Xiaoxu Wang
  Ph.D. in Computer Science
 

I am a Ph.D. candidate of Computer Science, Rutgers University-New Brunswick. I am working in the Center for Computational Biomedicine Imaging and Modeling (CBIM). My advisor is Professor Dimitris N. Metaxas. My research interests are mainly in Medical Image Analysis and Deformable Modeling.

 

 

Contact:

Department of Computer Science , Rutgers University, 110 Frelinghuysen Road, Piscataway, NJ 08854

Email: xiwang@cs.rutgers.edu

Work: (732) 445-2001

Publication

Meshless Deformable Models for 3D Cardiac Motion and Strain Analysis from Tagged MRI, Xiaoxu Wang, Ting Chen, Shaoting Zhang, Joel Schaerer, Zhen Qian, Suejung Huh, Dimitris Metaxas, Leon Axel, Magnetic Resonance Imaging, Jan, 2015

Nodule Detection with Pulmonary Bronchus Visualization from CT, Xiaoxu Wang, Fuchang Jia, Zhen Qian, Szilard Voros, Dimitris Metaxas, International Conference on Computer Science and Artificial Intelligence, ICCSAI, 2013

3D Cardiac Motion Reconstruction from CT Data and Tagged MRI, Xiaoxu Wang, Viorel Mihalef, Zhen Qian, Szilard Voros, Dimitris Metaxas, 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2012

Left Ventricle Segmentation with Mixture of Gaussian Active Contours, Xiaoxu Wang, Qingmao Hu, IEEE International Symposium on Biomedical Imaging, ISBI, 2012

Towards an Interactive Simulation System for Percutaneous Coronary Intervention Training, J. Qin, S. Li, H. S. Wu, L. S. Wang, X. Wang, T. T. Wong, C. M. Yu, P. A. Heng, Hong Kong SAR, International Congress of Cardiology, 2012

Automated 3D Motion Tracking Using Gabor filter Bank, Robust Point Matching, and Deformable Models, Ting Chen, Xiaoxu Wang, Sohae Chung, Dimitris Metaxas and Leon Axel, IEEE Transactions on Medical Imaging, Jan, 2010, vol. 29, page1-11

3D Segmentation Of Rodent Brains Using Deformable Models and Variational Methods, S.Zhang, J. Zhou, X. Wang, S. Chang, D. Metaxas, G. Pappas, F. Delis, N. Volkow, G. Wang, P. Thanos and C. Kambhamettu, In IEEE Computer Society Workshop On Mathematical Methods in Biomedical Image Analysis, in conjunction with CVPR 2009

LV Surface Reconstruction from Sparse TMRI using Laplacian Surface Deformation and Optimization, Shaoting Zhang, Xiaoxu Wang, Dimitris Metaxas, Ting Chen and Leon Axel, in Proceeding of the IEEE International Symposium on Biomedical Imaging, (ISBI), 2009

LV Motion and Strain Computation from TMRI based on Meshless Deformable Models, Xiaoxu Wang, Ting Chen, Shaoting Zhang, Dimitris Metaxas and Leon Axel, In Proceeding of International Conference on Medical Image Computing and Computer Assisted Intervention, (MICCAI), (1) 2008: 636-644

Cell Segmentation for Division Rate Estimation in Computerized Video Time-Lapse Microscopy, Xiaoxu Wang, Weijun He, Zhen Qian, Robin Mathew, Dimitris Metaxas, Eileen White. Book chapter in Microscopic Image Analysis for Life Science Applications, published by Artech. House, Inc., 2008.

Fast Motion Tracking of Tagged MRI using Angle Preserving Meshless Registration - Ting Chen, Xiaoxu Wang, Dimitris Metaxas, Leon Axel, In Proceeding of International Conference on Medical Image Computing and Computer Assisted Intervention, (MICCAI), (2) 2008: 313-321

Meshless Deformable Models for LV Motion Analysis, Xiaoxu Wang, Ting Chen, Dimitris Metaxas and Leon Axel, in Proceeding of Computer Vision and Pattern Recognition, (CVPR) 2008

3D Cardiac Motion Tracking using Robust Point Matching and Meshless Deformable Models, Ting Chen, Xiaoxu Wang, Dimitris N. Metaxas, Leon Axel, in Proceeding of the IEEE International Symposium on Biomedical Imaging, (ISBI) 2008: 280-283

Cell Segmentation using Adaboost and Watershed algorithm, Xiaoxu Wang, Weijun He, Dimitris Metaxas, Robin Mathew, Eileen White, MIAAB 2007 (MICCAI workshop)

Meshless Strain Computations of Highly Deformable Organs, Suejung Huh, Xiaoxu Wang, Dimitris Metaxas, MIAAB 2007 (MICCAI workshop)

Reconstruction of Detailed Left Ventricle Motion from TMRI Using Deformable Models, Xiaoxu Wang, Joel Schaerer, Suejung Huh, Zhen Qian, Dimitris Metaxas, Ting Chen, Leon Axel, In Proceeding of Functional Imaging and Modeling of the Heart, (FIMH) 2007

Cell Segmentation and Tracking Using Texture-adaptive Snakes, Xiaoxu Wang, Weijun He, Dimitris Metaxas, Robin Mathew, Eileen White, in Proceeding of the IEEE International Symposium on Biomedical Imaging, (ISBI), 2007

Cell Segmentation for Division Rate Estimation in Computerized Video Time-Lapse Microscopy, Weijun He, Xiaoxu Wang, Dimitris Metaxas, Robin Mathew, Eileen White, In Conference of Society of Photo-Optical Instrumentation Engineers, (SPIE) 2007

Analysis on the Assignment Landscape of 3-SAT Problems, Master Thesis, 2004

A Constraint Solver and its Application to Path Feasibility Analysis, Jian Zhang, Xiaoxu Wang, International Journal of Software Engineering and Knowledge Engineering, 2001

Project

  • Modeling 3D cardiac motion from tagged MRI with meshless deformable models.

Tagged MRI is a non-invasive way to track in-vivo cardiac motion. Tags are material points which deform as the heart contracts and relaxes during the cardiac cycle. We propose a novel meshless deformable model for volumetric motion reconstruction and analysis from 2D tagged MRI slices. Objects are modeled with parameterized functions in a prolate spheroidal coordinate system. Global movements like contraction and slight twisting are reconstructed with parameterized functions. Meshless deformable models interpret objects as point cloud instead of meshes, and local areas interact with each other by radius based kernels. By assuming the neighboring points in a kernel are going on the same similarity transformation, the transformation matrix can be calculated and the deformation of the object is estimated. The model can track the through-plane mayocadial motion of and provide a more comprehensive view for the research and early diagonosis of cardiac diseases. Video "Deformation results" shows the MRI imaging setting. The difference between a healthy heart motion and a patient heart motion can be viewed in video "comparison between healthy heart and patient heart".

.

 


  • Cell tracking with particle filters

Identifying cell trajectories is an important step in analyzing physiological events in computerized video time-lapse microcopy. The large variety and transformation of cell shapes and cells motion make cell tracking a challenge problem. In this paper we propose a cell tracking system, implemented as a particle filter incorporated with texture-adaptive coupled active contours. Video "cell location tracking results" is a demo of cell tracking with particle filter. Video "cell contour segmentation in motion" is a demo of cell contour tracking in the motion.