Objective:We propose a solution that is backed by cloud computing,combines a series of AI neural networks of computer vision;is capable of detecting,highlighting,and locating breast lesions from a live ultrasound vide...Objective:We propose a solution that is backed by cloud computing,combines a series of AI neural networks of computer vision;is capable of detecting,highlighting,and locating breast lesions from a live ultrasound video feed,provides BI-RADS categorizations;and has reliable sensitivity and specificity.Multiple deep-learning models were trained on more than 300,000 breast ultrasound images to achieve object detection and regions of interest classification.The main objective of this study was to determine whether the performance of our Al-powered solution was comparable to that of ultrasound radiologists.Methods:The noninferiority evaluation was conducted by comparing the examination results of the same screening women between our AI-powered solution and ultrasound radiologists with over 10 years of experience.The study lasted for one and a half years and was carried out in the Duanzhou District Women and Children's Hospital,Zhaoqing,China.1,133 females between 20 and 70 years old were selected through convenience sampling.Results:The accuracy,sensitivity,specificity,positive predictive value,and negative predictive value were 93.03%,94.90%,90.71%,92.68%,and 93.48%,respectively.The area under the curve(AUC)for all positives was 0.91569 and the AUC for all negatives was 0.90461.The comparison indicated that the overall performance of the AI system was comparable to that of ultrasound radiologists.Conclusion:This innovative AI-powered ultrasound solution is cost-effective and user-friendly,and could be applied to massive breast cancer screening.展开更多
Decreasing mode coupling coefficient(κ) is an effective approach to suppress the inter-core crosstalk. Therefore, we deploy a low index rod and rectangle trench in the middle of two neighboring cores to reduce κ so ...Decreasing mode coupling coefficient(κ) is an effective approach to suppress the inter-core crosstalk. Therefore, we deploy a low index rod and rectangle trench in the middle of two neighboring cores to reduce κ so that the overlap of electric field distribution can be suppressed. We also propose approximate analytical solution(AAS) for κ of two crosstalk suppression models, which are two cores with one low index rod deployed in the middle and two cores with one low index rectangle trench deployed in the middle. We then do some modification for the results obtained by AAS and the modified results are proved to agree well with that obtained by finite element method(FEM). Therefore, we can use the modified AAS to get inter-core crosstalk for abovementioned two models quickly.展开更多
Fertility is the most crucial step in the development process,which is controlled by many fertility-related proteins,including spermatogenesis-,oogenesis-and embryogenesis-related proteins.The identification of fertil...Fertility is the most crucial step in the development process,which is controlled by many fertility-related proteins,including spermatogenesis-,oogenesis-and embryogenesis-related proteins.The identification of fertility-related proteins can provide important clues for studying the role of these proteins in development.Therefore,in this study,we constructed a two-layer classifier to identify fertility-related proteins.In this classifier,we first used the composition of amino acids(AA)and their physical and chemical properties to code these three fertility-related proteins.Then,the feature set is optimized by analysis of variance(ANOVA)and incremental feature selection(IFS)to obtain the optimal feature subset.Through five-fold cross-validation(CV)and independent data tests,the performance of models constructed by different machine learning(ML)methods is evaluated and compared.Finally,based on support vector machine(SVM),we obtained a two-layer model to classify three fertility-related proteins.On the independent test data set,the accuracy(ACC)and the area under the receiver operating characteristic curve(AUC)of the first layer classifier are 81.95%and 0.89,respectively,and them of the second layer classifier are 84.74%and 0.90,respectively.These results show that the proposed model has stable performance and satisfactory prediction accuracy,and can become a powerful model to identify more fertility related proteins.展开更多
文摘Objective:We propose a solution that is backed by cloud computing,combines a series of AI neural networks of computer vision;is capable of detecting,highlighting,and locating breast lesions from a live ultrasound video feed,provides BI-RADS categorizations;and has reliable sensitivity and specificity.Multiple deep-learning models were trained on more than 300,000 breast ultrasound images to achieve object detection and regions of interest classification.The main objective of this study was to determine whether the performance of our Al-powered solution was comparable to that of ultrasound radiologists.Methods:The noninferiority evaluation was conducted by comparing the examination results of the same screening women between our AI-powered solution and ultrasound radiologists with over 10 years of experience.The study lasted for one and a half years and was carried out in the Duanzhou District Women and Children's Hospital,Zhaoqing,China.1,133 females between 20 and 70 years old were selected through convenience sampling.Results:The accuracy,sensitivity,specificity,positive predictive value,and negative predictive value were 93.03%,94.90%,90.71%,92.68%,and 93.48%,respectively.The area under the curve(AUC)for all positives was 0.91569 and the AUC for all negatives was 0.90461.The comparison indicated that the overall performance of the AI system was comparable to that of ultrasound radiologists.Conclusion:This innovative AI-powered ultrasound solution is cost-effective and user-friendly,and could be applied to massive breast cancer screening.
基金supported by National B a-sic Research Program of China(Grant No.2012CB315905)National Natural Science Foundation of China(Grant No.61501027)+1 种基金China Postdoctoral Science Foundation(Grant No.2015M570934)Fundamental Research Funds for the Central Universities(Grant No.FRF-TP-15-031A1)
文摘Decreasing mode coupling coefficient(κ) is an effective approach to suppress the inter-core crosstalk. Therefore, we deploy a low index rod and rectangle trench in the middle of two neighboring cores to reduce κ so that the overlap of electric field distribution can be suppressed. We also propose approximate analytical solution(AAS) for κ of two crosstalk suppression models, which are two cores with one low index rod deployed in the middle and two cores with one low index rectangle trench deployed in the middle. We then do some modification for the results obtained by AAS and the modified results are proved to agree well with that obtained by finite element method(FEM). Therefore, we can use the modified AAS to get inter-core crosstalk for abovementioned two models quickly.
基金funded by the Sichuan Major Science and Technology Project(2021ZDZX0009)the National Natural Science Foundation of China(Grant No.035Z2060).
文摘Fertility is the most crucial step in the development process,which is controlled by many fertility-related proteins,including spermatogenesis-,oogenesis-and embryogenesis-related proteins.The identification of fertility-related proteins can provide important clues for studying the role of these proteins in development.Therefore,in this study,we constructed a two-layer classifier to identify fertility-related proteins.In this classifier,we first used the composition of amino acids(AA)and their physical and chemical properties to code these three fertility-related proteins.Then,the feature set is optimized by analysis of variance(ANOVA)and incremental feature selection(IFS)to obtain the optimal feature subset.Through five-fold cross-validation(CV)and independent data tests,the performance of models constructed by different machine learning(ML)methods is evaluated and compared.Finally,based on support vector machine(SVM),we obtained a two-layer model to classify three fertility-related proteins.On the independent test data set,the accuracy(ACC)and the area under the receiver operating characteristic curve(AUC)of the first layer classifier are 81.95%and 0.89,respectively,and them of the second layer classifier are 84.74%and 0.90,respectively.These results show that the proposed model has stable performance and satisfactory prediction accuracy,and can become a powerful model to identify more fertility related proteins.
