2篇
您的检索式：作者名="Yuankai Mu"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | ALK gene expression status in pleural effusion predicts tumor responsiveness to crizotinib in Chinese patients with lung adenocarcinoma显示文摘Objective: The relationship between anaplastic lymphoma kinase(ALK) expression in malignant pleural effusion(MPE) samples detected only by Ventana immunohistochemistry(IHC) ALK(D5F3) and the efficacy of ALKtyrosine kinase inhibitor therapy is uncertain.Methods: Ventana anti-ALK(D5F3) rabbit monoclonal primary antibody testing was performed on 313 cell blocks of MPE samples from Chinese patients with advanced lung adenocarcinoma, and fluorescence in situ hybridization(FISH) was used to verify the ALK gene status in Ventana IHC ALK(D5F3)-positive samples. The follow-up clinical data on patients who received crizotinib treatment were recorded.Results: Of the 313 MPE samples, 27(8.6%) were confirmed as ALK expression-positive, and the Ventana IHC ALK(D5F3)-positive rate was 17.3%(27/156) in wild-type epidermal growth factor receptor(EGFR) MPE samples. Twenty-three of the 27 IHC ALK(D5F3)-positive samples were positive by FISH. Of the 11 Ventana IHC ALK(D5F3)-positive patients who received crizotinib therapy, 2 patients had complete response(CR), 5 had partial response(PR) and 3 had stable disease(SD).Conclusions: The ALK gene expression status detected by the Ventana IHC ALK(D5F3) platform in MPE samples may predict tumor responsiveness to crizotinib in Chinese patients with advanced lung adenocarcinoma. | Zheng Wang Xiaonan Wu Xiaohong Han Gang Cheng Xinlin Mu Yuhui Zhang Di Cui Chang Liu Dongge Liu Yuankai Shi | 2016 | Chinese Journal of Cancer Research2016，28，6： | 1 |
| 2 | A Client Selection Method Based on Loss Function Optimization for Federated Learning显示文摘Federated learning is a distributedmachine learningmethod that can solve the increasingly serious problemof data islands and user data privacy,as it allows training data to be kept locally and not shared with other users.It trains a globalmodel by aggregating locally-computedmodels of clients rather than their rawdata.However,the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global model.For this problem,we focus on the client selection with federated learning,which can affect the convergence performance of the global model with the selected local models.We propose FedChoice,a client selection method based on loss function optimization,to select appropriate local models to improve the convergence of the global model.It firstly sets selected probability for clients with the value of loss function,and the client with high loss will be set higher selected probability,which can make them more likely to participate in training.Then,it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction,respectively,and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviationof the local gradient causedby theNon-IIDdata.Wemake experiments to verify the validity of FedChoice on CIFAR-10,CINIC-10,MNIST,EMNITS,and FEMNIST datasets,and the results show that the convergence of FedChoice is significantly improved,compared with FedAvg,FedProx,and FedNova. | Yan Zeng Siyuan Teng Tian Xiang Jilin Zhang Yuankai Mu Yongjian Ren Jian Wan | 2023 | Computer Modeling in Engineering & Sciences2023，，10： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员