Yi Su

Framingham State University, Framingham, Massachusetts, United States

Are you Yi Su?

Claim your profile

Publications (31)23.6 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this work, we present a method to assess left ventricle (LV) regional function from cardiac magnetic resonance (CMR) imaging based on the regional ejection fraction (REF) and regional area strain (RAS). CMR scans were performed for 30 patients after first-time myocardial infarction (MI) and nine age- and sex-matched healthy volunteers. The CMR images were processed to reconstruct three-dimensional LV geometry, and the REF and RAS in a 16-segment model were computed using our proposed methodology. The method of computing the REF was tested and shown to be robust against variation in user input. Furthermore, analysis of data was feasible in all patients and healthy volunteers without any exclusions. The REF correlated well with the RAS in a nonlinear manner (quadratic fit-R(2) = 0.88). In patients after first-time MI, the REF and RAS were significantly reduced across all 16 segments (REF: p < 0.05; RAS: p < 0.01). Moreover, the REF and RAS significantly decreased with the extent of transmural scar obtained from late gadolinium-enhanced CMR images. In addition, we show that the REF and RAS can be used to identify regions with compromised function in the patients with preserved global ejection fraction with reasonable accuracy (more than 78%). These preliminary results confirmed the validity of our approach for accurate analysis of LV regional function. Our approach potentially offers physicians new insights into the local characteristics of the myocardial mechanics after a MI. © 2015 The Author(s) Published by the Royal Society. All rights reserved.
    Journal of the Royal Society, Interface / the Royal Society. 04/2015; 12(105).
  • [Show abstract] [Hide abstract]
    ABSTRACT: An interactive surgical simulation system needs to meet three main requirements, speed, accuracy and stability. In this paper, we present a stable and accurate method for animating mass-spring systems in real-time. An integration scheme derived from explicit integration is used to obtain interactive realistic animation for a multi-object environment. We explore a predictor-corrector approach by correcting the estimation of the explicit integration in a post-step process. We introduce novel constraints on positions into the Mass-Spring Model (MSM) to model the non-linearity and preserve volume for the realistic simulation of the incompressibility. We verify the proposed MSM by comparing its deformations with the reference deformations of the nonlinear finite element method. Moreover, experiments on porcine organs are designed for the evaluation of the multiobject deformation. Using a pair of freshly harvested porcine liver and gallbladder, the real organ deformations are acquired by computed tomography and used as the reference ground truth. Compared to the porcine model, our model achieves a 1:502 mm mean absolute error measured at landmark locations for cases with small deformation (the largest deformation is 49:109 mm) and a 3:639 mm mean absolute error for cases with large deformation (the largest deformation is 83:137 mm). The changes of volume for the two deformations are limited to 0:030% and 0:057%, respectively. Finally, an implementation in a virtual reality environment for laparoscopic cholecystectomy demonstrates that our model is capable to simulate large deformation and preserve volume in real-time calculations.
    IEEE Journal of Biomedical and Health Informatics 11/2014; · 1.98 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Geometric remodelling of the left ventricle (LV) following myocardial infarction reflects on the geometric characteristics directly. This study focuses on a potential index based on curvedness. Nine consecutive normal volunteers and thirty consecutive myocardial infarction patients underwent MRI scan (twenty-seven patients had follow-up scan). Short-axis cine images of all cases were delineated. Three dimensional LV models were reconstructed and restored for possible motion distortion. The curvedness values were computed over 16-segments nomenclature. The curvedness signal for each segment over twenty-two time frames were fitted using a second order Fourier Series. Fourier coefficients were extracted and unsupervised learning was conducted between normal and patient data. An accuracy of 89% and adjusted Rand Index of 0.5374 suggest that these Fourier Series and curvedness based features can be an useful index for prognosis and diagnosis in clinical practice.
    08/2014; 2014:5113-6.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Right ventricular (RV) function is increasingly recognized to play an important role in the clinical status and long-term outcome in patients with congenital heart disease as well as ischemic cardiomyopathy with left ventricular dysfunction. However, quantification of RV characteristics and function are still challenging due to its complex morphology and its thin wall with coarse trabeculations. To assess RV functions quantitatively, establishing the patient-specific model from medical images is a prerequisite task. This study aims to develop a novel method for RV model reconstruction. Magnetic resonance images were acquired and preprocessed. Contours of right ventricle, right atrium and pulmonary artery were manually delineated at all slices and all time frames. The contour coordinates as well as the medical image specifications such as image pixel resolution and slick thickness were exported. The contours were transformed to the correct positions. Reorientation and matching were executed in between neighboring contours; extrapolation and interpolation were conducted upon all contours. After preprocessing, the more dense point set was reconstructed through a variational tool. A Delaunay-based tetrahedral mesh was generated on the region of interest. The weighted minimal surface model was used to describe RV surface. The graphcuts technique, i.e., max-flow/min-cut algorithm, was applied to minimize the energy defined by the model. The reconstructed surface was extracted from the mesh according to the mincut. Smoothing and remeshing were performed. The CPU time to reconstruct the model for one frame was approximately 2 minutes. In 10 consecutive subjects referred for cardiac MRI (80% female), right ventricular volumes were measured using our method against the commercial available CMRtools package. The results demonstrated that there was a significant correlation in end-diastolic and end-systolic volumes between our method and commercial software (r= 0.89 for end-diastolic volume and r=0.79 for end-systolic volume, both P<;0.0001). The time to obtain right ventricular volumes was shorter using our method than commercial one. In conclusion, a new method for right ventricle reconstruction has been developed. We envisage that this automatic modeling tool could be used by radiographer and cardiologists to assess the RV function in diverse heart diseases.
    08/2014; 2014:6770-3.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Accurate and robust extraction of the left ventricle (LV) cavity is a key step for quantitative analysis of cardiac functions. In this study, we propose an improved LV cavity segmentation method that incorporates a dynamic shape constraint into the weighting function of the random walks algorithm. The method involves an iterative process that updates an intermediate result to the desired solution. The shape constraint restricts the solution space of the segmentation result, such that the robustness of the algorithm is increased to handle misleading information that emanates from noise, weak boundaries, and clutter. Our experiments on real cardiac magnetic resonance images demonstrate that the proposed method obtains better segmentation performance than standard method.
    08/2014; 2014:4723-6.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose an automatic algorithm for the reconstruction of patient-specific cardiac mesh models with 1-to-1 vertex correspondence. In this framework, a series of 3D meshes depicting the endocardial surface of the heart at each time step is constructed, based on a set of border delineated magnetic resonance imaging (MRI) data of the whole cardiac cycle. The key contribution in this work involves a novel reconstruction technique to generate a 4D (i.e., spatial-temporal) model of the heart with 1-to-1 vertex mapping throughout the time frames. The reconstructed 3D model from the first time step is used as a base template model and then deformed to fit the segmented contours from the subsequent time steps. A method to determine a tree-based connectivity relationship is proposed to ensure robust mapping during mesh deformation. The novel feature is the ability to handle intra- and inter-frame 2D topology changes of the contours, which manifests as a series of merging and splitting of contours when the images are viewed either in a spatial or temporal sequence. Our algorithm has been tested on five acquisitions of cardiac MRI and can successfully reconstruct the full 4D heart model in around 30 minutes per subject. The generated 4D heart model conforms very well with the input segmented contours and the mesh element shape is of reasonably good quality. The work is important in the support of downstream computational simulation activities.
    PLoS ONE 04/2014; 9(4):e93747. · 3.53 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Objective Support vector machines (SVMs) have drawn considerable attention due to their high generalisation ability and superior classification performance compared to other pattern recognition algorithms. However, the assumption that the learning data is identically generated from unknown probability distributions may limit the application of SVMs for real problems. In this paper, we propose a vicinal support vector classifier (VSVC) which is shown to be able to effectively handle practical applications where the learning data may originate from different probability distributions. Methods The proposed VSVC method utilises a set of new vicinal kernel functions which are constructed based on supervised clustering in the kernel-induced feature space. Our proposed approach comprises two steps. In the clustering step, a supervised kernel-based deterministic annealing (SKDA) clustering algorithm is employed to partition the training data into different soft vicinal areas of the feature space in order to construct the vicinal kernel functions. In the training step, the SVM technique is used to minimise the vicinal risk function under the constraints of the vicinal areas defined in the SKDA clustering step. Results Experimental results on both artificial and real medical datasets show our proposed VSVC achieves better classification accuracy and lower computational time compared to a standard SVM. For an artificial dataset constructed from non-separated data, the classification accuracy of VSVC is between 95.5% and 96.25% (using different cluster numbers) which compares favourably to the 94.5% achieved by SVM. The VSVC training time is between 8.75s and 17.83s (for 2 to 8 clusters), considerable less than the 65.0s required by SVM. On a real mammography dataset, the best classification accuracy of VSVC is 85.7% and thus clearly outperforms a standard SVM which obtains an accuracy of only 82.1%. A similar performance improvement is confirmed on two further real datasets, a breast cancer dataset (74.01% vs. 72.52%) and a heart dataset (84.77% vs. 83.81%), coupled with a reduction in terms of learning time (32.07s vs. 92.08s and 25.00s vs. 53.31s respectively). Furthermore, the VSVC results in the number of support vectors being equal to the specified cluster number, and hence in a much sparser solution compared to a standard SVM. Conclusion Incorporating a supervised clustering algorithm into the SVM technique leads to a sparse but effective solution, while making the proposed VSVC adaptive to different probability distributions of the training data.
    Artificial intelligence in medicine 03/2014; · 1.65 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In robotic-assisted surgical training, the expertise of surgeons in maneuvering surgical instruments may be utilized to provide the motion trajectories for teaching. However, the motion primitives for trajectory planning are not known until the motion trajectory is generalized. We hypothesize that a generic model that encodes surgical skills using demonstrations and statistical models can be used by the surgical training robot to determine the motion primitive base on the motion trajectory. The generic model was developed from twenty-two sets of motion trajectories of soft tissue division with laparoscopic scissors collected from a robotic laparoscopic surgical training system. Adaptive mean shift method with initial bandwidth determined by the plug-in-rule method was used to identify the primitives in the motion trajectories. Gaussian Mixture Model was applied to model the underlying motion structure. Gaussian Mixture Regression was then applied to reconstruct a generic motion trajectory for the task. The generic model and proposed method were investigated in experiments. Motion trajectory of tissue division was model and reconstructed. The motion model which was trained based on primitives determined by adaptive mean shift method produced RMS error of [Formula: see text] and [Formula: see text] with respect to the demonstrated trajectories of left and right instruments, respectively. The RMS error was smaller than that of k-means method and fixed bandwidth mean shift method. The dexterous features in the demonstrations were also preserved. Surgical tasks can be modeled using Gaussian Mixture Model and motion primitives identified by adaptive mean shift method with minimum user intervention. Generic motion trajectory has been successfully reconstructed based on the motion model. Investigation on the effectiveness of this method and generic model for surgical training is ongoing.
    International Journal of Computer Assisted Radiology and Surgery 12/2013; · 1.36 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Evaluation of right ventricular (RV) structure and function is of importance in the management of most cardiac disorders. But the segmentation of RV has always been considered challenging due to low contrast of the myocardium with surrounding and high shape variability of the RV. In this paper, we present a 2D + T active contour model for segmentation and tracking of RV endocardium on cardiac magnetic resonance (MR) images. To take into account the temporal information between adjacent frames, we propose to integrate the time-dependent constraints into the energy functional of the classical gradient vector flow (GVF). As a result, the prior motion knowledge of RV is introduced in the deformation process through the time-dependent constraints in the proposed GVF-T model. A weighting parameter is introduced to adjust the weight of the temporal information against the image data itself. The additional external edge forces retrieved from the temporal constraints may be useful for the RV segmentation, such that lead to a better segmentation performance. The effectiveness of the proposed approach is supported by experimental results on synthetic and cardiac MR images.
    2013 IEEE International Conference on Systems, Man and Cybernetics (SMC 2013); 10/2013
  • Abdominal Imaging. Computation and Clinical Applications, Nagoya, Japan; 09/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes an automatic algorithm that uses a geometry-driven optimization approach to restore the shape of three-dimensional (3D) left ventricular (LV) models created from magnetic resonance imaging (MRI) data. The basic premise is to restore the LV shape such that the LV epicardial surface is smooth after the restoration and that the general shape characteristic of the LV is not altered. The Maximum Principle Curvature ([Formula: see text]) and the Minimum Principle Curvature ([Formula: see text]) of the LV epicardial surface are used to construct a shape-based optimization objective function to restore the shape of a motion-affected LV via a dual-resolution semi-rigid deformation process and a free-form geometric deformation process. A limited memory quasi-Newton algorithm, L-BFGS-B, is then used to solve the optimization problem. The goal of the optimization is to achieve a smooth epicardial shape by iterative in-plane and through-plane translation of vertices in the LV model. We tested our algorithm on 30 sets of LV models with simulated motion artifact generated from a very smooth patient sample, and 20 in vivo patient-specific models which contain significant motion artifacts. In the 30 simulated samples, the Hausdorff distances with respect to the Ground Truth are significantly reduced after restoration, signifying that the algorithm can restore geometrical accuracy of motion-affected LV models. In the 20 in vivo patient-specific models, the results show that our method is able to restore the shape of LV models without altering the general shape of the model. The magnitudes of in-plane translations are also consistent with existing registration techniques and experimental findings.
    PLoS ONE 07/2013; 8(7):e68615. · 3.53 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: One challenge in surgical simulation is to design stable deformable models to simulate the dynamics of organs synchronously. In this paper, we develop a novel mass-spring model on the tetrahedral meshes for soft organs such as the liver and gallbladder, which can stably deform with large time steps. We model the contact forces between the organs as a kind of forces generated by the tensions of repulsive springs connecting in between the organs. The simulation system couples a pair of constraints on the length of springs with an implicit integration method. Based on the novel constraints, our simulator can efficiently preserve the volumes and geometric properties of the liver and gallbladder during the simulation. The numerical examples demonstrate that the proposed simulation system can provide realistic and stable deformable results.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 07/2013; 2013:4941-4944.
  • [Show abstract] [Hide abstract]
    ABSTRACT: This study proposes a novel method to reconstruct the left cardiac structure from contours. Given the contours representing left ventricle (LV), left atrium (LA), and aorta (AO), re-orientation, contour matching, extrapolation, and interpolation are performed sequentially. The processed data are then reconstructed via a variational method. The weighted minimal surface model is revised to handle the multi-phase cases, which happens at the LV-LA-AO junction. A Delaunay-based tetrahedral mesh is generated to discretize the domain while the max-flow/min-cut algorithm is utilized as the minimization tool. The reconstructed model including LV, LA, and AO structure is extracted from the mesh and post-processed further. Numerical examples show the robustness and effectiveness of the proposed method.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 07/2013; 2013:2976-2979.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Understanding and quantifying right ventricular (RV) remodeling in repaired Tetralogy of Fallot (TOF) is crucial for patient management and therapy planning, i.e., in determining the optimal time for pulmonary valve replacement. However, quantification of RV remodeling is usually hampered by its complex geometry. This paper presents a computer-aided cardiac assessment methodology to quantitate RV remodeling in terms of a histogram similarity index, based on the surface curvature distribution of three-dimensional (3D) RV geometries at both the end-diastole and end-systole phases. These 3D RV geometries are reconstructed from border delineated cardiac MRI images, whereby a surface fitting algorithm is then used to calculate the curvature distribution of the 3D models. The curvature histograms at ED and ES are computed and their similarities are measured using the Bhattacharya Similarity Metric, which is denoted as hdist. Based on an initial study involving 5 TOF patients and 5 normal subjects, we observed that the mean hdist for the normal controls is significantly higher (p = 0.0015 < 0.05 and p' = 0.004 < 0.05; student t-test and Mann-Whitney-Wilcoxon test, respectively) as compared to that of the TOF patients. This suggests that hdist can be used as a discriminant between TOF patients and normal control.
    02/2013;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This work presents a method for the generation of realistic bleeding effects in a real-time virtual simulation environment. This method is used in, but not limited to, the context of a virtual surgical simulator for laparoscopic surgery. In the proposed method, we employed a particle-based approach where quad-shaped decals with blood colored texture are used to simulate individual blood drops that flow out of an organ due to accidental contact with surgical tools during surgery. The path of the blood flow is computed on-the-fly such that it adapts in real-time to the organ deformation and the effect of gravity. Mechanisms are designed to emulate the behavior in blood emission and blood flow such as squirting at the wound and attrition due to friction. In addition, by using customized shader graphics, we are able to achieve a 3D curved-contour visual effect simulating the bumpiness of each individual blood droplet that adapts to varying lighting conditions. Our results indicate that we are able to achieve good visual realism, adaptive behavioural performance and modest computational footprint.
    02/2013;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This study aimed to assess the feasibility of using the regional uniformity of the left ventricle (LV) wall stress (WS) to diagnose patients with myocardial infarction. We present a novel method using a similarity map that measures the degree of uniformity in nominal systolic WS across pairs of segments within the same patient. The values of the nominal WS are computed at each vertex point from a 1-to-1 corresponding mesh pair of the LV at the end-diastole (ED) and end-systole (ES) phases. The 3D geometries of the LV at ED and ES are reconstructed from border-delineated MRI images and the 1-to-1 mesh generated using a strain-energy minimization approach. The LV is then partitioned into 16 segments based on published clinical standard and the nominal WS histogram distribution for each of the segment was computed. A similarity index is then computed for each pair of histogram distributions to generate a 16-by-16 similarity map. Based on our initial study involving 12 MI patients and 9 controls, we observed uniformity for intraregional comparisons in the controls compared against the patients. Our results suggest that the regional uniformity of the nominal systolic WS in the form of a similarity map can potentially be used as a discriminant between MI patients and normal controls.
    Computing in Cardiology Conference (CinC), 2013; 01/2013
  • Source
    Biomedical Science, Engineering and Technology, 01/2012; , ISBN: 978-953-307-471-9
  • Source
    Biomedical Science, Engineering and Technology, 01/2012; , ISBN: 978-953-307-471-9
  • 01/2012: pages 17-26; Springer Berlin Heidelberg., ISBN: 9783642339318
  • [Show abstract] [Hide abstract]
    ABSTRACT: Anatomical structure is important for medical education and disease diagnosis. In the application of surgical simulation, different anatomical structures can be retrieved to create variety of surgical scenarios for training, while similar structures can also be retrieved to assist disease diagnosis. This paper presents an approach to liver-gallbladder anatomical structure retrieval with 3D shape comparison, where the direct shape comparison based on dense shape registration is applied to liver shape due to its shape complexity, and feature based comparison is applied to gallbladder shape with a semantic shape decomposition using the saliency area based on multi-scale curvatures and concavity. After the registration of liver models, the geometric structure of the gallbladder and liver can be combined for joint comparison. With the 3D models constructed from a set of liver-gallbladder CT data, experiments are conducted for joint liver-gallbladder retrieval. Encouraging result shows that it can reveal important topology based on similarity and variance of 3D shapes and has a similar performance compared to that of manual retrieval by human operators.
    01/2012: pages 178-187; Springer Berlin Heidelberg., ISBN: 9783642336119