In the field of neutronics analysis, it is imperative to develop computer-aided modeling technology for Monte Carlo codes to address the increasing complexity of reactor core components by converting 3D CAD model(boun...In the field of neutronics analysis, it is imperative to develop computer-aided modeling technology for Monte Carlo codes to address the increasing complexity of reactor core components by converting 3D CAD model(boundary representation, BREP) to MC model(constructive solid geometry, CSG). Separation-based conversion from BREP to CSG is widely used in computer-aided modeling MC codes because of its high efficiency, reliability, and easy implementation. However, the current separation-based BREP-CSG conversion is poor for processing complex CAD models, and it is necessary to divide a complex model into several simple models before applying the separation-based conversion algorithm, which is time-consuming and tedious. To avoid manual segmentation, this study proposed a MeshCNN-based 3D-shape segmentation algorithm to automatically separate a complex model. The proposed 3D-shape segmentation algorithm was combined with separation-based BREP-CSG conversion algorithms to directly convert complex models.The proposed algorithm was integrated into the computeraided modeling software cosVMPT and validated using the Chinese fusion engineering testing reactor model. The results demonstrate that the MeshCNN-based BREP-CSG conversion algorithm has a better performance and higher efficiency, particularly in terms of CPU time, and the conversion result is more intuitive and consistent with the intention of the modeler.展开更多
To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative...To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative clustering for presegmentation procedure. The first step, we use simple linear iterative clustering algorithm to divide the image into a number of homogeneous over-segmented regions. Then, these regions are regarded as nodes, and a similarity matrix is constructed by comparing the histograms of each two regions. Finally, we apply the Ncut method to merging the over-segmented regions, then the image segmentation process is completed. The results show that the proposed segmentation scheme handles the strong speckle noise, low contrast, and weak edges well in ultrasound image. Our method has high segmentation precision and computation efficiency than the pixel-based Ncut method.展开更多
基金supported by the National Key R&D Program of China(Nos.2019YFE03110000 and 2017YFE0300501)the Chinese National Natural Science Foundation(No.11775256)。
文摘In the field of neutronics analysis, it is imperative to develop computer-aided modeling technology for Monte Carlo codes to address the increasing complexity of reactor core components by converting 3D CAD model(boundary representation, BREP) to MC model(constructive solid geometry, CSG). Separation-based conversion from BREP to CSG is widely used in computer-aided modeling MC codes because of its high efficiency, reliability, and easy implementation. However, the current separation-based BREP-CSG conversion is poor for processing complex CAD models, and it is necessary to divide a complex model into several simple models before applying the separation-based conversion algorithm, which is time-consuming and tedious. To avoid manual segmentation, this study proposed a MeshCNN-based 3D-shape segmentation algorithm to automatically separate a complex model. The proposed 3D-shape segmentation algorithm was combined with separation-based BREP-CSG conversion algorithms to directly convert complex models.The proposed algorithm was integrated into the computeraided modeling software cosVMPT and validated using the Chinese fusion engineering testing reactor model. The results demonstrate that the MeshCNN-based BREP-CSG conversion algorithm has a better performance and higher efficiency, particularly in terms of CPU time, and the conversion result is more intuitive and consistent with the intention of the modeler.
基金Supported by the National Basic Research Program ofChina(2011CB707900)
文摘To segment the tumor region precisely is a prerequisite for ultrasound navigation and treatment. In this paper, a normalized cut method to segment tumor ultrasound image is proposed by means of simple linear iterative clustering for presegmentation procedure. The first step, we use simple linear iterative clustering algorithm to divide the image into a number of homogeneous over-segmented regions. Then, these regions are regarded as nodes, and a similarity matrix is constructed by comparing the histograms of each two regions. Finally, we apply the Ncut method to merging the over-segmented regions, then the image segmentation process is completed. The results show that the proposed segmentation scheme handles the strong speckle noise, low contrast, and weak edges well in ultrasound image. Our method has high segmentation precision and computation efficiency than the pixel-based Ncut method.
