Are you W. Huang?

Claim your profile

Publications (5)0.99 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a semi-automatic approach to segmentation of liver parenchyma from 3D computed tomography (CT) images. Specifically, liver segmentation is formalized as a pattern recognition problem, where a given voxel is to be assigned a correct label - either in a liver or a non-liver class. Each voxel is associated with a feature vector that describes image textures. Based on the generated features, an Extreme Learning Machine (ELM) classifier is employed to perform the voxel classification. Since preliminary voxel segmentation tends to be less accurate at the boundary, and there are other non-liver tissue voxels with similar texture characteristics as liver parenchyma, morphological smoothing and 3D level set refinement are applied to enhance the accuracy of segmentation. Our approach is validated on a set of CT data. The experiment shows that the proposed approach with ELM has the reasonably good performance for liver parenchyma segmentation. It demonstrates a comparable result in accuracy of classification but with a much faster training and classification speed compared with support vector machine (SVM).
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2012; 2012:3752-5. DOI:10.1109/EMBC.2012.6346783
  • [Show abstract] [Hide abstract]
    ABSTRACT: A challenge in virtual reality based laparoscopic cholecystectomy simulation is to construct a fast and accurate deformable gallbladder model. This paper proposed a multi-layered mass-spring model which can adapt well to the built-in accelerating algorithms in PhysX-Engine of Graphics Processing Unit (GPU). The gallbladder was first segmented from clinical Computed Tomography (CT) images. From the segmentation result, a surface mesh of a gallbladder was constructed. The inner layers of a mass-spring model were generated from the surface mesh based on the anatomical structure of gallbladder. We configured the parameters of the springs based on the biomechanical properties of gallbladder to ensure the reality of the deformation results. Preliminary experiments demonstrated that our model was able to achieve satisfactory results in terms of both visual perception and time performance.
    Computers & Electrical Engineering 01/2012; 39(1). DOI:10.1016/j.compeleceng.2012.05.012 · 0.99 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: One challenge in laparoscopic cholecystectomy surgery simulation is to construct a fast and accurate deformable gallbladder model. This paper proposed an improved multi-layer mass-spring modeling method which can adapt well to the built-in accelerating algorithms in PhysX-engine of GPU. A multi-layer mass-spring model was constructed based on the surface mesh of a gallbladder. The inner layers of the mass-spring model were generated using more geometrical information than the previous method. The parameters of the springs were configured based on the biomechanical properties of gallbladder to ensure the realism of the deformation results. Preliminary experiments demonstrate that our model can achieve better results in terms of both visual perception and time performance.
    Industrial Electronics and Applications (ICIEA), 2011 6th IEEE Conference on; 07/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: A challenge in virtual reality based laparoscopic cholecystectomy simulation is to construct a fast and accurate deformable gallbladder model. This paper proposes a multi-layer mass-spring model which can adapt well to the built-in accelerating algorithms in PhysX-engine of GPU. The gallbladder is first segmented from clinical CT images. A multi-layer model based on the anatomical structure of gallbladder is subsequently constructed. We configure the parameters of the springs based on the biomechanical properties of gallbladder to ensure the realism of the deformation results. Preliminary experiments demonstrate that our model can achieve satisfactory results in terms of both visual perception and time performance.
    Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on; 11/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Modeling forces applied to cut biological material with laparoscopic scissors is important for haptic rendering in laparoscopic surgical simulation. The cutting process is characterized in deformation and fracture. An analytical model for cutting human iliac artery with laparoscopic scissors is derived with concepts of shearing deformation and fracture mechanics in this study. An experimental set-up was built to verify the analytical cutting force model. Three pieces of human iliac artery were cut with laparoscopic scissors. Force required to cut arterial wall and corresponding angular displacement of scissors' handle were collected to evaluate the parameters in the cutting force model. The cutting force model is able to fit the average normalized force-handle angle curve with coefficient of determination equals to 0.977. The starting point of fracture is modeled by energy based fracture mechanics method. The energy based method predicts the fracture point with only 3% deviation from the manual determination.
    Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference onBiomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on; 01/2010