Aiming at the problems of information loss and the relationship between features and target tasks in multimodal medical image segmentation, a multimodal medical image segmentation algorithm based on feature decoupling...Aiming at the problems of information loss and the relationship between features and target tasks in multimodal medical image segmentation, a multimodal medical image segmentation algorithm based on feature decoupling and information bottleneck theory is proposed in this paper. Based on the reversible network, the bottom-up learning method for different modal information is constructed, which enhances the features’ expression ability and the network’s learning ability. The feature fusion module is designed to balance multi-directional information flow. To retain the information relevant to the target task to the maximum extent and suppress the information irrelevant to the target task, the feature decoupling module is designed to ensure a strong correlation between the feature and the target task. A loss function based on information bottleneck theory was intended to improve information quality and remove redundant information. Based on BraTs2021, BraTs2023-MET and ANNLIB datasets, the proposed algorithm is analyzed qualitatively and quantitatively in this paper. In the quantitative experiment, the Dice coefficient of the proposed algorithm was increased by 0.110 on average compared with other methods, and the HD95 was decreased by 28.568 on average compared with other methods. In qualitative analysis, the proposed algorithm can effectively segment the incoherent region between the lesion and the lesion boundary and achieve accurate segmentation of the lesion.展开更多
Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hier...Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local features.The network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information redundancy.In the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent slices.In the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation capability.The double-branch iterative multi-scale classification block is used to improve the classification performance.On the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation indicators.On the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.展开更多
Smart energy is the foundation and important component of smart cities, and it is the source of energy that guarantees the efficient and reliable operation of each subsystem of the city. Based on the practical experie...Smart energy is the foundation and important component of smart cities, and it is the source of energy that guarantees the efficient and reliable operation of each subsystem of the city. Based on the practical experience in the exploration of the construction of smart energy at home and abroad, and the goal of achieving “three transformations and one center”, the basic principles of the frame construction as well as display construction and physical construction of smart energy have been proposed. Four main tasks of the construction of smart energy have been discussed: infrastructure, energy supply, energy consumption, and management services.展开更多
The authors integrate two well-known systems, the Rssler and Lorentz systems,to introduce a new chaotic system, called the Lorentz-Rssler system. Then, taking into account the effect of environmental noise, the author...The authors integrate two well-known systems, the Rssler and Lorentz systems,to introduce a new chaotic system, called the Lorentz-Rssler system. Then, taking into account the effect of environmental noise, the authors incorporate white noise in both Rssler and Lorentz systems to have a corresponding stochastic system. By deriving the uniform a priori estimates for an approximate system and then taking them to the limit,the authors prove the global existence, uniqueness and the pathwise property of solutions to the Lorentz-Rssler system. Moreover, the authors carried out a number of numerical experiments, and the numerical results demonstrate their theoretic analysis and show some new qualitative properties of solutions which reveal that the Lorentz-Ro¨ssler system could be used to design more complex and more secure nonlinear hop-frequence time series.展开更多
基金supported by the following grants:Beijing Natural Science Foundation(No.Z210003)National Natural Science Foundation of China(NSFC12026607)+2 种基金NationalNatural Science Foundation of China(NSFC12031016)KeyR&DProgramof the Scientific Research Department(2020YFA0712203)Key R&D Programof the Scientific ResearchDepartment(2020YFA0712201).
文摘Aiming at the problems of information loss and the relationship between features and target tasks in multimodal medical image segmentation, a multimodal medical image segmentation algorithm based on feature decoupling and information bottleneck theory is proposed in this paper. Based on the reversible network, the bottom-up learning method for different modal information is constructed, which enhances the features’ expression ability and the network’s learning ability. The feature fusion module is designed to balance multi-directional information flow. To retain the information relevant to the target task to the maximum extent and suppress the information irrelevant to the target task, the feature decoupling module is designed to ensure a strong correlation between the feature and the target task. A loss function based on information bottleneck theory was intended to improve information quality and remove redundant information. Based on BraTs2021, BraTs2023-MET and ANNLIB datasets, the proposed algorithm is analyzed qualitatively and quantitatively in this paper. In the quantitative experiment, the Dice coefficient of the proposed algorithm was increased by 0.110 on average compared with other methods, and the HD95 was decreased by 28.568 on average compared with other methods. In qualitative analysis, the proposed algorithm can effectively segment the incoherent region between the lesion and the lesion boundary and achieve accurate segmentation of the lesion.
基金Major Program of National Natural Science Foundation of China(NSFC12292980,NSFC12292984)National Key R&D Program of China(2023YFA1009000,2023YFA1009004,2020YFA0712203,2020YFA0712201)+2 种基金Major Program of National Natural Science Foundation of China(NSFC12031016)Beijing Natural Science Foundation(BNSFZ210003)Department of Science,Technology and Information of the Ministry of Education(8091B042240).
文摘Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local features.The network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information redundancy.In the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent slices.In the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation capability.The double-branch iterative multi-scale classification block is used to improve the classification performance.On the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation indicators.On the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.
文摘Smart energy is the foundation and important component of smart cities, and it is the source of energy that guarantees the efficient and reliable operation of each subsystem of the city. Based on the practical experience in the exploration of the construction of smart energy at home and abroad, and the goal of achieving “three transformations and one center”, the basic principles of the frame construction as well as display construction and physical construction of smart energy have been proposed. Four main tasks of the construction of smart energy have been discussed: infrastructure, energy supply, energy consumption, and management services.
基金supported by the National Natural Science Foundation of China(Nos.11101044,11371065)the Beijing Center for Mathematics and Information Interdisciplinary Sciences
文摘The authors integrate two well-known systems, the Rssler and Lorentz systems,to introduce a new chaotic system, called the Lorentz-Rssler system. Then, taking into account the effect of environmental noise, the authors incorporate white noise in both Rssler and Lorentz systems to have a corresponding stochastic system. By deriving the uniform a priori estimates for an approximate system and then taking them to the limit,the authors prove the global existence, uniqueness and the pathwise property of solutions to the Lorentz-Rssler system. Moreover, the authors carried out a number of numerical experiments, and the numerical results demonstrate their theoretic analysis and show some new qualitative properties of solutions which reveal that the Lorentz-Ro¨ssler system could be used to design more complex and more secure nonlinear hop-frequence time series.
