Accurate identification of rice diseases is crucial for controlling diseases and improving rice yield.To improve the classification accuracy of rice diseases,this paper proposed a classification and identification met...Accurate identification of rice diseases is crucial for controlling diseases and improving rice yield.To improve the classification accuracy of rice diseases,this paper proposed a classification and identification method based on an improved ShuffleNet V2(GE-ShuffleNet)model.Firstly,the Ghost module is used to replace the 1×1 convolution in the two basic unit modules of ShuffleNet V2,and the unimportant 1×1 convolution is deleted from the two basic unit modules of ShuffleNet V2.The Hardswish activation function is applied to replace the ReLU activation function to improve the identification accuracy of the model.Secondly,an effective channel attention(ECA)module is added to the network to avoid dimension reduction,and the correlation between channels is effectively extracted through 1D convolution.Besides,L2 regularization is introduced to fine-tune the training parameters during training to prevent overfitting.Finally,the considerable experimental and numerical results proved the advantages of our proposed model in terms of model size,floating-point operation per second(FLOPs),and parameters(Params).Especially in the case of smaller model size(5.879 M),the identification accuracy of GE-ShuffleNet(96.6%)is higher than that of ShuffleNet V2(94.4%),MobileNet V2(93.7%),AlexNet(79.1%),Swim Transformer(88.1%),EfficientNet V2(89.7%),VGG16(81.9%),GhostNet(89.3%)and ResNet50(92.5%).展开更多
Boosting tumor immunosurveillance with vaccines has been proven to be a feasible and cost-effective strategy to fight cancer. Although major breakthroughs have been achieved in preventative tumor vaccines targeting on...Boosting tumor immunosurveillance with vaccines has been proven to be a feasible and cost-effective strategy to fight cancer. Although major breakthroughs have been achieved in preventative tumor vaccines targeting oncogenic viruses, limited advances have been made in curative vaccines for virus-irrelevant malignancies. Accumulating evidence suggests that preconditioning tumor cells with certain cytotoxic drugs can generate whole-cell tumor vaccines with strong prophylactic activities. However, the immunogenicity of these vaccines is not sufficient to restrain the outgrowth of existing tumors. In this study, we identified arsenic trioxide (ATO) as a wide-spectrum cytotoxic and highly immunogenic drug through multiparameter screening. ATO preconditioning could generate whole-cell tumor vaccines with potent antineoplastic effects in both prophylactic and therapeutic settings. The tumor-preventive or tumor-suppressive benefits of these vaccines relied on CD8^(+) T cells and type I and II interferon signaling and could be linked to the release of immunostimulatory danger molecules. Unexpectedly, following ATO-induced oxidative stress, multiple cell death pathways were activated, including autophagy, apoptosis, necroptosis, and ferroptosis. CRISPR‒Cas9-mediated knockout of cell death executors revealed that the absence of Rip3, Mlkl, or Acsl4 largely abolished the efficacy of ATO-based prophylactic and therapeutic cancer vaccines. This therapeutic failure could be rescued by coadministration of danger molecule analogs. In addition, PD-1 blockade synergistically improved the therapeutic efficacy of ATO-based cancer vaccines by augmenting local IFN-γ production.展开更多
基金This work is supported in part by the Ji Lin provincial science and technology department international science and technology cooperation project under Grant 20200801014GHthe Changchun City Science and Technology Bureau key science and technology research projects under Grant 21ZGN28.
文摘Accurate identification of rice diseases is crucial for controlling diseases and improving rice yield.To improve the classification accuracy of rice diseases,this paper proposed a classification and identification method based on an improved ShuffleNet V2(GE-ShuffleNet)model.Firstly,the Ghost module is used to replace the 1×1 convolution in the two basic unit modules of ShuffleNet V2,and the unimportant 1×1 convolution is deleted from the two basic unit modules of ShuffleNet V2.The Hardswish activation function is applied to replace the ReLU activation function to improve the identification accuracy of the model.Secondly,an effective channel attention(ECA)module is added to the network to avoid dimension reduction,and the correlation between channels is effectively extracted through 1D convolution.Besides,L2 regularization is introduced to fine-tune the training parameters during training to prevent overfitting.Finally,the considerable experimental and numerical results proved the advantages of our proposed model in terms of model size,floating-point operation per second(FLOPs),and parameters(Params).Especially in the case of smaller model size(5.879 M),the identification accuracy of GE-ShuffleNet(96.6%)is higher than that of ShuffleNet V2(94.4%),MobileNet V2(93.7%),AlexNet(79.1%),Swim Transformer(88.1%),EfficientNet V2(89.7%),VGG16(81.9%),GhostNet(89.3%)and ResNet50(92.5%).
基金supported by the National Science and Technology Innovation 2030 Major Project of China(2022ZD0205700)Natural Science Foundation of China(NSFC,81972701)+2 种基金CAMS Innovation Fund for Medical Sciences(CIFMS,2021-I2M-1-074,2022-I2M-2-004)National Special Support Program for High-level Talents,China Ministry of Science and Technology(National Key Research and Development Program,Grant 2017YFA0506200)Innovative and Entrepreneurial Team Program(Jiangsu Province).
文摘Boosting tumor immunosurveillance with vaccines has been proven to be a feasible and cost-effective strategy to fight cancer. Although major breakthroughs have been achieved in preventative tumor vaccines targeting oncogenic viruses, limited advances have been made in curative vaccines for virus-irrelevant malignancies. Accumulating evidence suggests that preconditioning tumor cells with certain cytotoxic drugs can generate whole-cell tumor vaccines with strong prophylactic activities. However, the immunogenicity of these vaccines is not sufficient to restrain the outgrowth of existing tumors. In this study, we identified arsenic trioxide (ATO) as a wide-spectrum cytotoxic and highly immunogenic drug through multiparameter screening. ATO preconditioning could generate whole-cell tumor vaccines with potent antineoplastic effects in both prophylactic and therapeutic settings. The tumor-preventive or tumor-suppressive benefits of these vaccines relied on CD8^(+) T cells and type I and II interferon signaling and could be linked to the release of immunostimulatory danger molecules. Unexpectedly, following ATO-induced oxidative stress, multiple cell death pathways were activated, including autophagy, apoptosis, necroptosis, and ferroptosis. CRISPR‒Cas9-mediated knockout of cell death executors revealed that the absence of Rip3, Mlkl, or Acsl4 largely abolished the efficacy of ATO-based prophylactic and therapeutic cancer vaccines. This therapeutic failure could be rescued by coadministration of danger molecule analogs. In addition, PD-1 blockade synergistically improved the therapeutic efficacy of ATO-based cancer vaccines by augmenting local IFN-γ production.