Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Tianshu Xie"'
Autor:
Minghui Liu, Meiyi Yang, Jiali Deng, Xuan Cheng, Tianshu Xie, Pan Deng, Haigang Gong, Ming Liu, Xiaomin Wang
Publikováno v:
International Journal of Computational Intelligence Systems, Vol 16, Iss 1, Pp 1-12 (2023)
Abstract Over-fitting is a significant threat to the integrity and reliability of deep neural networks with generous parameters. One problem is that the model learned more specific features than general features in the training process. To solve the
Externí odkaz:
https://doaj.org/article/d3831f29335f41fdb62ecb765e3bfcc0
Publikováno v:
IEEE Access, Vol 11, Pp 1708-1717 (2023)
Traditional self-supervised learning requires convolutional neural networks (CNNs) using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this paper, we show that feature transformati
Externí odkaz:
https://doaj.org/article/f9c7111f594347e39c381f1feb392e38
Publikováno v:
Journal of Traditional Chinese Medical Sciences, Vol 9, Iss 4, Pp 420-431 (2022)
Objective: To provide a possible basis for the anti-aging effect of modified Qiongyu paste (MQP). Methods: Ultra-high-performance liquid chromatography-Q-Orbitrap mass spectrometry was applied to confirm the effective components of MQP that we had id
Externí odkaz:
https://doaj.org/article/2533a9ea9fa14455b3ebc67dad929efa
Autor:
Qianqian Huang, Chen Zhang, Shi Dong, Junwen Han, Sihao Qu, Tianshu Xie, Haibin Zhao, Yuanyuan Shi
Publikováno v:
Chinese Medicine, Vol 17, Iss 1, Pp 1-21 (2022)
Abstract Background Alzheimer's Disease (AD) is a serious neurodegenerative disease and there is currently no effective treatment for AD progression. The use of TCM as a potential treatment strategy for AD is an evolving field of investigation. Asafo
Externí odkaz:
https://doaj.org/article/b853ef357d464e16be8dc5f8b298fd47
Autor:
Tianshu Xie, Yi Wei, Lifeng Xu, Qian Li, Feng Che, Qing Xu, Xuan Cheng, Minghui Liu, Meiyi Yang, Xiaomin Wang, Feng Zhang, Bin Song, Ming Liu
Publikováno v:
Frontiers in Oncology, Vol 13 (2023)
Background and purposeProgrammed cell death protein-1 (PD-1) and programmed cell death-ligand-1 (PD-L1) expression status, determined by immunohistochemistry (IHC) of specimens, can discriminate patients with hepatocellular carcinoma (HCC) who can de
Externí odkaz:
https://doaj.org/article/85979f6c74014b0286bd347fbdb3dd47
Autor:
Yi Wei, Meiyi Yang, Lifeng Xu, Minghui Liu, Feng Zhang, Tianshu Xie, Xuan Cheng, Xiaomin Wang, Feng Che, Qian Li, Qing Xu, Zixing Huang, Ming Liu
Publikováno v:
Cancers, Vol 15, Iss 3, p 658 (2023)
The expression status of programmed cell death protein 1 (PD-1) in patients with hepatocellular carcinoma (HCC) is associated with the checkpoint blockade treatment responses of PD-1/PD-L1. Thus, accurately and preoperatively identifying the status o
Externí odkaz:
https://doaj.org/article/533718b3c5eb4c8ba2c26bf4c8a4edac
Publikováno v:
Applied Sciences, Vol 12, Iss 15, p 7682 (2022)
In a convolutional neural network (CNN), dropout cannot work well because dropped information is not entirely obscured in convolutional layers where features are correlated spatially. Except for randomly discarding regions or channels, many approache
Externí odkaz:
https://doaj.org/article/c4e64704ecbd4359b43a0a2e6cf8d1d3
Autor:
Lifeng Xu, Chun Yang, Feng Zhang, Xuan Cheng, Yi Wei, Shixiao Fan, Minghui Liu, Xiaopeng He, Jiali Deng, Tianshu Xie, Xiaomin Wang, Ming Liu, Bin Song
Publikováno v:
Cancers, Vol 14, Iss 11, p 2574 (2022)
This retrospective study aimed to develop and validate deep-learning-based models for grading clear cell renal cell carcinoma (ccRCC) patients. A cohort enrolling 706 patients (n = 706) with pathologically verified ccRCC was used in this study. A tem
Externí odkaz:
https://doaj.org/article/b2be454552fe452fbec282365eebfe72
Autor:
Minghui Liu, Jiali Deng, Meiyi Yang, Xuan Cheng, Tianshu Xie, Pan Deng, Xiaomin Wang, Ming Liu
Publikováno v:
Applied Sciences, Vol 12, Iss 8, p 3910 (2022)
Generative Adversarial Networks (GANs) are powerful generative models for numerous tasks and datasets. However, most of the existing models suffer from mode collapse. The most recent research indicates that the reason for it is that the optimal trans
Externí odkaz:
https://doaj.org/article/eb64e2fb62b84578800722782bf2fdcc
Publikováno v:
Applied Sciences, Vol 12, Iss 7, p 3318 (2022)
In this paper, we propose a novel training strategy named Feature Mining for convolutional neural networks (CNNs) that aims to strengthen the network’s learning of the local features. Through experiments, we found that different parts of the featur
Externí odkaz:
https://doaj.org/article/9fbe3047f41b4bdba96ea448a0d6d8c0