In order to improve the registration accuracy of brain magnetic resonance images(MRI),some deep learning registration methods use segmentation images for training model.How-ever,the segmentation values are constant fo...In order to improve the registration accuracy of brain magnetic resonance images(MRI),some deep learning registration methods use segmentation images for training model.How-ever,the segmentation values are constant for each label,which leads to the gradient variation con-centrating on the boundary.Thus,the dense deformation field(DDF)is gathered on the boundary and there even appears folding phenomenon.In order to fully leverage the label information,the morphological opening and closing information maps are introduced to enlarge the non-zero gradi-ent regions and improve the accuracy of DDF estimation.The opening information maps supervise the registration model to focus on smaller,narrow brain regions.The closing information maps supervise the registration model to pay more attention to the complex boundary region.Then,opening and closing morphology networks(OC_Net)are designed to automatically generate open-ing and closing information maps to realize the end-to-end training process.Finally,a new registra-tion architecture,VM_(seg+oc),is proposed by combining OC_Net and VoxelMorph.Experimental results show that the registration accuracy of VM_(seg+oc) is significantly improved on LPBA40 and OASIS1 datasets.Especially,VM_(seg+oc) can well improve registration accuracy in smaller brain regions and narrow regions.展开更多
Identifying the morphology of rock blocks is vital to accurate modelling of rock mass structures. This paper applies the concepts of directed edges and vertex chain operations which are typical for block tracing appro...Identifying the morphology of rock blocks is vital to accurate modelling of rock mass structures. This paper applies the concepts of directed edges and vertex chain operations which are typical for block tracing approach to block assembling approach to construct the structure of three-dimensional fractured rock masses. Polygon subtraction and union algorithms that rely merely on vertex chain operation are proposed, which allow a fast and convenient construction of complex faces/loops. Apart from its robustness in dealing with finite discontinuities and complex geometries, the advantages of the current methodology in tackling some challenging issues associated with the morphological analysis of rock blocks are addressed. In particular, the identification of complex blocks with interior voids such as cavity, pit and toms can be readily achieved based on the number and the type of loops. The improved morphology visualization approach can benefit the pre-processing stage when analyzing the stability of rock masses subject to various engineering impacts using the block theory and the discrete element method.展开更多
基金supported by Shandong Provincial Natural Science Foundation(No.ZR2023MF062)the National Natural Science Foundation of China(No.61771230).
文摘In order to improve the registration accuracy of brain magnetic resonance images(MRI),some deep learning registration methods use segmentation images for training model.How-ever,the segmentation values are constant for each label,which leads to the gradient variation con-centrating on the boundary.Thus,the dense deformation field(DDF)is gathered on the boundary and there even appears folding phenomenon.In order to fully leverage the label information,the morphological opening and closing information maps are introduced to enlarge the non-zero gradi-ent regions and improve the accuracy of DDF estimation.The opening information maps supervise the registration model to focus on smaller,narrow brain regions.The closing information maps supervise the registration model to pay more attention to the complex boundary region.Then,opening and closing morphology networks(OC_Net)are designed to automatically generate open-ing and closing information maps to realize the end-to-end training process.Finally,a new registra-tion architecture,VM_(seg+oc),is proposed by combining OC_Net and VoxelMorph.Experimental results show that the registration accuracy of VM_(seg+oc) is significantly improved on LPBA40 and OASIS1 datasets.Especially,VM_(seg+oc) can well improve registration accuracy in smaller brain regions and narrow regions.
基金The research was conducted with funding provided by the National Basic Research Program of China （973 program, No.2014CB046905）, the National Science Foundation of China （Grant No. 41672262）, the State Key Laboratory for Geo mechanics and Deep Underground Engineering （No.SKLGDUEK1303）, and the Department of Communications of Guangdong Province （No.2016）.
文摘Identifying the morphology of rock blocks is vital to accurate modelling of rock mass structures. This paper applies the concepts of directed edges and vertex chain operations which are typical for block tracing approach to block assembling approach to construct the structure of three-dimensional fractured rock masses. Polygon subtraction and union algorithms that rely merely on vertex chain operation are proposed, which allow a fast and convenient construction of complex faces/loops. Apart from its robustness in dealing with finite discontinuities and complex geometries, the advantages of the current methodology in tackling some challenging issues associated with the morphological analysis of rock blocks are addressed. In particular, the identification of complex blocks with interior voids such as cavity, pit and toms can be readily achieved based on the number and the type of loops. The improved morphology visualization approach can benefit the pre-processing stage when analyzing the stability of rock masses subject to various engineering impacts using the block theory and the discrete element method.
