Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of...Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.展开更多
To grade Small Hepatocellular Car Cinoma(SHCC)using texture analysis of CT images,we retrospectively analysed 68 cases of Grade II(medium-differentiation)and 37 cases of Grades III and IV(high-differentiation).The gra...To grade Small Hepatocellular Car Cinoma(SHCC)using texture analysis of CT images,we retrospectively analysed 68 cases of Grade II(medium-differentiation)and 37 cases of Grades III and IV(high-differentiation).The grading scheme follows 4 stages:(1)training a Super Resolution Generative Adversarial Network(SRGAN)migration learning model on the Lung Nodule Analysis 2016 Dataset,and employing this model to reconstruct Super Resolution Images of the SHCC Dataset(SR-SHCC)images;(2)designing a texture clustering method based on Gray-Level Co-occurrence Matrix(GLCM)to segment tumour regions,which are Regions Of Interest(ROIs),from the original and SR-SHCC images,respectively;(3)extracting texture features on the ROIs;(4)performing statistical analysis and classifications.The segmentation achieved accuracies of 0.9049 and 0.8590 in the original SHCC images and the SR-SHCC images,respectively.The classification achived an accuracy of 0.838 and an Area Under the ROC Curve(AUC)of 0.84.The grading scheme can effectively reduce poor impacts on the texture analysis of SHCC ROIs.It may play a guiding role for physicians in early diagnoses of medium-differentiation and high-differentiation in SHCC.展开更多
The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in tra...The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual’s privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.展开更多
基金The authors received Sichuan Science and Technology Program(No.18YYJC1917)funding for this study.
文摘Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.
基金supported by the National Key R&D Program of China(No.2018YFC0807500)。
文摘To grade Small Hepatocellular Car Cinoma(SHCC)using texture analysis of CT images,we retrospectively analysed 68 cases of Grade II(medium-differentiation)and 37 cases of Grades III and IV(high-differentiation).The grading scheme follows 4 stages:(1)training a Super Resolution Generative Adversarial Network(SRGAN)migration learning model on the Lung Nodule Analysis 2016 Dataset,and employing this model to reconstruct Super Resolution Images of the SHCC Dataset(SR-SHCC)images;(2)designing a texture clustering method based on Gray-Level Co-occurrence Matrix(GLCM)to segment tumour regions,which are Regions Of Interest(ROIs),from the original and SR-SHCC images,respectively;(3)extracting texture features on the ROIs;(4)performing statistical analysis and classifications.The segmentation achieved accuracies of 0.9049 and 0.8590 in the original SHCC images and the SR-SHCC images,respectively.The classification achived an accuracy of 0.838 and an Area Under the ROC Curve(AUC)of 0.84.The grading scheme can effectively reduce poor impacts on the texture analysis of SHCC ROIs.It may play a guiding role for physicians in early diagnoses of medium-differentiation and high-differentiation in SHCC.
文摘The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations.Graph embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data continuously.Publishing social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual’s privacy and security.Unfortunately,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks.To be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding.In this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph embedding.Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.
