the high genetic differentiation; therefore, the tested nematode population showed high within-group genetic variation (96.30%). The haplotype Hap8 was located at the bottom of the network topology, with the widest distribution and the highest frequency (59.26%), indicating that it was the ancestral haplotype. The populations in cluster 3 were newly invasive according to the lowest frequency of occurrence of Hap8, the highest number of endemic haplotypes, and the highest total haplotype frequency (60%). In contrast, cluster 1 having the highest genetic diversity (Hd = 0.772, π = 0.01127) indicated that it was the most primitive. Interestingly, the highest gene flow (Nm > 1), lowest genetic differentiation (Fst ≤ 0.33), and closest genetic distance (0.000) only occurred between the Guangdong/Hainan population and others, which suggested that there might be channels for gene exchange between them and that long-distance dispersal occurred. This suggestion is further confirmed by the weak correlation between genetic distance and geographical distance. Based on these data, a hypothesis can be drawn that M. graminicola populations in China were spreading from south to north, specifically from Guangdong and Hainan Provinces to other regions. Natural selection (including anthropogenic) and genetic drift were the main drivers of their evolution. Coincidentally, this hypothesis was consistent with the gradual warming trend and the chronological order of reporting these populations. The main factors influencing current M. graminicola population expansion and distribution patterns might be geography, climate, long-distance seedling transport, interregional operations of agricultural machinery, and rotation mode. It reminds human beings of the necessity to be vigilant about preventing nematode disease according to local conditions all year round.


Assuntos
Oryza , Tylenchoidea , Animais , Humanos , Filogenia , Tylenchoidea/genética , Geografia , Deriva Genética , China
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...