The purpose of this study was to develop methodology to segment tumors on 18F-fluorodeoxyg- lucose (FDG) positron emission tomography (PET) images. Sixty-four metastatic bone tumors were included. Graph cut was used f...The purpose of this study was to develop methodology to segment tumors on 18F-fluorodeoxyg- lucose (FDG) positron emission tomography (PET) images. Sixty-four metastatic bone tumors were included. Graph cut was used for tumor segmentation, with segmentation energy divided into unary and pairwise terms. Locally connected conditional random fields (LCRF) were proposed for the pairwise term. In LCRF, three-dimensional cubic window with length L was set for each voxel, and voxels within the window were considered for the pairwise term. Three other types of segmentation were applied: region-growing based on 35%, 40%, and 45% of the tumor maximum standardized uptake value (RG35, RG40, and RG45, respectively), SLIC superpixels (SS), and region-based active contour models (AC). To validate the tumor segmentation accuracy, dice similarity coefficients (DSC) were calculated between the result of each technique and manual segmentation. Differences in DSC were tested using the Wilcoxon signed-rank test. Mean DSCs for LCRF at L = 3, 5, 7, and 9 were 0.784, 0.801, 0.809, and 0.812, respectively. Mean DSCs for the other techniques were: RG35, 0.633;RG40, 0.675;RG45, 0.689;SS, 0.709;and AC, 0.758. The DSC differences between LCRF and other techniques were statistically significant (p < 0.05). Tumor segmentation was reliably performed with LCRF.展开更多
车载点云数据语义标注是道路场景语义分析和理解的前提,该文提出了结合分割算法和图卷积网络的车载点云分类方法。首先利用具有噪声的基于密度的聚类方法(densitybased spatial clustering of applications with noise,DBSCAN)将点云分...车载点云数据语义标注是道路场景语义分析和理解的前提,该文提出了结合分割算法和图卷积网络的车载点云分类方法。首先利用具有噪声的基于密度的聚类方法(densitybased spatial clustering of applications with noise,DBSCAN)将点云分割成点簇,并以点簇为节点,相邻点簇构成边,节点和边形成图;然后利用图卷积网络对图节点进行半监督分类,得到点云中任一点的类别标注。实验表明,所提方法以点簇代替原始点云,极大减少了算法处理的数据量;半监督图卷积网络模型顾及了点云数据的上下文关联,在少量标注样本的情况下,能够获得较高的分类精度,场景简单的实验数据分类精度可以与Pointnet++模型相当,场景较为复杂的实验数据分类精度与Pointnet++模型相差在6.7%以内。展开更多
文摘The purpose of this study was to develop methodology to segment tumors on 18F-fluorodeoxyg- lucose (FDG) positron emission tomography (PET) images. Sixty-four metastatic bone tumors were included. Graph cut was used for tumor segmentation, with segmentation energy divided into unary and pairwise terms. Locally connected conditional random fields (LCRF) were proposed for the pairwise term. In LCRF, three-dimensional cubic window with length L was set for each voxel, and voxels within the window were considered for the pairwise term. Three other types of segmentation were applied: region-growing based on 35%, 40%, and 45% of the tumor maximum standardized uptake value (RG35, RG40, and RG45, respectively), SLIC superpixels (SS), and region-based active contour models (AC). To validate the tumor segmentation accuracy, dice similarity coefficients (DSC) were calculated between the result of each technique and manual segmentation. Differences in DSC were tested using the Wilcoxon signed-rank test. Mean DSCs for LCRF at L = 3, 5, 7, and 9 were 0.784, 0.801, 0.809, and 0.812, respectively. Mean DSCs for the other techniques were: RG35, 0.633;RG40, 0.675;RG45, 0.689;SS, 0.709;and AC, 0.758. The DSC differences between LCRF and other techniques were statistically significant (p < 0.05). Tumor segmentation was reliably performed with LCRF.
基金Acknowledgments: The authors thank for Prof. ZHANG Rong's valuable comments that improve the readability of this paper. This work was supported by the National Natural Science Foundation of China (No. 60672071), the Ministry of Education (No. NCET-05-0534), the Natural Science Foundation of Zhejiang (No. D 1080807).
文摘车载点云数据语义标注是道路场景语义分析和理解的前提,该文提出了结合分割算法和图卷积网络的车载点云分类方法。首先利用具有噪声的基于密度的聚类方法(densitybased spatial clustering of applications with noise,DBSCAN)将点云分割成点簇,并以点簇为节点,相邻点簇构成边,节点和边形成图;然后利用图卷积网络对图节点进行半监督分类,得到点云中任一点的类别标注。实验表明,所提方法以点簇代替原始点云,极大减少了算法处理的数据量;半监督图卷积网络模型顾及了点云数据的上下文关联,在少量标注样本的情况下,能够获得较高的分类精度,场景简单的实验数据分类精度可以与Pointnet++模型相当,场景较为复杂的实验数据分类精度与Pointnet++模型相差在6.7%以内。