Yi Su

Institute Of High Performance Computing, Tumasik, Singapore

Are you Yi Su?

Claim your profile

Publications (20)19.4 Total impact

  • 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 01/2014; 9(4):e93747. · 3.73 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
  • 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. · 3.73 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: 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
    01/2012; , ISBN: 978-953-307-471-9
  • Source
    01/2012; , ISBN: 978-953-307-471-9
  • 01/2012: pages 17-26; , 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; , ISBN: 9783642336119
  • [Show abstract] [Hide abstract]
    ABSTRACT: A quantitative understanding of right ventricular (RV) remodeling in repaired tetralogy of Fallot (rTOF) is crucial for patient management. The objective of this study is to quantify the regional curvatures and area strain based on three-dimensional (3-D) reconstructions of the RV using cardiac magnetic resonance imaging (MRI). Fourteen (14) rTOF patients and nine (9) normal subjects underwent cardiac MRI scan. 3-D RV endocardial surface models were reconstructed from manually delineated contours and correspondence between end-diastole (ED) and end systole (ES) was determined. Regional curvedness (C) and surface area at ED and ES were calculated as well as the area strain. The RV shape and deformation in rTOF patients differed from normal subjects in several respects. Firstly, the curvedness at ED (mean for 13 segments, 0.030 ± 0.0076 vs. 0.029 ± 0.0065 mm(-1); P < 0.05) and ES (mean for 13 segments, 0.040 ± 0.012 vs. 0.034 ± 0.0072 mm(-1); P < 0.001) was decreased by chronic pulmonary regurgitation. Secondly, the surface area increased significantly at ED (mean for 13 segments, 982 ± 192 vs. 1,397 ± 387 mm(2); P < 0.001) and ES (mean for 13 segments, 576 ± 130 vs. 1,012 ± 302 mm(2); P < 0.001). In particular, rTOF patients had significantly larger surface area than that in normal subjects in the free wall but not for the septal wall. Thirdly, area strain was significantly decreased (mean for 13 segments, 56 ± 6 vs. 34 ± 7%; P < 0.0001) in rTOF patients. Fourthly, there were increases in surface area at ED (5,726 ± 969 vs. 6,605 ± 1,122 mm(2); P < 0.05) and ES (4,280 ± 758 vs. 5,569 ± 1,112 mm(2); P < 0.01) and decrease in area strain (29 ± 8 vs. 18 ± 8%; P < 0.001) for RV outflow tract. These findings suggest significant geometric and strain differences between rTOF and normal subjects that may help guide therapeutic treatment.
    AJP Heart and Circulatory Physiology 12/2011; 302(6):H1306-16. · 3.63 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Laparoscopic Surgery poses significant complexity in hand-eye coordination to the surgeon. In order to improve their proficiency beyond the limited exposure in the operating theatre, surgeons need to practice on laparoscopic trainers. We have constructed a robotic laparoscopic trainer with identical degrees of freedom and range of motion as a conventional laparoscopic instrument. We hypothesize that active robotic assistance through a laparoscopic trainer improves training efficacy as compared to autonomous practice. In order to test the hypothesis, we have divided the subjects into two groups. The control group practiced on two laparoscopic tasks manually without feedback or supervision. The other group practiced on the same tasks with robotic assistance. Results from the robot-assisted group show that tool orientation (pitch and yaw joint motion) in the pointing task improved by more than 15%.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2011; 2011:4534-7.
  • [Show abstract] [Hide abstract]
    ABSTRACT: A computational method for quantifying left ventricle (LV) remodeling using 3D mesh models reconstructed from magnetic resonance imaging is proposed. The underlying geometry of the LV mesh is obtained by using a quadric fitting method, and its quantification is performed by using a curvedness shape descriptor. To achieve robustness, we have performed detailed studies of the effects of n-ring parameter selection on the accuracy of this method with in vitro and in vivo LV models. We have found that curvedness calculations based on a 5-ring selection can accurately depict anomalies in LV shape despite the presence of noise due to manual image segmentation. Our studies show that patients after myocardial infarction exhibit significant LV shape alteration in terms of curvedness, in particular at the apex. The diastole-to-systole change in regional curvedness was significantly lower suggesting regional differences in hypokinesis due to infarcted myocardium. This approach may add new insights into ventricular deformation and enable better discrimination between normal and pathologic conditions.
    Computer methods and programs in biomedicine 04/2011; 108(2):500-10. · 1.56 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an approach to gallbladder shape comparison by using 3D shape modeling and decomposition. The gallbladder models can be used for shape anomaly analysis and model comparison and selection in image guided robotic surgical training, especially for laparoscopic cholecystectomy simulation. The 3D shape of a gallbladder is first represented as a surface model, reconstructed from the contours segmented in CT data by a scheme of propagation based voxel learning and classification. To better extract the shape feature, the surface mesh is further down-sampled by a decimation filter and smoothed by a Taubin algorithm, followed by applying an advancing front algorithm to further enhance the regularity of the mesh. Multi-scale curvatures are then computed on the regularized mesh for the robust saliency landmark localization on the surface. The shape decomposition is proposed based on the saliency landmarks and the concavity, measured by the distance from the surface point to the convex hull. With a given tolerance the 3D shape can be decomposed and represented as 3D ellipsoids, which reveal the shape topology and anomaly of a gallbladder. The features based on the decomposed shape model are proposed for gallbladder shape comparison, which can be used for new model selection. We have collected 19 sets of abdominal CT scan data with gallbladders, some shown in normal shape and some in abnormal shapes. The experiments have shown that the decomposed shapes reveal important topology features.
    Proc SPIE 03/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Laparoscopic surgery requires rigorous training in order to overcome physical, spatial and visual constraints. We are developing a laparoscopic robot trainer. The robot trainer can learn the motion of the master surgeon when he is performing a virtual surgery, and drive the surgical tool by mimicking the learnt trajectory during training. This paper reports our investigation on robot learning using learning by imitation for surgical training. The feasibility of implementing this innovative learning method is demonstrated with recent results on the robot trainer, and experiments involving our laparoscopic surgery trainer box and computer vision system.
    01/2011;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Geometric remodeling of the left ventricle (LV) after myocardial infarction is associated with changes in myocardial wall stress. The objective of this study was to determine the regional curvatures and wall stress based on three-dimensional (3-D) reconstructions of the LV using MRI. Ten patients with ischemic dilated cardiomyopathy (IDCM) and 10 normal subjects underwent MRI scan. The IDCM patients also underwent delayed gadolinium-enhancement imaging to delineate the extent of myocardial infarct. Regional curvedness, local radii of curvature, and wall thickness were calculated. The percent curvedness change between end diastole and end systole was also calculated. In normal heart, a short- and long-axis two-dimensional analysis showed a 41 +/- 11% and 45 +/- 12% increase of the mean of peak systolic wall stress between basal and apical sections, respectively. However, 3-D analysis showed no significant difference in peak systolic wall stress from basal and apical sections (P = 0.298, ANOVA). LV shape differed between IDCM patients and normal subjects in several ways: LV shape was more spherical (sphericity index = 0.62 +/- 0.08 vs. 0.52 +/- 0.06, P < 0.05), curvedness at end diastole (mean for 16 segments = 0.034 +/- 0.0056 vs. 0.040 +/- 0.0071 mm(-1), P < 0.001) and end systole (mean for 16 segments = 0.037 +/- 0.0068 vs. 0.067 +/- 0.020 mm(-1), P < 0.001) was affected by infarction, and peak systolic wall stress was significantly increased at each segment in IDCM patients. The 3-D quantification of regional wall stress by cardiac MRI provides more precise evaluation of cardiac mechanics. Identification of regional curvedness and wall stresses helps delineate the mechanisms of LV remodeling in IDCM and may help guide therapeutic LV restoration.
    AJP Heart and Circulatory Physiology 01/2009; 296(3):H573-84. · 3.63 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: It is believed that left ventricular (LV) regional shape is indicative of LV regional function, and cardiac pathologies are often associated with regional alterations in ventricular shape. In this article, we present a set of procedures for evaluating regional LV surface shape from anatomically accurate models reconstructed from cardiac magnetic resonance (MR) images. LV surface curvatures are computed using local surface fitting method, which enables us to assess regional LV shape and its variation. Comparisons are made between normal and diseased hearts. It is illustrated that LV surface curvatures at different regions of the normal heart are higher than those of the diseased heart. Also, the normal heart experiences a larger change in regional curvedness during contraction than the diseased heart. It is believed that with a wide range of dataset being evaluated, this approach will provide a new and efficient way of quantifying LV regional function.
    Medical & Biological Engineering 11/2008; 47(3):313-22. · 1.76 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The rapid pressure built-up in the left ventricular (LV) cavity is mainly due to the contraction of the helically oriented myocardial fibers, and its associated wall deformation. In this paper, we recover and elucidate the left ventricular wall motion during isovolumic contraction using a shape-based tracking approach. In particular, the LV surface properties are derived by means of local surface fitting, and the point-correspondences between successive time frames are determined using a thin plate bending model. Results show that the LV motion during isovolumic contraction is largely contributed by the twisting action of the LV.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 02/2007; 2007:787-90.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Left ventricular functional abnormalities are postulated to be associated with regional modification of surface curvature. This study describes the computation of the differential properties of the LV surface via an analytic approach using local surface fitting. Quantification was implemented with cine magnetic resonance imaging (MRI), which was used as the source to derive 3D wire-frame models and the related shape descriptors. Based on these shape descriptors, the shape of LV could be represented in both static and dynamic manners. These may have implications for diverse cardiac diseases.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 02/2007; 2007:884-7.