Research in the field ofmedical image is an important part of themedical robot to operate human organs.Amedical robot is the intersection ofmulti-disciplinary research fields,in whichmedical image is an important dire...Research in the field ofmedical image is an important part of themedical robot to operate human organs.Amedical robot is the intersection ofmulti-disciplinary research fields,in whichmedical image is an important direction and has achieved fruitful results.In this paper,amethodof soft tissue surface feature tracking basedonadepthmatching network is proposed.This method is described based on the triangular matching algorithm.First,we construct a self-made sample set for training the depth matching network from the first N frames of speckle matching data obtained by the triangle matching algorithm.The depth matching network is pre-trained on the ORL face data set and then trained on the self-made training set.After the training,the speckle matching is carried out in the subsequent frames to obtain the speckle matching matrix between the subsequent frames and the first frame.From this matrix,the inter-frame feature matching results can be obtained.In this way,the inter-frame speckle tracking is completed.On this basis,the results of this method are compared with the matching results based on the convolutional neural network.The experimental results show that the proposed method has higher matching accuracy.In particular,the accuracy of the MNIST handwritten data set has reached more than 90%.展开更多
A new robust electronic image stabilization system is presented, which involves feature-point, tracking based global motion estimation and Kalman filtering based motion compensation. First, global motion is estimated ...A new robust electronic image stabilization system is presented, which involves feature-point, tracking based global motion estimation and Kalman filtering based motion compensation. First, global motion is estimated from the local motions of selected feature points. Considering the local moving objects or the inevitable mismatch, the matching validation, based on the stable relative distance between the points set is proposed, thus maintaining high accuracy and robustness. Next, the global motion parameters are accumulated for correction by Kalman filteration. The experimental result illustrates that the proposed system is effective to stabilize translational, rotational, and zooming jitter and robust to local motions.展开更多
Facial expression recognition consists of determining what kind of emotional content is presented in a human face. The problem presents a complex area for exploration, since it encompasses face acquisition, facial fea...Facial expression recognition consists of determining what kind of emotional content is presented in a human face. The problem presents a complex area for exploration, since it encompasses face acquisition, facial feature tracking, facial ex- pression classification. Facial feature tracking is of the most interest. Active Appearance Model (AAM) enables accurate tracking of facial features in real-time, but lacks occlusions and self-occlusions. In this paper we propose a solution to improve the accuracy of fitting technique. The idea is to include occluded images into AAM training data. We demonstrate the results by running ex- periments using gradient descent algorithm for fitting the AAM. Our experiments show that using fitting algorithm with occluded training data improves the fitting quality of the algorithm.展开更多
This paper presents a user friendly approach to localize the pupil center with a single web camera.Several methods have been proposed to determine the coordinates of the pupil center in an image,but with practical lim...This paper presents a user friendly approach to localize the pupil center with a single web camera.Several methods have been proposed to determine the coordinates of the pupil center in an image,but with practical limitations.The proposed method can track the user’s eye movements in real time under normal image resolution and lighting conditions using a regular webcam,without special equipment such as infrared illuminators.After the pre-processing steps used to deal with illumination variations,the pupil center is detected using iterative thresholding by applying geometric constraints.Experimental results show that robustness and speed in determining the pupil’s location in real time for users of various ethnicities,under various lighting conditions,at different distances from the webcam and with standard resolution images.展开更多
Moving objects tracking is one of the most used categories in the realm of machine vision that has attracted attention of so many researchers in recent decades. Video tracking has various applications in military indu...Moving objects tracking is one of the most used categories in the realm of machine vision that has attracted attention of so many researchers in recent decades. Video tracking has various applications in military industries, protective systems and machine vision. Target tracking algorithms vary according to their usages. In this paper, it has been attempted to discuss and analyze mobile target tracking techniques and algorithms in Marine.展开更多
Objective To investigate the impact of microvascular obstruction(MVO)on the global and regional myocardial function by cardiac magnetic resonance feature-tracking(CMR-FT)in ST-segment-elevation myocardial infarction(S...Objective To investigate the impact of microvascular obstruction(MVO)on the global and regional myocardial function by cardiac magnetic resonance feature-tracking(CMR-FT)in ST-segment-elevation myocardial infarction(STEMI)patients after percutaneous coronary intervention.Methods Consecutive acute STEMI patients who underwent cardiac magnetic resonance imaging 1-7 days after successful reperfusion by percutaneous coronary intervention treatment were included in this retrospective study.Based on the presence or absence of MVO on late gadolinium enhancement images,patients were divided into groups with MVO and without MVO.The infarct zone,adjacent zone,and remote zone were determined based on a myocardial 16-segment model.The radial strain(RS),circumferential strain(CS),and longitudinal strain(LS)of the global left ventricle(LV)and the infarct,adjacent,and remote zones were measured by CMRFT from cine images and compared between patients with and without MVO using independent-samples t-test.Logistic regression analysis was used to assess the association of MVO with the impaired LV function.Results A total of 157 STEMI patients(mean age 56.66±11.38 years)were enrolled.MVO was detected in 37.58%(59/157)of STEMI patients,and the mean size of MVO was 3.00±3.76 mL.Compared with patients without MVO(n=98),the MVO group had significantly reduced LV global RS(t=-4.30,P<0.001),global CS(t=4.99,P<0.001),and global LS(t=3.51,P=0.001).The RS and CS of the infarct zone in patients with MVO were significantly reduced(t=-3.38,P=0.001;t=2.64,P=0.01;respectively)and the infarct size was significantly larger(t=8.37,P<0.001)than that of patients without MVO.The presence of LV MVO[OR=4.10,95%CI:2.05-8.19,P<0.001]and its size[OR=1.38,95%CI:1.10-1.72,P=0.01],along with the heart rate and LV infarct size were significantly associated with impaired LV global CS in univariable Logistic regression analysis,while only heart rate(OR=1.08,95%CI:1.03-1.13,P=0.001)and LV infarct size(OR=1.10,95%CI:1.03-1.16,P=0.003)were independent influencing factors for the impaired LV global CS in multivariable Logistic regression analysis.Conclusion The infarct size was larger in STEMI patients with MVO,and MVO deteriorates the global and regional LV myocardial function.展开更多
The left atrium(LA) acts as a modulator of left ventricular(LV) filling. Although there is considerable evidence to support the use of LA maximum and minimum volumes for disease prediction,theoretical considerations a...The left atrium(LA) acts as a modulator of left ventricular(LV) filling. Although there is considerable evidence to support the use of LA maximum and minimum volumes for disease prediction,theoretical considerations and a growing body of literature suggest to focus on the quantification of the three basic LA functions:(1) Reservoir function:collection of pulmonary venous return during LV systole;(2) Conduit function:passage of blood to the left ventricle during early LV diastole; and(3) Contractile booster pump function(augmentation of ventricular filling during late LV diastole. Tremendous advances in our ability to non-invasively characterize all three elements of atrial function include speckle tracking echocardiography(STE),and more recently cardiovascular magnetic resonance myocardial feature tracking(CMR-FT). Corresponding imaging biomarkers are increasingly recognized to have incremental roles in determining prognosis and risk stratification in cardiac dysfunction of different origins. The current editorial introduces the role of STE and CMR-FT for the functional assessment of LA deformation as determined by strain and strain rate imaging and provides an outlook of how this exciting field may develop in the future.展开更多
Background:An isolated bicuspid aortic valve(BAV)is associated with structural and functional abnormalities of the aorta and the left ventricle(LV).Although~50%of patients with aortic coarctation(CoA)have a BAV,less i...Background:An isolated bicuspid aortic valve(BAV)is associated with structural and functional abnormalities of the aorta and the left ventricle(LV).Although~50%of patients with aortic coarctation(CoA)have a BAV,less is known about its impact on LV function and aortic geometry and function in CoA patients.In this cardiovascular magnetic resonance imaging(CMR)study,we analysed markers of LV and aortic function as well as aortic geometry in a large cohort of CoA patients with a BAVand compared them with CoA patients with a tricuspid aortic valve(TAV).Methods:We included 48 patients with a BAV(18.4±9.3 years)and 45 patients with TAV(20.7±9.9 years).LV volumes,mass and ejection fraction as well as aortic distensibilty,pulse wave velocity(PWV)were measured from standard cine CMR and phase-contrast CMR images.2-dimensional CMR feature tracking(2DCMR-FT)was performed to measure longitudinal,circumferential and radial strain and strain rate of the LV.Aortic arch geometry was classified as romanic,gothic and crenel.Results:LV volumes,mass and ejection fraction as well as aortic distensibility and PWV did not significantly differ between the BAV and the TAV group.There was also no significant difference for LV global longitudinal,radial and circumferential strain and strain rate between both groups.Patients with a BAV had more commonly a gothic aortic arch compared to TAV patients,but this difference was not statistically significant(22 vs.14,p=0.2).Ascending and descending aortic distensibility correlated with LV mass in the entire patient group(p<0.001).Global longitudinal,circumferential and radial strain(GLS,GCS,GRS)and global longitudinal and circumferential strain rate(GLSR,GCSR)correlated with LV ejection fraction(p<0.001).Conclusion:Our data suggest that the presence of a BAV does not adversely impact LV and aortic function in children and young adults with CoA.The correlation of global circumferential,longitudinal and radial strain values with LV ejection fraction demonstrates that 2D-CMR-FT might provide additional information related to ventricular function in CoA patients.展开更多
Background:The right ventricle to pulmonary artery conduit(RVPAC)may impair right ventricular(RV)function in patients with functional single right ventricles.Modification of the RVPAC using a ring-reinforced end with ...Background:The right ventricle to pulmonary artery conduit(RVPAC)may impair right ventricular(RV)function in patients with functional single right ventricles.Modification of the RVPAC using a ring-reinforced end with dunked insertion into the RV through a limited ventriculotomy may reduce the impact on RV function.We compared RV segmental strain between patients with a traditional RVPAC and ring-reinforced RVPAC using feature tracking cardiovascular magnetic resonance(CMR)imaging.Methods:Patients with CMR examinations after Stage I operation with RVPAC between 2000 and 2018 were reviewed.Ventricular mass,volumes,late gadolinium enhancement(LGE),and peak radial and circumferential strain of the 4 segments near the RVPAC insertion site were analyzed.Results:The study included 71 CMR examinations in 61 patients(30 traditional RVPAC,31 ring-reinforced RVPAC).Prior to Stage II,the ring-reinforced RVPAC group had better peak radial strain and circumferential strain in 1 of 4 segments proximal to the RVPAC insertion site compared to the traditional RVPAC group.Prior to Stage III operation,the ring-reinforced group had better peak radial and circumferential strain in 2 of 4 segments.LGE at the RVPAC insertion site was observed in 97%of patients before Stage II and 95%of patients before Stage III.RVPAC type and regional strain were not associated with transplant-free survival during a median follow-up of 6.3 years.Conclusions:Compared to a traditional RVPAC,the ring-reinforced RVPAC is associated with improved regional mechanics at the conduit insertion site.Further investigation of long-term outcomes after ring-reinforced RVPAC is warranted.展开更多
Target tracking is one typical application of visual servoing technology. It is still a difficult task to track high speed target with current visual servo system. The improvement of visual servoing scheme is strongly...Target tracking is one typical application of visual servoing technology. It is still a difficult task to track high speed target with current visual servo system. The improvement of visual servoing scheme is strongly required. A position-based visual servo parallel system is presented for tracking target with high speed. A local Frenet frame is assigned to the sampling point of spatial trajectory. Position estimation is formed by the differential features of intrinsic geometry, and orientation estimation is formed by homogenous transformation. The time spent for searching and processing can be greatly reduced by shifting the window according to features location prediction. The simulation results have demonstrated the ability of the system to track spatial moving object.展开更多
Effective exploration of spatiotemporal volumetric data sets remains a key challenge in scientific visualization.Although great advances have been made over the years,existing solutions typically focus on only one or ...Effective exploration of spatiotemporal volumetric data sets remains a key challenge in scientific visualization.Although great advances have been made over the years,existing solutions typically focus on only one or two aspects of data analysis and visualization.A streamlined workflow for analyzing time-varying data in a comprehensive and unified manner is still missing.Towards this goal,we present a novel approach for time-varying data visualization that encompasses keyframe identification,feature extraction and tracking under a single,unified framework.At the heart of our approach lies in the GPU-accelerated BlockMatch method,a dense block correspondence technique that extends the PatchMatch method from 2D pixels to 3D voxels.Based on the results of dense correspondence,we are able to identify keyframes from the time sequence using k-medoids clustering along with a bidirectional similarity measure.Furthermore,in conjunction with the graph cut algorithm,this framework enables us to perform fine-grained feature extraction and tracking.We tested our approach using several time-varying data sets to demonstrate its effectiveness and utility.展开更多
基金supported by the Sichuan Science and Technology Program (Grant:2021YFQ0003,Acquired by Wenfeng Zheng).
文摘Research in the field ofmedical image is an important part of themedical robot to operate human organs.Amedical robot is the intersection ofmulti-disciplinary research fields,in whichmedical image is an important direction and has achieved fruitful results.In this paper,amethodof soft tissue surface feature tracking basedonadepthmatching network is proposed.This method is described based on the triangular matching algorithm.First,we construct a self-made sample set for training the depth matching network from the first N frames of speckle matching data obtained by the triangle matching algorithm.The depth matching network is pre-trained on the ORL face data set and then trained on the self-made training set.After the training,the speckle matching is carried out in the subsequent frames to obtain the speckle matching matrix between the subsequent frames and the first frame.From this matrix,the inter-frame feature matching results can be obtained.In this way,the inter-frame speckle tracking is completed.On this basis,the results of this method are compared with the matching results based on the convolutional neural network.The experimental results show that the proposed method has higher matching accuracy.In particular,the accuracy of the MNIST handwritten data set has reached more than 90%.
基金the National Natural Science Foundation (60572152) of China and Science Foundation ofShaanxi Province (2005F26)
文摘A new robust electronic image stabilization system is presented, which involves feature-point, tracking based global motion estimation and Kalman filtering based motion compensation. First, global motion is estimated from the local motions of selected feature points. Considering the local moving objects or the inevitable mismatch, the matching validation, based on the stable relative distance between the points set is proposed, thus maintaining high accuracy and robustness. Next, the global motion parameters are accumulated for correction by Kalman filteration. The experimental result illustrates that the proposed system is effective to stabilize translational, rotational, and zooming jitter and robust to local motions.
文摘Facial expression recognition consists of determining what kind of emotional content is presented in a human face. The problem presents a complex area for exploration, since it encompasses face acquisition, facial feature tracking, facial ex- pression classification. Facial feature tracking is of the most interest. Active Appearance Model (AAM) enables accurate tracking of facial features in real-time, but lacks occlusions and self-occlusions. In this paper we propose a solution to improve the accuracy of fitting technique. The idea is to include occluded images into AAM training data. We demonstrate the results by running ex- periments using gradient descent algorithm for fitting the AAM. Our experiments show that using fitting algorithm with occluded training data improves the fitting quality of the algorithm.
文摘This paper presents a user friendly approach to localize the pupil center with a single web camera.Several methods have been proposed to determine the coordinates of the pupil center in an image,but with practical limitations.The proposed method can track the user’s eye movements in real time under normal image resolution and lighting conditions using a regular webcam,without special equipment such as infrared illuminators.After the pre-processing steps used to deal with illumination variations,the pupil center is detected using iterative thresholding by applying geometric constraints.Experimental results show that robustness and speed in determining the pupil’s location in real time for users of various ethnicities,under various lighting conditions,at different distances from the webcam and with standard resolution images.
文摘Moving objects tracking is one of the most used categories in the realm of machine vision that has attracted attention of so many researchers in recent decades. Video tracking has various applications in military industries, protective systems and machine vision. Target tracking algorithms vary according to their usages. In this paper, it has been attempted to discuss and analyze mobile target tracking techniques and algorithms in Marine.
文摘Objective To investigate the impact of microvascular obstruction(MVO)on the global and regional myocardial function by cardiac magnetic resonance feature-tracking(CMR-FT)in ST-segment-elevation myocardial infarction(STEMI)patients after percutaneous coronary intervention.Methods Consecutive acute STEMI patients who underwent cardiac magnetic resonance imaging 1-7 days after successful reperfusion by percutaneous coronary intervention treatment were included in this retrospective study.Based on the presence or absence of MVO on late gadolinium enhancement images,patients were divided into groups with MVO and without MVO.The infarct zone,adjacent zone,and remote zone were determined based on a myocardial 16-segment model.The radial strain(RS),circumferential strain(CS),and longitudinal strain(LS)of the global left ventricle(LV)and the infarct,adjacent,and remote zones were measured by CMRFT from cine images and compared between patients with and without MVO using independent-samples t-test.Logistic regression analysis was used to assess the association of MVO with the impaired LV function.Results A total of 157 STEMI patients(mean age 56.66±11.38 years)were enrolled.MVO was detected in 37.58%(59/157)of STEMI patients,and the mean size of MVO was 3.00±3.76 mL.Compared with patients without MVO(n=98),the MVO group had significantly reduced LV global RS(t=-4.30,P<0.001),global CS(t=4.99,P<0.001),and global LS(t=3.51,P=0.001).The RS and CS of the infarct zone in patients with MVO were significantly reduced(t=-3.38,P=0.001;t=2.64,P=0.01;respectively)and the infarct size was significantly larger(t=8.37,P<0.001)than that of patients without MVO.The presence of LV MVO[OR=4.10,95%CI:2.05-8.19,P<0.001]and its size[OR=1.38,95%CI:1.10-1.72,P=0.01],along with the heart rate and LV infarct size were significantly associated with impaired LV global CS in univariable Logistic regression analysis,while only heart rate(OR=1.08,95%CI:1.03-1.13,P=0.001)and LV infarct size(OR=1.10,95%CI:1.03-1.16,P=0.003)were independent influencing factors for the impaired LV global CS in multivariable Logistic regression analysis.Conclusion The infarct size was larger in STEMI patients with MVO,and MVO deteriorates the global and regional LV myocardial function.
基金Supported by The DZHK(German Centre for Cardiovascular Research)the BMBF(German Ministry of Education and Research)the Research program of the Faculty of Medicine of the Georg-August-University in G ttingen,Germany
文摘The left atrium(LA) acts as a modulator of left ventricular(LV) filling. Although there is considerable evidence to support the use of LA maximum and minimum volumes for disease prediction,theoretical considerations and a growing body of literature suggest to focus on the quantification of the three basic LA functions:(1) Reservoir function:collection of pulmonary venous return during LV systole;(2) Conduit function:passage of blood to the left ventricle during early LV diastole; and(3) Contractile booster pump function(augmentation of ventricular filling during late LV diastole. Tremendous advances in our ability to non-invasively characterize all three elements of atrial function include speckle tracking echocardiography(STE),and more recently cardiovascular magnetic resonance myocardial feature tracking(CMR-FT). Corresponding imaging biomarkers are increasingly recognized to have incremental roles in determining prognosis and risk stratification in cardiac dysfunction of different origins. The current editorial introduces the role of STE and CMR-FT for the functional assessment of LA deformation as determined by strain and strain rate imaging and provides an outlook of how this exciting field may develop in the future.
基金This study was supported by Deutsches Zentrum für Herz-Kreislaufforschung e.V.
文摘Background:An isolated bicuspid aortic valve(BAV)is associated with structural and functional abnormalities of the aorta and the left ventricle(LV).Although~50%of patients with aortic coarctation(CoA)have a BAV,less is known about its impact on LV function and aortic geometry and function in CoA patients.In this cardiovascular magnetic resonance imaging(CMR)study,we analysed markers of LV and aortic function as well as aortic geometry in a large cohort of CoA patients with a BAVand compared them with CoA patients with a tricuspid aortic valve(TAV).Methods:We included 48 patients with a BAV(18.4±9.3 years)and 45 patients with TAV(20.7±9.9 years).LV volumes,mass and ejection fraction as well as aortic distensibilty,pulse wave velocity(PWV)were measured from standard cine CMR and phase-contrast CMR images.2-dimensional CMR feature tracking(2DCMR-FT)was performed to measure longitudinal,circumferential and radial strain and strain rate of the LV.Aortic arch geometry was classified as romanic,gothic and crenel.Results:LV volumes,mass and ejection fraction as well as aortic distensibility and PWV did not significantly differ between the BAV and the TAV group.There was also no significant difference for LV global longitudinal,radial and circumferential strain and strain rate between both groups.Patients with a BAV had more commonly a gothic aortic arch compared to TAV patients,but this difference was not statistically significant(22 vs.14,p=0.2).Ascending and descending aortic distensibility correlated with LV mass in the entire patient group(p<0.001).Global longitudinal,circumferential and radial strain(GLS,GCS,GRS)and global longitudinal and circumferential strain rate(GLSR,GCSR)correlated with LV ejection fraction(p<0.001).Conclusion:Our data suggest that the presence of a BAV does not adversely impact LV and aortic function in children and young adults with CoA.The correlation of global circumferential,longitudinal and radial strain values with LV ejection fraction demonstrates that 2D-CMR-FT might provide additional information related to ventricular function in CoA patients.
基金This study was supported by Evan’s Heart Fund(RH Rathod).
文摘Background:The right ventricle to pulmonary artery conduit(RVPAC)may impair right ventricular(RV)function in patients with functional single right ventricles.Modification of the RVPAC using a ring-reinforced end with dunked insertion into the RV through a limited ventriculotomy may reduce the impact on RV function.We compared RV segmental strain between patients with a traditional RVPAC and ring-reinforced RVPAC using feature tracking cardiovascular magnetic resonance(CMR)imaging.Methods:Patients with CMR examinations after Stage I operation with RVPAC between 2000 and 2018 were reviewed.Ventricular mass,volumes,late gadolinium enhancement(LGE),and peak radial and circumferential strain of the 4 segments near the RVPAC insertion site were analyzed.Results:The study included 71 CMR examinations in 61 patients(30 traditional RVPAC,31 ring-reinforced RVPAC).Prior to Stage II,the ring-reinforced RVPAC group had better peak radial strain and circumferential strain in 1 of 4 segments proximal to the RVPAC insertion site compared to the traditional RVPAC group.Prior to Stage III operation,the ring-reinforced group had better peak radial and circumferential strain in 2 of 4 segments.LGE at the RVPAC insertion site was observed in 97%of patients before Stage II and 95%of patients before Stage III.RVPAC type and regional strain were not associated with transplant-free survival during a median follow-up of 6.3 years.Conclusions:Compared to a traditional RVPAC,the ring-reinforced RVPAC is associated with improved regional mechanics at the conduit insertion site.Further investigation of long-term outcomes after ring-reinforced RVPAC is warranted.
基金This project is supported by National Electric Power Corporation Foundation of China(No.SPKJ010-27).
文摘Target tracking is one typical application of visual servoing technology. It is still a difficult task to track high speed target with current visual servo system. The improvement of visual servoing scheme is strongly required. A position-based visual servo parallel system is presented for tracking target with high speed. A local Frenet frame is assigned to the sampling point of spatial trajectory. Position estimation is formed by the differential features of intrinsic geometry, and orientation estimation is formed by homogenous transformation. The time spent for searching and processing can be greatly reduced by shifting the window according to features location prediction. The simulation results have demonstrated the ability of the system to track spatial moving object.
文摘Effective exploration of spatiotemporal volumetric data sets remains a key challenge in scientific visualization.Although great advances have been made over the years,existing solutions typically focus on only one or two aspects of data analysis and visualization.A streamlined workflow for analyzing time-varying data in a comprehensive and unified manner is still missing.Towards this goal,we present a novel approach for time-varying data visualization that encompasses keyframe identification,feature extraction and tracking under a single,unified framework.At the heart of our approach lies in the GPU-accelerated BlockMatch method,a dense block correspondence technique that extends the PatchMatch method from 2D pixels to 3D voxels.Based on the results of dense correspondence,we are able to identify keyframes from the time sequence using k-medoids clustering along with a bidirectional similarity measure.Furthermore,in conjunction with the graph cut algorithm,this framework enables us to perform fine-grained feature extraction and tracking.We tested our approach using several time-varying data sets to demonstrate its effectiveness and utility.
