Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 4 de 4
Filter
Add more filters










Database
Language
Publication year range
1.
Zhongguo Xue Xi Chong Bing Fang Zhi Za Zhi ; 33(5): 445-451, 2021 Oct 27.
Article in Chinese | MEDLINE | ID: mdl-34791840

ABSTRACT

OBJECTIVE: To establish a deep learning-based visual model for intelligent recognition of Oncomelania hupensis, the intermediate host of Schistosoma japonicum, and evaluate the effects of different training strategies for O. hupensis image recognition. METHODS: A total of 2 614 datasets of O. hupensis snails and 4 similar snails were generated through field sampling and internet capture, and were divided into training sets and test sets. An intelligent recognition model was created based on deep learning, and was trained and tested. The precision, sensitivity, specificity, accuracy, F1 score and Youden index were calculated. In addition, the receiver operating characteristic (ROC) curve of the model for snail recognition was plotted to evaluate the effects of "new learning", "transfer learning" and "transfer learning + data enhancement" training strategies on the accuracy of the model for snail recognition. RESULTS: Under the "transfer learning + data enhancement" strategy, the precision, sensitivity, specificity, accuracy, Youden index and F1 score of the model were 90.10%, 91.00%, 97.50%, 96.20%, 88.50% and 90.51% for snail recognition, which were all higher than those under both "new learning" and "transfer learning" strategies. There were significant differences in the sensitivity, specificity and accuracy of the model for snail recognition under "new learning", "transfer learning" and "transfer learning + data enhancement" training strategies (all P values < 0.001). In addition, the area under the ROC curve of the model was highest (0.94) under the "transfer learning + dataenhancement" training strategy. CONCLUSIONS: This is the first visual model for intelligent recognition of O. hupensis based on deep learning, which shows a high accuracy for snail image recognition. The "transfer learning + data enhancement" training strategy is helpful to improve the accuracy of the model for snail recognition.


Subject(s)
Deep Learning , Schistosoma japonicum , Animals , China , Snails
2.
Article in Chinese | MEDLINE | ID: mdl-33660468

ABSTRACT

Since 2015 when the transmission of schistosomiasis was controlled in China, the country has been moving towards elimination of schistosomiasis, with the surveillance-response as the main interventions for schistosomiasis control. During the period of the 13th Five-Year Plan, the transmission of schistosomiasis had been interrupted in four provinces of Sichuan, Jiangsu, Yunnan and Hubei and the prevalence of schistosomiasis has been at the historically lowest level in China. As a consequence, the goal set in The 13th Five-Year National Schistosomiasis Control Program in China is almost achieved. However, there are multiple challenges during the stage moving towards elimination of schistosomiasis in China, including the widespread distribution of intermediate host snails and complicated snail habitats, many types of sources of Schistosoma japonicum infections and difficulty in management of bovines and sheep, unmet requirements for the current schistosomiasis control program with the currently available tools, and vulnerable control achievements. During the 14th Five-Year period, it is crucial to consolidate the schistosomiasis control achievements and gradually solve the above difficulties, and critical to provide the basis for achieving the ultimate goal of elimination of schistosomiasis in China. Based on the past experiences from the national schistosomiasis control program and the challenges for schistosomiasis elimination in China, an expert consensus has been reached pertaining to the objectives, control strategy and measures for The 14th Five-Year National Schistosomiasis Control Program in China, so as to provide insights in to the development of The 14th Five-Year National Schistosomiasis Control Program in China.


Subject(s)
Schistosomiasis japonica , Schistosomiasis , Animals , Cattle , China/epidemiology , Consensus , Schistosomiasis/epidemiology , Schistosomiasis/prevention & control , Sheep , Snails
3.
Zhongguo Xue Xi Chong Bing Fang Zhi Za Zhi ; 31(6): 583-590, 2019 Dec 12.
Article in Chinese | MEDLINE | ID: mdl-32064799

ABSTRACT

Schistosomiasis was once heavily endemic in Jiangsu Province. Following the control efforts for several decades, schistosomiasis was almost eradicated in all endemic counties in Jiangsu Province in 1980, and transmission control was achieved in the province in 2011. According to the principle of "implementing the control measures with adaptation to local circumstances and guiding the control programs with classified interventions", an integrated strategy with emphasis on the management of both infectious sources and snails has been recently employed for schitsosomiasis control in Jiangsu Province. In addition, a sensitive and highly effective surveillance system has been built and the application of novel techniques and information construction has been intensified to effectively interrupt the transmission of schistosomiasis in the Province. Transmission interruption of schistosomiasis was achieved in all endemic counties in Jiangsu Province. The paper summarizes the endemic situation of schistosomiasis, progress of schistosomiasis control, and major schistosomiasis control measures implemented during the stage of transmission interruption in Jiangsu Province.


Subject(s)
Government Programs , Schistosomiasis , Animals , China , Disease Eradication/standards , Government Programs/standards , Government Programs/trends , Schistosomiasis/prevention & control , Schistosomiasis/transmission , Snails/parasitology
4.
Yi Chuan Xue Bao ; 28(11): 1062-7, 2001 Nov.
Article in Chinese | MEDLINE | ID: mdl-11725641

ABSTRACT

Apomixis is very common in Citrus genus and its related genus. Two monoembryonic tangerine varieties (C. reticulata Blanco) Clementine and Wilking were used as seed parents to cross with four polyembryonic orange varieties [C. sinensis (L.) Osbeck]. Both sexual and apomictic progenies were found in each F1 population with different segregation ratios. In a total of 74 Wilking progenies, 23 were monoembryonic and 51 polyembryonic and the ratio of sexual and apomictic progenies was about 1:2 tested either in each individual cross or in the whole Wilking cross combionations. In Clementine progenies, 84 were monoembryonic and 71 polyembryonic and the ratio was about 1:1 tested either in each individual cross or in the whole Clementine cross combionations. According to the results together with other data published, a possible apomixis controlling mechanism was proposed, which involves two complementary dominant genes named as A1 and A2 that control apomixis in genus Citrus and Poncirus. Trees of genotype A1-A2-, except for homozygous of dominant gene A1 (which is lethal), can produce apomixis seeds. And those of other genotypes will produce sexual seeds. The segregation and recombination of these two genes accorded with Mendel's genetic laws. The proposed mechanism could explain genotypes controlling polyembryony-monoembryony existing both in nature species and artificial hybridization progenies as well as most of the known hybridization results.


Subject(s)
Citrus/genetics , Genes, Dominant , Citrus/physiology , Crosses, Genetic , Reproduction
SELECTION OF CITATIONS
SEARCH DETAIL
...