To balance the speed and accuracy in semantic segmentation of the urban street images for autonomous driving,we proposed an improved U-Net network.Firstly,to improve the model representation capability,our improved U-...To balance the speed and accuracy in semantic segmentation of the urban street images for autonomous driving,we proposed an improved U-Net network.Firstly,to improve the model representation capability,our improved U-Net network structure was designed as three parts,shallow layer,intermediate layer and deep layer.Different attention mechanisms were used according to their feature extraction characteristics.Specifically,a spatial attention module was used in the shallow network,a dual attention module was used in the intermediate layer network and a channel attention module was used in the deep network.At the same time,the traditional convolution was replaced by depthwise separable convolution in above three parts,which can largely reduce the number of network parameters,and improve the network operation speed greatly.The experimental results on three datasets show that our improved U-Net semantic segmentation model for street images can get better results in both segmentation accuracy and speed.The average mean intersection over union(MIoU)is 68.8%,which is increased by 9.2%and the computation speed is about 38 ms/frame.We can process 27 frames images for segmentation per second,which meets the real-time process and accuracy requirements for semantic segmentation of urban street images.展开更多
To solve the problems of convolutional neural network–principal component analysis(CNN-PCA)in fine description and generalization of complex reservoir geological features,a 3D attention U-Net network was proposed not...To solve the problems of convolutional neural network–principal component analysis(CNN-PCA)in fine description and generalization of complex reservoir geological features,a 3D attention U-Net network was proposed not using a trained C3D video motion analysis model to extract the style of a 3D model,and applied to complement the details of geologic model lost in the dimension reduction of PCA method in this study.The 3D attention U-Net network was applied to a complex river channel sandstone reservoir to test its effects.The results show that compared with CNN-PCA method,the 3D attention U-Net network could better complement the details of geological model lost in the PCA dimension reduction,better reflect the fluid flow features in the original geologic model,and improve history matching results.展开更多
Brown adipose tissue(BAT)is a kind of adipose tissue engaging in thermoregulatory thermogenesis,metaboloregulatory thermogenesis,and secretory.Current studies have revealed that BAT activity is negatively correlated w...Brown adipose tissue(BAT)is a kind of adipose tissue engaging in thermoregulatory thermogenesis,metaboloregulatory thermogenesis,and secretory.Current studies have revealed that BAT activity is negatively correlated with adult body weight and is considered a target tissue for the treatment of obesity and other metabolic-related diseases.Additionally,the activity of BAT presents certain differences between different ages and genders.Clinically,BAT segmentation based on PET/CT data is a reliable method for brown fat research.However,most of the current BAT segmentation methods rely on the experience of doctors.In this paper,an improved U-net network,ICA-Unet,is proposed to achieve automatic and precise segmentation of BAT.First,the traditional 2D convolution layer in the encoder is replaced with a depth-wise overparameterized convolutional(Do-Conv)layer.Second,the channel attention block is introduced between the double-layer convolution.Finally,the image information entropy(IIE)block is added in the skip connections to strengthen the edge features.Furthermore,the performance of this method is evaluated on the dataset of PET/CT images from 368 patients.The results demonstrate a strong agreement between the automatic segmentation of BAT and manual annotation by experts.The average DICE coeffcient(DSC)is 0.9057,and the average Hausdorff distance is 7.2810.Experimental results suggest that the method proposed in this paper can achieve effcient and accurate automatic BAT segmentation and satisfy the clinical requirements of BAT.展开更多
Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other aspects.Predicting the changes and trends of air pollution can provide a scientific ...Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other aspects.Predicting the changes and trends of air pollution can provide a scientific basis for governance and prevention efforts.In this paper,we propose an interval prediction method that considers the spatio-temporal characteristic information of PM_(2.5)signals from multiple stations.K-nearest neighbor(KNN)algorithm interpolates the lost signals in the process of collection,transmission,and storage to ensure the continuity of data.Graph generative network(GGN)is used to process time-series meteorological data with complex structures.The graph U-Nets framework is introduced into the GGN model to enhance its controllability to the graph generation process,which is beneficial to improve the efficiency and robustness of the model.In addition,sparse Bayesian regression is incorporated to improve the dimensional disaster defect of traditional kernel density estimation(KDE)interval prediction.With the support of sparse strategy,sparse Bayesian regression kernel density estimation(SBR-KDE)is very efficient in processing high-dimensional large-scale data.The PM_(2.5)data of spring,summer,autumn,and winter from 34 air quality monitoring sites in Beijing verified the accuracy,generalization,and superiority of the proposed model in interval prediction.展开更多
Background:Diabetic retinopathy(DR)is one of the primary causes of visual impairment globally,resulting from microvascular abnormalities in the retina.Accurate segmentation of retinal blood vessels from fundus images ...Background:Diabetic retinopathy(DR)is one of the primary causes of visual impairment globally,resulting from microvascular abnormalities in the retina.Accurate segmentation of retinal blood vessels from fundus images plays a pivotal role in the early diagnosis,progression monitoring,and treatment planning of DR and related ocular conditions.Traditional convolutional neural networks often struggle with capturing the intricate structures of thin vessels under varied illumination and contrast conditions.Methods:In this study,we propose an improved U-Net-based framework named MSAC U-Net,which enhances feature extraction and reconstruction through multiscale and attention-based modules.Specifically,the encoder replaces standard convolutions with a Multiscale Asymmetric Convolution(MSAC)block,incorporating parallel 1×n,n×1,and n×n kernels at different scales(3×3,5×5,7×7)to effectively capture fine-grained vascular structures.To further refine spatial representation,skip connections are utilized,and the decoder is augmented with dual activation strategies,Squeeze-and-Excitation blocks,and Convolutional Block Attention Modules for improved contextual understanding.Results:The model was evaluated on the publicly available DRIVE dataset.It achieved an accuracy of 96.48%,sensitivity of 88.31%,specificity of 97.90%,and an AUC of 98.59%,demonstrating superior performance compared to several state-of-the-art segmentation methods.Conclusion:The proposed MSAC U-Net provides a robust and accurate approach for retinal vessel segmentation,offering substantial clinical value in the early detection and management of diabetic retinopathy.Its design contributes to enhanced segmentation reliability and may serve as a foundation for broader applications in medical image analysis.展开更多
由于患者个体差异、采集协议多样性和数据损坏等因素,现有基于磁共振成像(Magnetic resonance imaging,MRI)的脑肿瘤分割方法存在模态数据丢失问题,导致分割精度不高。为此,本文提出了一种基于U-Net和Transformer结合的不完整多模态脑...由于患者个体差异、采集协议多样性和数据损坏等因素,现有基于磁共振成像(Magnetic resonance imaging,MRI)的脑肿瘤分割方法存在模态数据丢失问题,导致分割精度不高。为此,本文提出了一种基于U-Net和Transformer结合的不完整多模态脑肿瘤分割(Incomplete multimodal brain tumor segmentation based on the combination of U-Net and Transformer,IM TransNet)方法。首先,针对脑肿瘤MRI的4个不同模态设计了单模态特定编码器,提升模型对各模态数据的表征能力。其次,在U-Net中嵌入双重注意力的Transformer模块,克服模态缺失引起的信息不完整问题,减少U-Net的长距离上下文交互和空间依赖性局限。在U-Net的跳跃连接中加入跳跃交叉注意力机制,动态关注不同层级和模态的特征,即使在模态缺失时,也能有效融合特征并进行重建。此外,针对模态缺失引起的训练不平衡问题,设计了辅助解码模块,确保模型在各种不完整模态子集上均能稳定高效地分割脑肿瘤。最后,基于公开数据集BRATS验证模型的性能。实验结果表明,本文提出的模型在增强型肿瘤、肿瘤核心和全肿瘤上的平均Dice评分分别为63.19%、76.42%和86.16%,证明了其在处理不完整多模态数据时的优越性和稳定性,为临床实践中脑肿瘤的准确、高效和可靠分割提供了一种可行的技术手段。展开更多
基金supported by the National Natural Science Foundation China(No.61601174)the Postdoctoral Research Foundation of Heilongjiang Province(No.LBH-Q17150)the Science and Technology Innovative Research Team in Higher Educational Institutions of Heilongjiang Province(No.2012TD007)。
文摘To balance the speed and accuracy in semantic segmentation of the urban street images for autonomous driving,we proposed an improved U-Net network.Firstly,to improve the model representation capability,our improved U-Net network structure was designed as three parts,shallow layer,intermediate layer and deep layer.Different attention mechanisms were used according to their feature extraction characteristics.Specifically,a spatial attention module was used in the shallow network,a dual attention module was used in the intermediate layer network and a channel attention module was used in the deep network.At the same time,the traditional convolution was replaced by depthwise separable convolution in above three parts,which can largely reduce the number of network parameters,and improve the network operation speed greatly.The experimental results on three datasets show that our improved U-Net semantic segmentation model for street images can get better results in both segmentation accuracy and speed.The average mean intersection over union(MIoU)is 68.8%,which is increased by 9.2%and the computation speed is about 38 ms/frame.We can process 27 frames images for segmentation per second,which meets the real-time process and accuracy requirements for semantic segmentation of urban street images.
基金Supported by the China National Oil and Gas Major Project(2016ZX05010-003)PetroChina Science and Technology Major Project(2019B1210,2021DJ1201).
文摘To solve the problems of convolutional neural network–principal component analysis(CNN-PCA)in fine description and generalization of complex reservoir geological features,a 3D attention U-Net network was proposed not using a trained C3D video motion analysis model to extract the style of a 3D model,and applied to complement the details of geologic model lost in the dimension reduction of PCA method in this study.The 3D attention U-Net network was applied to a complex river channel sandstone reservoir to test its effects.The results show that compared with CNN-PCA method,the 3D attention U-Net network could better complement the details of geological model lost in the PCA dimension reduction,better reflect the fluid flow features in the original geologic model,and improve history matching results.
基金supported in part by the National Natural Science Foundation of China(61701403,82122033,81871379)National Key Research and Development Program of China(2016YFC0103804,2019YFC1521103,2020YFC1523301,2019YFC-1521102)+3 种基金Key R&D Projects in Shaanxi Province(2019ZDLSF07-02,2019ZDLGY10-01)Key R&D Projects in Qinghai Province(2020-SF-143)China Post-doctoral Science Foundation(2018M643719)Young Talent Support Program of the Shaanxi Association for Science and Technology(20190107).
文摘Brown adipose tissue(BAT)is a kind of adipose tissue engaging in thermoregulatory thermogenesis,metaboloregulatory thermogenesis,and secretory.Current studies have revealed that BAT activity is negatively correlated with adult body weight and is considered a target tissue for the treatment of obesity and other metabolic-related diseases.Additionally,the activity of BAT presents certain differences between different ages and genders.Clinically,BAT segmentation based on PET/CT data is a reliable method for brown fat research.However,most of the current BAT segmentation methods rely on the experience of doctors.In this paper,an improved U-net network,ICA-Unet,is proposed to achieve automatic and precise segmentation of BAT.First,the traditional 2D convolution layer in the encoder is replaced with a depth-wise overparameterized convolutional(Do-Conv)layer.Second,the channel attention block is introduced between the double-layer convolution.Finally,the image information entropy(IIE)block is added in the skip connections to strengthen the edge features.Furthermore,the performance of this method is evaluated on the dataset of PET/CT images from 368 patients.The results demonstrate a strong agreement between the automatic segmentation of BAT and manual annotation by experts.The average DICE coeffcient(DSC)is 0.9057,and the average Hausdorff distance is 7.2810.Experimental results suggest that the method proposed in this paper can achieve effcient and accurate automatic BAT segmentation and satisfy the clinical requirements of BAT.
基金Project(2020YFC2008605)supported by the National Key Research and Development Project of ChinaProject(52072412)supported by the National Natural Science Foundation of ChinaProject(2021JJ30359)supported by the Natural Science Foundation of Hunan Province,China。
文摘Urban air pollution has brought great troubles to physical and mental health,economic development,environmental protection,and other aspects.Predicting the changes and trends of air pollution can provide a scientific basis for governance and prevention efforts.In this paper,we propose an interval prediction method that considers the spatio-temporal characteristic information of PM_(2.5)signals from multiple stations.K-nearest neighbor(KNN)algorithm interpolates the lost signals in the process of collection,transmission,and storage to ensure the continuity of data.Graph generative network(GGN)is used to process time-series meteorological data with complex structures.The graph U-Nets framework is introduced into the GGN model to enhance its controllability to the graph generation process,which is beneficial to improve the efficiency and robustness of the model.In addition,sparse Bayesian regression is incorporated to improve the dimensional disaster defect of traditional kernel density estimation(KDE)interval prediction.With the support of sparse strategy,sparse Bayesian regression kernel density estimation(SBR-KDE)is very efficient in processing high-dimensional large-scale data.The PM_(2.5)data of spring,summer,autumn,and winter from 34 air quality monitoring sites in Beijing verified the accuracy,generalization,and superiority of the proposed model in interval prediction.
基金supported by the Guangdong Basic and Applied Basic Research Foundation(2024A1515010987)the Medical Scientific Research Foundation of Guangdong Province(B2024035).
文摘Background:Diabetic retinopathy(DR)is one of the primary causes of visual impairment globally,resulting from microvascular abnormalities in the retina.Accurate segmentation of retinal blood vessels from fundus images plays a pivotal role in the early diagnosis,progression monitoring,and treatment planning of DR and related ocular conditions.Traditional convolutional neural networks often struggle with capturing the intricate structures of thin vessels under varied illumination and contrast conditions.Methods:In this study,we propose an improved U-Net-based framework named MSAC U-Net,which enhances feature extraction and reconstruction through multiscale and attention-based modules.Specifically,the encoder replaces standard convolutions with a Multiscale Asymmetric Convolution(MSAC)block,incorporating parallel 1×n,n×1,and n×n kernels at different scales(3×3,5×5,7×7)to effectively capture fine-grained vascular structures.To further refine spatial representation,skip connections are utilized,and the decoder is augmented with dual activation strategies,Squeeze-and-Excitation blocks,and Convolutional Block Attention Modules for improved contextual understanding.Results:The model was evaluated on the publicly available DRIVE dataset.It achieved an accuracy of 96.48%,sensitivity of 88.31%,specificity of 97.90%,and an AUC of 98.59%,demonstrating superior performance compared to several state-of-the-art segmentation methods.Conclusion:The proposed MSAC U-Net provides a robust and accurate approach for retinal vessel segmentation,offering substantial clinical value in the early detection and management of diabetic retinopathy.Its design contributes to enhanced segmentation reliability and may serve as a foundation for broader applications in medical image analysis.
文摘由于患者个体差异、采集协议多样性和数据损坏等因素,现有基于磁共振成像(Magnetic resonance imaging,MRI)的脑肿瘤分割方法存在模态数据丢失问题,导致分割精度不高。为此,本文提出了一种基于U-Net和Transformer结合的不完整多模态脑肿瘤分割(Incomplete multimodal brain tumor segmentation based on the combination of U-Net and Transformer,IM TransNet)方法。首先,针对脑肿瘤MRI的4个不同模态设计了单模态特定编码器,提升模型对各模态数据的表征能力。其次,在U-Net中嵌入双重注意力的Transformer模块,克服模态缺失引起的信息不完整问题,减少U-Net的长距离上下文交互和空间依赖性局限。在U-Net的跳跃连接中加入跳跃交叉注意力机制,动态关注不同层级和模态的特征,即使在模态缺失时,也能有效融合特征并进行重建。此外,针对模态缺失引起的训练不平衡问题,设计了辅助解码模块,确保模型在各种不完整模态子集上均能稳定高效地分割脑肿瘤。最后,基于公开数据集BRATS验证模型的性能。实验结果表明,本文提出的模型在增强型肿瘤、肿瘤核心和全肿瘤上的平均Dice评分分别为63.19%、76.42%和86.16%,证明了其在处理不完整多模态数据时的优越性和稳定性,为临床实践中脑肿瘤的准确、高效和可靠分割提供了一种可行的技术手段。
