Improving 3D active appearance model segmentation of the left ventricle with Jacobian tuning
K. Y. Esther LeungMarijn van StralenMarco M. VoormolenNico de JongAntonius F.W. van der SteenJohan H. C. ReiberJohan G. Bosch
10
Citation
20
Reference
10
Related Paper
Citation Trend
Abstract:
Automated image processing techniques may prove invaluable in the examination of real-time three-dimensional echocardiograms, by providing quantitative and objective measurements of functional parameters such as left ventricular (LV) volume and ejection fraction. In this study, we investigate the use of active appearance models (AAMs) for automatic detection of left ventricular endocardial contours. AAMs are especially useful in segmenting ultrasound images, due to their ability to model the typical LV appearance. However, since only a limited number of images is available for training, the model may be incapable of capturing the large variability in ultrasound image appearance. This may cause standard AAM matching procedures to fail if the model and image are significantly different. Recently, a Jacobian-tuning method for AAM matching was proposed, which allowed the model's training matrix to adapt to the new, unseen image. This may potentially result in a more robust matching. To compare both matching methods, AAMs were built with end-diastolic images from 54 patients. Larger capture ranges and higher accuracy were obtained when the new method was used. In conclusion, this method has great potential for segmentation in echocardiograms and will improve the assessment of LV functional parameters.Keywords:
Active appearance model
The speed of simulation of power system dynamics has been one of the topics most concerned with on-line security assessment. This paper proposes a new method for forming the constant Jacobian matrix for enhancing the speed of system simulation. By using the constant Jacobian matrix approach in system simulations, both for post-fault and fault-on duration, simulation efficiency is greatly enhanced. Techniques for speeding up the constant Jacobian matrix approach are discussed. Theoretical analysis is presented to demonstrate how the constant Jacobian matrix approach can be extended to a power system with generator controls. Simulation results with the constant Jacobian matrix approach in the 10-generator New England test system and the North China power system are compared with the results obtained by the use of commercial software BPA.
Constant (computer programming)
Matrix (chemical analysis)
Cite
Citations (3)
Visual Servoing
Epipolar geometry
Cite
Citations (8)
An efficient method for Jacobian evaluations in multimode hierarchical circuit simulation is presented. The method evaluates the Jacobian matrix based on the block Jacobian contributions which can be evaluated by various methods for different types of blocks to achieve both accuracy and efficiency. Comparison of the method with the forward-difference method shows considerable improvement in simulation efficiency and convergence.
Cite
Citations (0)
The Jacobian matrix is the core part of power flow analysis, which is the basis for power system planning and operations. This paper estimates the Jacobian matrix in high dimensional space. Firstly, theoretical analysis and model-based calculation of the Jacobian matrix are introduced to obtain the benchmark value. Then, the estimation algorithms based on least-squared errors and the deviation estimation based on the neural network are studied in detail, including the theories, equations, derivations, codes, advantages and disadvantages, and application scenes. The proposed algorithms are data-driven and sensitive to up-to-date topology parameters and state variables. The efforts are validate by comparing the results to benchmark values.
Benchmark (surveying)
Matrix (chemical analysis)
Basis (linear algebra)
Cite
Citations (2)
Manipulator (device)
Cite
Citations (6)
Development of optimal design methods for general 6 degree-of-freedom parallel manipulators is important in obtaining an optimal architecture or pose for the best kinematic performance. Use of a performance index such as the condition number of the Jacobian matrix that is composed of nonhomogeneous physical units may lack physical significance. In order to avoid unit mismatch in the Jacobian matrix, the paper presents a new Jacobian formulation by use of three point generalized coordinates, which results in a (9/spl times/9) dimensionally homogeneous Jacobian matrix. The condition number of the new Jacobian matrix is used to design an optimal architecture or pose of parallel manipulators for best dexterity. A design example with a Gough-Stewart platform parallel manipulator by using the proposed formulation is shown to generate the same optimal configuration as from using the other Jacobian formulation methods.
Optimal design
Stewart platform
Matrix (chemical analysis)
Condition number
Cite
Citations (2)
The velocity Jacobian matrix and the force Jacobian matrix are important index for kinematics, singularity and dynamics analyses of parallel manipulators. A novel computer variation geometric approach is proposed for solving the velocity Jacobian matrix and the force Jacobian matrix of parallel manipulators with linear driving limbs, as well as the determinant of Jacobian matrix. First, basic computer variation geometry techniques and definitions are presented for designing the simulation mechanisms, and several simulation mechanisms of parallel manipulators with linear driving limbs are created. Second, some velocity simulation mechanisms are created and the partial derivatives in Jacobian matrix are solved automatically and visualized dynamically. Based on the results of the computer simulation, the velocity Jacobian matrix and force Jacobian matrix are formed and the determinant of Jacobian matrix is solved. Moreover, the simulation results prove that the computer variation geometry approach is fairly quick and straightforward, and is accurate and repeatable. This project is supported by NSFC No. 50575198.
Matrix (chemical analysis)
Cite
Citations (2)
For solving large systems of nonlinear equations by quasi-Newton methods it may often be preferable to store an approximation to the Jacobian rather than an approximation to the inverse Jacobian. The main reason is that when the Jacobian is sparse and the locations of the zeroes are known, the updating procedure can be made more efficient for the approximate Jacobian than for the approximate inverse Jacobian.
Quasi-Newton method
Cite
Citations (197)
This paper presents the Jacobian analysis of a parallel manipulator that has a fully decoupled 4-DOF remote center-of-motion for application in minimally invasive surgery. Owing to the special structure of the manipulator, the Jacobian matrix of the manipulator is expressed as a combination of three special Jacobian matrices, namely the Jacobian of motion space, Jacobian of constraints, and Jacobian of actuations. Based on these Jacobian matrices, the singular configurations of the manipulator are then identified. It shows that the configuration singularity only exists at the central point and the boundary of the reachable workspace of the manipulator.
Work space
Stewart platform
Cite
Citations (0)
The Jacobian matrix of a dynamical system describes its response to perturbations. Conversely, one can estimate the Jacobian matrix by carefully monitoring how the system responds to environmental noise. We present a closed-form analytical solution for the calculation of a system's Jacobian from a time series. Being able to access the Jacobian enables a broad range of mathematical analyses by which deeper insights into the system can be gained. Here we consider in particular the computation of the leading Jacobian eigenvalue as an early warning signal for critical transitions. To illustrate this approach, we apply it to ecological meta-foodweb models, which are strongly nonlinear dynamical multi-layer networks. Our analysis shows that accurate results can be obtained, although the data demand of the method is still high.
SIGNAL (programming language)
Matrix (chemical analysis)
Cite
Citations (9)