In this study,a non-tensor product B-spline algorithm is applied to the search space of the registration process,and a new method of image non-rigid registration is proposed.The tensor product B-spline is a function d...In this study,a non-tensor product B-spline algorithm is applied to the search space of the registration process,and a new method of image non-rigid registration is proposed.The tensor product B-spline is a function defined in the two directions of x and y,while the non-tensor product B-spline S^(1/2)(Δ_(mn)^((2)))is defined in four directions on the 2-type triangulation.For certain problems,using non-tensor product B-splines to describe the non-rigid deformation of an image can more accurately extract the four-directional information of the image,thereby describing the global or local non-rigid deformation of the image in more directions.Indeed,it provides a method to solve the problem of image deformation in multiple directions.In addition,the region of interest of medical images is irregular,and usually no value exists on the boundary triangle.The value of the basis function of the non-tensor product B-spline on the boundary triangle is only 0.The algorithm process is optimized.The algorithm performs completely automatic non-rigid registration of computed tomography and magnetic resonance imaging images of patients.In particular,this study compares the performance of the proposed algorithm with the tensor product B-spline registration algorithm.The results elucidate that the proposed algorithm clearly improves the accuracy.展开更多
The purpose of the study was to evaluate the effect of motion compensation by non-rigid registration combined with the Karhunen-Loeve Transform (KLT) filter on the signal to noise (SNR) and contrast-to-noise ratio (CN...The purpose of the study was to evaluate the effect of motion compensation by non-rigid registration combined with the Karhunen-Loeve Transform (KLT) filter on the signal to noise (SNR) and contrast-to-noise ratio (CNR) of hybrid gradient-echo echoplanar (GRE-EPI) first-pass myocardial perfusion imaging. Twenty one consecutive first-pass adenosine stress perfusion MR data sets interpreted positive for ischemia or infarction were processed by non-rigid Registration followed by KLT filtering. SNR and CNR were measured in abnormal and normal myocardium in unfiltered and KLT filtered images following nonrigid registration to compensate for respiratory and other motions. Image artifacts introduced by filtering in registered and nonregistered images were evaluated by two observers. There was a statistically sig- nificant increase in both SNR and CNR between normal and abnormal myocardium with KLT filtering (mean SNR increased by 62.18% ± 21.05% and mean CNR increased by 58.84% ± 18.06%;p = 0.01). Motion correction prior to KLT filtering reduced significantly the occurrence of filter induced artifacts (KLT only-artifacts in 42 out of 55 image series vs. registered plus KLT-artifacts in 3 out of 55 image series). In conclusion the combination of non-rigid registration and KLT filtering was shown to increase the SNR and CNR of GRE-EPI perfusion images. Subjective evaluation of image artifacts revealed that prior motion compensation significantly reduced the artifacts introduced by the KLT filtering process.展开更多
A mutual information based 3D non-rigid registration approach was proposed for the registration of deformable CT/MR body abdomen images. The Parzen Windows Density Estimation (PWDE) method is adopted to calculate the ...A mutual information based 3D non-rigid registration approach was proposed for the registration of deformable CT/MR body abdomen images. The Parzen Windows Density Estimation (PWDE) method is adopted to calculate the mutual information between the two modals of CT and MRI abdomen images. By maximizing MI between the CT and MR volume images, the overlapping part of them reaches the biggest, which means that the two body images of CT and MR matches best to each other. Visible Human Project (VHP) Male abdomen CT and MRI Data are used as experimental data sets. The experimental results indicate that this approach of non-rigid 3D registration of CT/MR body abdominal images can be achieved effectively and automatically, without any prior processing procedures such as segmentation and feature extraction, but has a main drawback of very long computation time.展开更多
Optical flow estimation in human facial video,which provides 2D correspondences between adjacent frames,is a fundamental pre-processing step for many applications,like facial expression capture and recognition.However...Optical flow estimation in human facial video,which provides 2D correspondences between adjacent frames,is a fundamental pre-processing step for many applications,like facial expression capture and recognition.However,it is quite challenging as human facial images contain large areas of similar textures,rich expressions,and large rotations.These characteristics also result in the scarcity of large,annotated realworld datasets.We propose a robust and accurate method to learn facial optical flow in a self-supervised manner.Specifically,we utilize various shape priors,including face depth,landmarks,and parsing,to guide the self-supervised learning task via a differentiable nonrigid registration framework.Extensive experiments demonstrate that our method achieves remarkable improvements for facial optical flow estimation in the presence of significant expressions and large rotations.展开更多
Non-rigid registration of point clouds is still far from stable,especially for the largely deformed one.Sparse initial correspondences are often adopted to facilitate the process.However,there are few studies on how t...Non-rigid registration of point clouds is still far from stable,especially for the largely deformed one.Sparse initial correspondences are often adopted to facilitate the process.However,there are few studies on how to build them automatically.Therefore,in this paper,we propose a robust method to compute such priors automatically,where a global and local combined strategy is adopted.These priors in different degrees of deformation are obtained by the locally geometrical-consistent point matches from the globally structural-consistent region correspondences.To further utilize the matches,this paper also proposes a novel registration method based on the Coherent Point Drift framework.This method takes both the spatial proximity and local structural consistency of the priors as supervision of the registration process and thus obtains a robust alignment for clouds with significantly different deformations.Qualitative and quantitative experiments demonstrate the advantages of the proposed method.展开更多
The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target surface.Among the pipeline,the corresp...The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target surface.Among the pipeline,the correspondence construction and iterative manner are key to the results,while existing strategies might result in local optima.In this paper,we adopt the widely used deformation graph-based representation,while replacing some key modules with neural learning-based strategies.Specifically,we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair rejection.Besides,we adopt the GRU-based recurrent network for iterative refinement,which is more robust than the traditional strategy.The model is trained in a self-supervised manner and thus can be used for arbitrary datasets without ground-truth.Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin.展开更多
Many deep learning-based registration methods rely on a single-stream encoder-decoder network for computing deformation fields between 3D volumes.However,these methods often lack constraint information and overlook se...Many deep learning-based registration methods rely on a single-stream encoder-decoder network for computing deformation fields between 3D volumes.However,these methods often lack constraint information and overlook semantic consistency,limiting their performance.To address these issues,we present a novel approach for medical image registration called theDual-VoxelMorph,featuring a dual-channel cross-constraint network.This innovative network utilizes both intensity and segmentation images,which share identical semantic information and feature representations.Two encoder-decoder structures calculate deformation fields for intensity and segmentation images,as generated by the dual-channel cross-constraint network.This design facilitates bidirectional communication between grayscale and segmentation information,enabling the model to better learn the corresponding grayscale and segmentation details of the same anatomical structures.To ensure semantic and directional consistency,we introduce constraints and apply the cosine similarity function to enhance semantic consistency.Evaluation on four public datasets demonstrates superior performance compared to the baselinemethod,achieving Dice scores of 79.9%,64.5%,69.9%,and 63.5%for OASIS-1,OASIS-3,LPBA40,and ADNI,respectively.展开更多
This literature review primarily aims to explore and synthesise the previous studies in simulation education research conducted over the past five years related to the effects of simulation training on the self-effica...This literature review primarily aims to explore and synthesise the previous studies in simulation education research conducted over the past five years related to the effects of simulation training on the self-efficacy of undergraduate pre-registration nursing students. The second aim of this study is to explore additional outcome variables that were examined in the previous studies. Five electronic databases were searched systematically. These databases were MEDLINE, CINAHL Plus, Scopus, Embase and PsycINFO. The PICO model was employed to identify the search terms, with a thesaurus being used to provide synonyms. Reference lists of relevant articles were examined and hand searches of journals were also undertaken. The quality of each study was assessed using the Simulation Research Rubric (SRR). A total of 11 studies were included. All studies explored the impact of simulation education on undergraduate pre-registration nursing. Six studies explored nursing students’ competence and performance and two papers examined their critical thinking. Problem solving, learning motivation, communication skills and knowledge acquisition were examined once. The majority of studies indicated that simulation training has a positive impact on pre-registration nursing students’ self-efficacy and other outcome variables. Furthermore, the study results indicate that simulation training is more dependable than traditional training, and students were extremely satisfied with the simulation training. However, most of the studies included in this review had several gaps, including study design, sample size and dissimilarities between the scales used. Further research with large samples, reliable and valid instruments, and outcomes measures (such as critical thinking and transferability of skills) is required to provide better insight into the effectiveness of simulation in undergraduate nursing education. .展开更多
Compared with the pair-wise registration of point clouds,multi-view point cloud registration is much less studied.In this dissertation,a disordered multi-view point cloud registration method based on the soft trimmed ...Compared with the pair-wise registration of point clouds,multi-view point cloud registration is much less studied.In this dissertation,a disordered multi-view point cloud registration method based on the soft trimmed deep network is proposed.In this method,firstly,the expression ability of feature extraction module is improved and the registration accuracy is increased by enhancing feature extraction network with the point pair feature.Secondly,neighborhood and angle similarities are used to measure the consistency of candidate points to surrounding neighborhoods.By combining distance consistency and high dimensional feature consistency,our network introduces the confidence estimation module of registration,so the point cloud trimmed problem can be converted to candidate for the degree of confidence estimation problem,achieving the pair-wise registration of partially overlapping point clouds.Thirdly,the results from pair-wise registration are fed into the model fusion to achieve the rough registration of multi-view point clouds.Finally,the hierarchical clustering is used to iteratively optimize the clustering center model by gradually increasing the number of clustering categories and performing clustering and registration alternately.This method achieves rough point cloud registration quickly in the early stage,improves the accuracy of multi-view point cloud registration in the later stage,and makes full use of global information to achieve robust and accurate multi-view registration without initial value.展开更多
BACKGROUND It has been confirmed that three-dimensional(3D)imaging allows easier identification of bile duct anatomy and intraoperative guidance of endoscopic retrograde cholangiopancreatography(ERCP),which reduces th...BACKGROUND It has been confirmed that three-dimensional(3D)imaging allows easier identification of bile duct anatomy and intraoperative guidance of endoscopic retrograde cholangiopancreatography(ERCP),which reduces the radiation dose and procedure time with improved safety.However,current 3D biliary imaging does not have good real-time fusion with intraoperative imaging,a process meant to overcome the influence of intraoperative respiratory motion and guide navigation.The present study explored the feasibility of real-time continuous image-guided ERCP.AIM To explore the feasibility of real-time continuous image-guided ERCP.METHODS We selected 23D-printed abdominal biliary tract models with different structures to simulate different patients.The ERCP environment was simulated for the biliary phantom experiment to create a navigation system,which was further tested in patients.In addition,based on the estimation of the patient’s respiratory motion,preoperative 3D biliary imaging from computed tomography of 18 patients with cholelithiasis was registered and fused in real-time with 2D fluoroscopic sequence generated by the C-arm unit during ERCP.RESULTS Continuous image-guided ERCP was applied in the biliary phantom with a registration error of 0.46 mm±0.13 mm and a tracking error of 0.64 mm±0.24mm.After estimating the respiratory motion,3D/2D registration accurately transformed preoperative 3D biliary images to each image in the X-ray image sequence in real-time in 18 patients,with an average fusion rate of 88%.CONCLUSION Continuous image-guided ERCP may be an effective approach to assist the operator and reduce the use of X-ray and contrast agents.展开更多
Airborne laser scanning(ALS)and terrestrial laser scanning(TLS)has attracted attention due to their forest parameter investigation and research applications.ALS is limited to obtaining fi ne structure information belo...Airborne laser scanning(ALS)and terrestrial laser scanning(TLS)has attracted attention due to their forest parameter investigation and research applications.ALS is limited to obtaining fi ne structure information below the forest canopy due to the occlusion of trees in natural forests.In contrast,TLS is unable to gather fi ne structure information about the upper canopy.To address the problem of incomplete acquisition of natural forest point cloud data by ALS and TLS on a single platform,this study proposes data registration without control points.The ALS and TLS original data were cropped according to sample plot size,and the ALS point cloud data was converted into relative coordinates with the center of the cropped data as the origin.The same feature point pairs of the ALS and TLS point cloud data were then selected to register the point cloud data.The initial registered point cloud data was fi nely and optimally registered via the iterative closest point(ICP)algorithm.The results show that the proposed method achieved highprecision registration of ALS and TLS point cloud data from two natural forest plots of Pinus yunnanensis Franch.and Picea asperata Mast.which included diff erent species and environments.An average registration accuracy of 0.06 m and 0.09 m were obtained for P.yunnanensis and P.asperata,respectively.展开更多
Multi‐modal brain image registration has been widely applied to functional localisation,neurosurgery and computational anatomy.The existing registration methods based on the dense deformation fields involve too many ...Multi‐modal brain image registration has been widely applied to functional localisation,neurosurgery and computational anatomy.The existing registration methods based on the dense deformation fields involve too many parameters,which is not conducive to the exploration of correct spatial correspondence between the float and reference images.Meanwhile,the unidirectional registration may involve the deformation folding,which will result in the change of topology during registration.To address these issues,this work has presented an unsupervised image registration method using the free form deformation(FFD)and the symmetry constraint‐based generative adversarial networks(FSGAN).The FSGAN utilises the principle component analysis network‐based structural representations of the reference and float images as the inputs and uses the generator to learn the FFD model parameters,thereby producing two deformation fields.Meanwhile,the FSGAN uses two discriminators to decide whether the bilateral registration have been realised simultaneously.Besides,the symmetry constraint is utilised to construct the loss function,thereby avoiding the deformation folding.Experiments on BrainWeb,high grade gliomas,IXI and LPBA40 show that compared with state‐of‐the‐art methods,the FSGAN provides superior performance in terms of visual comparisons and such quantitative indexes as dice value,target registration error and computational efficiency.展开更多
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
Three-dimensional(3D)shape registration is a challenging problem,especially for shapes under non-rigid transformations.In this paper,a 3D non-rigid shape registration method is proposed,called balanced functional maps...Three-dimensional(3D)shape registration is a challenging problem,especially for shapes under non-rigid transformations.In this paper,a 3D non-rigid shape registration method is proposed,called balanced functional maps(BFM).The BFM algorithm generalizes the point-based correspondence to functions.By choosing the Laplace-Beltrami eigenfunctions as the function basis,the transformations between shapes can be represented by the functional map(FM)matrix.In addition,many constraints on shape registration,such as the feature descriptor,keypoint,and salient region correspondence,can be formulated linearly using the matrix.By bi-directionally searching for the nearest neighbors of points’indicator functions in the function space,the point-based correspondence can be derived from FMs.We conducted several experiments on the Topology and Orchestration Specification for Cloud Applications(TOSCA)dataset and the Shape Completion and Animation of People(SCAPE)dataset.Experimental results show that the proposed BFM algorithm is effective and has superior performance than the state-of-the-art methods on both datasets.展开更多
Due to the importance of vibration effects on the functional accuracy of mechanical systems,this research aims to develop a precise model of a nonlinearly vibrating single-link mobile flexible manipulator.The manipula...Due to the importance of vibration effects on the functional accuracy of mechanical systems,this research aims to develop a precise model of a nonlinearly vibrating single-link mobile flexible manipulator.The manipulator consists of an elastic arm,a rotary motor,and a rigid carrier,and undergoes general in-plane rigid body motion along with elastic transverse deformation.To accurately model the elastic behavior,Timoshenko’s beam theory is used to describe the flexible arm,which accounts for rotary inertia and shear deformation effects.By applying Newton’s second law,the nonlinear governing equations of motion for the manipulator are derived as a coupled system of ordinary differential equations(ODEs)and partial differential equations(PDEs).Then,the assumed mode method(AMM)is used to solve this nonlinear system of governing equations with appropriate shape functions.The assumed modes can be obtained after solving the characteristic equation of a Timoshenko beam with clamped boundary conditions at one end and an attached mass/inertia at the other.In addition,the effect of the transverse vibration of the inextensible arm on its axial behavior is investigated.Despite the axial rigidity,the effect makes the rigid body dynamics invalid for the axial behavior of the arm.Finally,numerical simulations are conducted to evaluate the performance of the developed model,and the results are compared with those obtained by the finite element approach.The comparison confirms the validity of the proposed dynamic model for the system.According to the mentioned features,this model can be reliable for investigating the system’s vibrational behavior and implementing vibration control algorithms.展开更多
A mutual information-based non-rigid medical image registration algorithm is presented. An approximate function of Hanning windowed sinc is used as kernel function of partial volume (PV) interpolation to estimate the ...A mutual information-based non-rigid medical image registration algorithm is presented. An approximate function of Hanning windowed sinc is used as kernel function of partial volume (PV) interpolation to estimate the joint histogram, which is the key to calculating the mutual information. And a new method is proposed to compute the gradient of mutual information with respect to the model parameters. The transformation of object is modeled by a free-form deformation (FFD) based on B-splines. The experiments on 3D synthetic and real image data show that the algorithm can converge at the global optimum and restrain the emergency of local extreme.展开更多
An intensity-based non-rigid registration algorithm is discussed, which uses Gaussian smoothing to constrain the transformation to be smooth, and thus preserves the topology of images. In view of the insufficiency of ...An intensity-based non-rigid registration algorithm is discussed, which uses Gaussian smoothing to constrain the transformation to be smooth, and thus preserves the topology of images. In view of the insufficiency of the uniform Gaussian filtering of the deformation field, an automatic and accurate non-rigid image registration method based on B-splines approximation is proposed. The regularization strategy is adopted by using multi-level B-splines approximation to regularize the displacement fields in a coarse-to-fine manner. Moreover, it assigns the different weights to the estimated displacements according to their reliabilities. In this way, the level of regularity can be adapted locally. Experiments were performed on both synthetic and real medical images of brain, and the results show that the proposed method improves the registration accuracy and robustness.展开更多
Point features, as the basis of lines, surfaces, and bodies, are commonly used in medical image registration. To obtain an elegant spatial transformation of extracted feature points, many point set matching algorithms...Point features, as the basis of lines, surfaces, and bodies, are commonly used in medical image registration. To obtain an elegant spatial transformation of extracted feature points, many point set matching algorithms(PMs) have been developed to match two point sets by optimizing multifarious distance functions. There are ample reviews related to medical image registration and PMs which summarize their basic principles and main algorithms separately. However,to data, detailed summary of PMs used in medical image registration in different clinical environments has not been published. In this paper, we provide a comprehensive review of the existing key techniques of the PMs applied to medical image registration according to the basic principles and clinical applications. As the core technique of the PMs, geometric transformation models are elaborated in this paper, demonstrating the mechanism of point set registration. We also focus on the clinical applications of the PMs and propose a practical classification method according to their applications in different clinical surgeries. The aim of this paper is to provide a summary of pointfeaturebased methods used in medical image registration and to guide doctors or researchers interested in this field to choose appropriate techniques in their research.展开更多
The iterative closest point(ICP)algorithm has the advantages of high accuracy and fast speed for point set registration,but it performs poorly when the point set has a large number of noisy outliers.To solve this prob...The iterative closest point(ICP)algorithm has the advantages of high accuracy and fast speed for point set registration,but it performs poorly when the point set has a large number of noisy outliers.To solve this problem,we propose a new affine registration algorithm based on correntropy which works well in the affine registration of point sets with outliers.Firstly,we substitute the traditional measure of least squares with a maximum correntropy criterion to build a new registration model,which can avoid the influence of outliers.To maximize the objective function,we then propose a robust affine ICP algorithm.At each iteration of this new algorithm,we set up the index mapping of two point sets according to the known transformation,and then compute the closed-form solution of the new transformation according to the known index mapping.Similar to the traditional ICP algorithm,our algorithm converges to a local maximum monotonously for any given initial value.Finally,the robustness and high efficiency of affine ICP algorithm based on correntropy are demonstrated by 2D and 3D point set registration experiments.展开更多
基金This research was funded by National Natural Science Foundation of China,No.61702184Ministry of Education Production University Cooperation Education Project,No.201802305012Tangshan Innovation Team Project,No.18130209 B.
文摘In this study,a non-tensor product B-spline algorithm is applied to the search space of the registration process,and a new method of image non-rigid registration is proposed.The tensor product B-spline is a function defined in the two directions of x and y,while the non-tensor product B-spline S^(1/2)(Δ_(mn)^((2)))is defined in four directions on the 2-type triangulation.For certain problems,using non-tensor product B-splines to describe the non-rigid deformation of an image can more accurately extract the four-directional information of the image,thereby describing the global or local non-rigid deformation of the image in more directions.Indeed,it provides a method to solve the problem of image deformation in multiple directions.In addition,the region of interest of medical images is irregular,and usually no value exists on the boundary triangle.The value of the basis function of the non-tensor product B-spline on the boundary triangle is only 0.The algorithm process is optimized.The algorithm performs completely automatic non-rigid registration of computed tomography and magnetic resonance imaging images of patients.In particular,this study compares the performance of the proposed algorithm with the tensor product B-spline registration algorithm.The results elucidate that the proposed algorithm clearly improves the accuracy.
文摘The purpose of the study was to evaluate the effect of motion compensation by non-rigid registration combined with the Karhunen-Loeve Transform (KLT) filter on the signal to noise (SNR) and contrast-to-noise ratio (CNR) of hybrid gradient-echo echoplanar (GRE-EPI) first-pass myocardial perfusion imaging. Twenty one consecutive first-pass adenosine stress perfusion MR data sets interpreted positive for ischemia or infarction were processed by non-rigid Registration followed by KLT filtering. SNR and CNR were measured in abnormal and normal myocardium in unfiltered and KLT filtered images following nonrigid registration to compensate for respiratory and other motions. Image artifacts introduced by filtering in registered and nonregistered images were evaluated by two observers. There was a statistically sig- nificant increase in both SNR and CNR between normal and abnormal myocardium with KLT filtering (mean SNR increased by 62.18% ± 21.05% and mean CNR increased by 58.84% ± 18.06%;p = 0.01). Motion correction prior to KLT filtering reduced significantly the occurrence of filter induced artifacts (KLT only-artifacts in 42 out of 55 image series vs. registered plus KLT-artifacts in 3 out of 55 image series). In conclusion the combination of non-rigid registration and KLT filtering was shown to increase the SNR and CNR of GRE-EPI perfusion images. Subjective evaluation of image artifacts revealed that prior motion compensation significantly reduced the artifacts introduced by the KLT filtering process.
基金An international cooperation project between Shanghai Jiaotong U niversity and Hong Kong Polytechnic University
文摘A mutual information based 3D non-rigid registration approach was proposed for the registration of deformable CT/MR body abdomen images. The Parzen Windows Density Estimation (PWDE) method is adopted to calculate the mutual information between the two modals of CT and MRI abdomen images. By maximizing MI between the CT and MR volume images, the overlapping part of them reaches the biggest, which means that the two body images of CT and MR matches best to each other. Visible Human Project (VHP) Male abdomen CT and MRI Data are used as experimental data sets. The experimental results indicate that this approach of non-rigid 3D registration of CT/MR body abdominal images can be achieved effectively and automatically, without any prior processing procedures such as segmentation and feature extraction, but has a main drawback of very long computation time.
基金This work was supported by National Natural Science Foundation of China(No.62122071)the Youth Innovation Promotion Association CAS(No.2018495)+1 种基金the Fundamental Research Funds for the Central Universities(No.WK3470000021)through the Alibaba Innovation Research Program(AIR).
文摘Optical flow estimation in human facial video,which provides 2D correspondences between adjacent frames,is a fundamental pre-processing step for many applications,like facial expression capture and recognition.However,it is quite challenging as human facial images contain large areas of similar textures,rich expressions,and large rotations.These characteristics also result in the scarcity of large,annotated realworld datasets.We propose a robust and accurate method to learn facial optical flow in a self-supervised manner.Specifically,we utilize various shape priors,including face depth,landmarks,and parsing,to guide the self-supervised learning task via a differentiable nonrigid registration framework.Extensive experiments demonstrate that our method achieves remarkable improvements for facial optical flow estimation in the presence of significant expressions and large rotations.
基金supported by Natural Science Foundation of Anhui Province (2108085MF210,1908085MF187)Key Natural Science Fund of Department of Eduction of Anhui Province (KJ2021A0042)Natural Social Science Foundation of China (19BTY091).
文摘Non-rigid registration of point clouds is still far from stable,especially for the largely deformed one.Sparse initial correspondences are often adopted to facilitate the process.However,there are few studies on how to build them automatically.Therefore,in this paper,we propose a robust method to compute such priors automatically,where a global and local combined strategy is adopted.These priors in different degrees of deformation are obtained by the locally geometrical-consistent point matches from the globally structural-consistent region correspondences.To further utilize the matches,this paper also proposes a novel registration method based on the Coherent Point Drift framework.This method takes both the spatial proximity and local structural consistency of the priors as supervision of the registration process and thus obtains a robust alignment for clouds with significantly different deformations.Qualitative and quantitative experiments demonstrate the advantages of the proposed method.
基金supported by National Natural Science Foundation of China(No.62122071)the Youth Innovation Promotion Association CAS(No.2018495)“the Fundamental Research Funds for the Central Universities”(No.WK3470000021).
文摘The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target surface.Among the pipeline,the correspondence construction and iterative manner are key to the results,while existing strategies might result in local optima.In this paper,we adopt the widely used deformation graph-based representation,while replacing some key modules with neural learning-based strategies.Specifically,we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair rejection.Besides,we adopt the GRU-based recurrent network for iterative refinement,which is more robust than the traditional strategy.The model is trained in a self-supervised manner and thus can be used for arbitrary datasets without ground-truth.Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin.
基金National Natural Science Foundation of China(Grant Nos.62171130,62172197,61972093)the Natural Science Foundation of Fujian Province(Grant Nos.2020J01573,2022J01131257,2022J01607)+3 种基金Fujian University Industry University Research Joint Innovation Project(No.2022H6006)in part by the Fund of Cloud Computing and BigData for SmartAgriculture(GrantNo.117-612014063)NationalNatural Science Foundation of China(Grant No.62301160)Nature Science Foundation of Fujian Province(Grant No.2022J01607).
文摘Many deep learning-based registration methods rely on a single-stream encoder-decoder network for computing deformation fields between 3D volumes.However,these methods often lack constraint information and overlook semantic consistency,limiting their performance.To address these issues,we present a novel approach for medical image registration called theDual-VoxelMorph,featuring a dual-channel cross-constraint network.This innovative network utilizes both intensity and segmentation images,which share identical semantic information and feature representations.Two encoder-decoder structures calculate deformation fields for intensity and segmentation images,as generated by the dual-channel cross-constraint network.This design facilitates bidirectional communication between grayscale and segmentation information,enabling the model to better learn the corresponding grayscale and segmentation details of the same anatomical structures.To ensure semantic and directional consistency,we introduce constraints and apply the cosine similarity function to enhance semantic consistency.Evaluation on four public datasets demonstrates superior performance compared to the baselinemethod,achieving Dice scores of 79.9%,64.5%,69.9%,and 63.5%for OASIS-1,OASIS-3,LPBA40,and ADNI,respectively.
文摘This literature review primarily aims to explore and synthesise the previous studies in simulation education research conducted over the past five years related to the effects of simulation training on the self-efficacy of undergraduate pre-registration nursing students. The second aim of this study is to explore additional outcome variables that were examined in the previous studies. Five electronic databases were searched systematically. These databases were MEDLINE, CINAHL Plus, Scopus, Embase and PsycINFO. The PICO model was employed to identify the search terms, with a thesaurus being used to provide synonyms. Reference lists of relevant articles were examined and hand searches of journals were also undertaken. The quality of each study was assessed using the Simulation Research Rubric (SRR). A total of 11 studies were included. All studies explored the impact of simulation education on undergraduate pre-registration nursing. Six studies explored nursing students’ competence and performance and two papers examined their critical thinking. Problem solving, learning motivation, communication skills and knowledge acquisition were examined once. The majority of studies indicated that simulation training has a positive impact on pre-registration nursing students’ self-efficacy and other outcome variables. Furthermore, the study results indicate that simulation training is more dependable than traditional training, and students were extremely satisfied with the simulation training. However, most of the studies included in this review had several gaps, including study design, sample size and dissimilarities between the scales used. Further research with large samples, reliable and valid instruments, and outcomes measures (such as critical thinking and transferability of skills) is required to provide better insight into the effectiveness of simulation in undergraduate nursing education. .
文摘Compared with the pair-wise registration of point clouds,multi-view point cloud registration is much less studied.In this dissertation,a disordered multi-view point cloud registration method based on the soft trimmed deep network is proposed.In this method,firstly,the expression ability of feature extraction module is improved and the registration accuracy is increased by enhancing feature extraction network with the point pair feature.Secondly,neighborhood and angle similarities are used to measure the consistency of candidate points to surrounding neighborhoods.By combining distance consistency and high dimensional feature consistency,our network introduces the confidence estimation module of registration,so the point cloud trimmed problem can be converted to candidate for the degree of confidence estimation problem,achieving the pair-wise registration of partially overlapping point clouds.Thirdly,the results from pair-wise registration are fed into the model fusion to achieve the rough registration of multi-view point clouds.Finally,the hierarchical clustering is used to iteratively optimize the clustering center model by gradually increasing the number of clustering categories and performing clustering and registration alternately.This method achieves rough point cloud registration quickly in the early stage,improves the accuracy of multi-view point cloud registration in the later stage,and makes full use of global information to achieve robust and accurate multi-view registration without initial value.
文摘BACKGROUND It has been confirmed that three-dimensional(3D)imaging allows easier identification of bile duct anatomy and intraoperative guidance of endoscopic retrograde cholangiopancreatography(ERCP),which reduces the radiation dose and procedure time with improved safety.However,current 3D biliary imaging does not have good real-time fusion with intraoperative imaging,a process meant to overcome the influence of intraoperative respiratory motion and guide navigation.The present study explored the feasibility of real-time continuous image-guided ERCP.AIM To explore the feasibility of real-time continuous image-guided ERCP.METHODS We selected 23D-printed abdominal biliary tract models with different structures to simulate different patients.The ERCP environment was simulated for the biliary phantom experiment to create a navigation system,which was further tested in patients.In addition,based on the estimation of the patient’s respiratory motion,preoperative 3D biliary imaging from computed tomography of 18 patients with cholelithiasis was registered and fused in real-time with 2D fluoroscopic sequence generated by the C-arm unit during ERCP.RESULTS Continuous image-guided ERCP was applied in the biliary phantom with a registration error of 0.46 mm±0.13 mm and a tracking error of 0.64 mm±0.24mm.After estimating the respiratory motion,3D/2D registration accurately transformed preoperative 3D biliary images to each image in the X-ray image sequence in real-time in 18 patients,with an average fusion rate of 88%.CONCLUSION Continuous image-guided ERCP may be an effective approach to assist the operator and reduce the use of X-ray and contrast agents.
基金supported by the National Natural Science Foundation of China,Grant Number 41961060by the Program for Innovative Research Team (in Science and Technology) in the University of Yunnan Province,Grant Number IRTSTYN+1 种基金by the Scientific Research Fund Project of the Education Department of Yunnan Province,Grant Numbers 2020J0256 and 2021J0438by the Postgraduate Scientific Research and Innovation Fund Project of Yunnan Normal University,Grant Number YJSJJ21-A08
文摘Airborne laser scanning(ALS)and terrestrial laser scanning(TLS)has attracted attention due to their forest parameter investigation and research applications.ALS is limited to obtaining fi ne structure information below the forest canopy due to the occlusion of trees in natural forests.In contrast,TLS is unable to gather fi ne structure information about the upper canopy.To address the problem of incomplete acquisition of natural forest point cloud data by ALS and TLS on a single platform,this study proposes data registration without control points.The ALS and TLS original data were cropped according to sample plot size,and the ALS point cloud data was converted into relative coordinates with the center of the cropped data as the origin.The same feature point pairs of the ALS and TLS point cloud data were then selected to register the point cloud data.The initial registered point cloud data was fi nely and optimally registered via the iterative closest point(ICP)algorithm.The results show that the proposed method achieved highprecision registration of ALS and TLS point cloud data from two natural forest plots of Pinus yunnanensis Franch.and Picea asperata Mast.which included diff erent species and environments.An average registration accuracy of 0.06 m and 0.09 m were obtained for P.yunnanensis and P.asperata,respectively.
基金supported in part by the National Key Research and Development Program of China under Grant 2018Y FE0206900in part by the National Natural Science Foundation of China under Grant 61871440in part by the CAAIHuawei MindSpore Open Fund.We gratefully acknowledge the support of MindSpore for this research.
文摘Multi‐modal brain image registration has been widely applied to functional localisation,neurosurgery and computational anatomy.The existing registration methods based on the dense deformation fields involve too many parameters,which is not conducive to the exploration of correct spatial correspondence between the float and reference images.Meanwhile,the unidirectional registration may involve the deformation folding,which will result in the change of topology during registration.To address these issues,this work has presented an unsupervised image registration method using the free form deformation(FFD)and the symmetry constraint‐based generative adversarial networks(FSGAN).The FSGAN utilises the principle component analysis network‐based structural representations of the reference and float images as the inputs and uses the generator to learn the FFD model parameters,thereby producing two deformation fields.Meanwhile,the FSGAN uses two discriminators to decide whether the bilateral registration have been realised simultaneously.Besides,the symmetry constraint is utilised to construct the loss function,thereby avoiding the deformation folding.Experiments on BrainWeb,high grade gliomas,IXI and LPBA40 show that compared with state‐of‐the‐art methods,the FSGAN provides superior performance in terms of visual comparisons and such quantitative indexes as dice value,target registration error and computational efficiency.
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 China Scholarship Council under Grant No.201406070059.
文摘Three-dimensional(3D)shape registration is a challenging problem,especially for shapes under non-rigid transformations.In this paper,a 3D non-rigid shape registration method is proposed,called balanced functional maps(BFM).The BFM algorithm generalizes the point-based correspondence to functions.By choosing the Laplace-Beltrami eigenfunctions as the function basis,the transformations between shapes can be represented by the functional map(FM)matrix.In addition,many constraints on shape registration,such as the feature descriptor,keypoint,and salient region correspondence,can be formulated linearly using the matrix.By bi-directionally searching for the nearest neighbors of points’indicator functions in the function space,the point-based correspondence can be derived from FMs.We conducted several experiments on the Topology and Orchestration Specification for Cloud Applications(TOSCA)dataset and the Shape Completion and Animation of People(SCAPE)dataset.Experimental results show that the proposed BFM algorithm is effective and has superior performance than the state-of-the-art methods on both datasets.
文摘Due to the importance of vibration effects on the functional accuracy of mechanical systems,this research aims to develop a precise model of a nonlinearly vibrating single-link mobile flexible manipulator.The manipulator consists of an elastic arm,a rotary motor,and a rigid carrier,and undergoes general in-plane rigid body motion along with elastic transverse deformation.To accurately model the elastic behavior,Timoshenko’s beam theory is used to describe the flexible arm,which accounts for rotary inertia and shear deformation effects.By applying Newton’s second law,the nonlinear governing equations of motion for the manipulator are derived as a coupled system of ordinary differential equations(ODEs)and partial differential equations(PDEs).Then,the assumed mode method(AMM)is used to solve this nonlinear system of governing equations with appropriate shape functions.The assumed modes can be obtained after solving the characteristic equation of a Timoshenko beam with clamped boundary conditions at one end and an attached mass/inertia at the other.In addition,the effect of the transverse vibration of the inextensible arm on its axial behavior is investigated.Despite the axial rigidity,the effect makes the rigid body dynamics invalid for the axial behavior of the arm.Finally,numerical simulations are conducted to evaluate the performance of the developed model,and the results are compared with those obtained by the finite element approach.The comparison confirms the validity of the proposed dynamic model for the system.According to the mentioned features,this model can be reliable for investigating the system’s vibrational behavior and implementing vibration control algorithms.
基金Supported bythe National Basic Research Programof China ("973"Program) (No2003CB716103)Key Project of Shanghai Scienceand Technology Committee(No05DZ19509)
文摘A mutual information-based non-rigid medical image registration algorithm is presented. An approximate function of Hanning windowed sinc is used as kernel function of partial volume (PV) interpolation to estimate the joint histogram, which is the key to calculating the mutual information. And a new method is proposed to compute the gradient of mutual information with respect to the model parameters. The transformation of object is modeled by a free-form deformation (FFD) based on B-splines. The experiments on 3D synthetic and real image data show that the algorithm can converge at the global optimum and restrain the emergency of local extreme.
基金Supported by National Natural Science Foundation of China (No60373061)Joint Programof National Natural Science Foundation of ChinaGeneral Administration of Civil Aviation of China (No60672168)
文摘An intensity-based non-rigid registration algorithm is discussed, which uses Gaussian smoothing to constrain the transformation to be smooth, and thus preserves the topology of images. In view of the insufficiency of the uniform Gaussian filtering of the deformation field, an automatic and accurate non-rigid image registration method based on B-splines approximation is proposed. The regularization strategy is adopted by using multi-level B-splines approximation to regularize the displacement fields in a coarse-to-fine manner. Moreover, it assigns the different weights to the estimated displacements according to their reliabilities. In this way, the level of regularity can be adapted locally. Experiments were performed on both synthetic and real medical images of brain, and the results show that the proposed method improves the registration accuracy and robustness.
基金Supported by the National Natural Science Foundation of China(Grant No.61533016)
文摘Point features, as the basis of lines, surfaces, and bodies, are commonly used in medical image registration. To obtain an elegant spatial transformation of extracted feature points, many point set matching algorithms(PMs) have been developed to match two point sets by optimizing multifarious distance functions. There are ample reviews related to medical image registration and PMs which summarize their basic principles and main algorithms separately. However,to data, detailed summary of PMs used in medical image registration in different clinical environments has not been published. In this paper, we provide a comprehensive review of the existing key techniques of the PMs applied to medical image registration according to the basic principles and clinical applications. As the core technique of the PMs, geometric transformation models are elaborated in this paper, demonstrating the mechanism of point set registration. We also focus on the clinical applications of the PMs and propose a practical classification method according to their applications in different clinical surgeries. The aim of this paper is to provide a summary of pointfeaturebased methods used in medical image registration and to guide doctors or researchers interested in this field to choose appropriate techniques in their research.
基金supported in part by the National Natural Science Foundation of China(61627811,61573274,61673126,U1701261)
文摘The iterative closest point(ICP)algorithm has the advantages of high accuracy and fast speed for point set registration,but it performs poorly when the point set has a large number of noisy outliers.To solve this problem,we propose a new affine registration algorithm based on correntropy which works well in the affine registration of point sets with outliers.Firstly,we substitute the traditional measure of least squares with a maximum correntropy criterion to build a new registration model,which can avoid the influence of outliers.To maximize the objective function,we then propose a robust affine ICP algorithm.At each iteration of this new algorithm,we set up the index mapping of two point sets according to the known transformation,and then compute the closed-form solution of the new transformation according to the known index mapping.Similar to the traditional ICP algorithm,our algorithm converges to a local maximum monotonously for any given initial value.Finally,the robustness and high efficiency of affine ICP algorithm based on correntropy are demonstrated by 2D and 3D point set registration experiments.