Computational Respiratory Lung/Tumor Modeling and Radiotherapy Management

Project Overview

  • We study computational biomedicine modeling and medical imaging for computer-aided clinical analysis and management.
  • Currently, radiotherapy for lung cancer is challenging due to respiration-induced motion: (1) Treatment plans are based on static CT images; (2) Treatmetn is delivered without precise knowledge of the actual position of the tumor and of the internal organs.
  • The lack of precise knowledge of the actual position of the tumor and internal organs during treatment makes the calculation of real dose delivered to the lung and surrounding tissues unknown.
  • The goal of this project is to model the motion of the lung tumors during the respiratory process. The results can be used to support tumor tracking for dose verification in lung cancer radiotherapy.
  • We are working on several fundamental problems: feature extraction, 4D registration, biomedical modeling

    • Collaborators

  • University of Texas Southwestern Medical Center: Amit Sawant, Puneeth Iyengar
  • University of California, San Diego, Department of Radiation Oncology

    • Data Sources

  • UT Southwestern Medical Center
  • UCSD Moorse Cancer Center
  • LSU Pennington Biomedical Research Center
  • Mary Bird Perkins Cancer Center, Baton Rouge

    • Recent Work

    Feature Extraction and Matching

    4D (Spatial-temporal) Volumetric Registration

    Modeling Deformation of Lung

    Parallel Speed-up (GPU/High-performance Computing)

    Publications

    1. H. Xu, Xin Li, " Consistent Feature-aligned 4D Image Registration for Respiratory Motion Modeling. ," IEEE International Symposium on Biomedical Imaging (ISBI) 2013 (Oral Paper) , [PDF]

    This paper presents a consistent feature-aligned 4D image registration algorithm and its medical application. The matching across a temporal sequence of volumetric images is based on a 4D (3D spatial + 1D temporal) free-form B-spline deformation model, which ensures interpolated motions with both spatial and temporal smoothness. We first develop the forward and inverse matching models with feature alignment constraints, then iteratively refine the registration results by incorporating extra inverse consistency. Experimental results show that our method achieves better registration accuracy than previous 3D registration and 4D registration methods. This algorithm can be used to parameterize temporal CT lung volume images for motion analysis and tracking.

    2. S. Iyengar, Xin Li, Huanhuan Xu, Amit Sawant, P. Iyengar, S. Mukhopadhyay, N. Balakrishnan. "Toward More Precise Radiotherapy Treatment of Lung Tumors," IEEE Computer, vol.45, no.1, pp.59-65, 2012. [PDF] [Bibtex]

    A computational framework for modeling the respiratory motion of lung tumors provides a 4D parametric representation that tracks, analyzes, and models movement to provide more accurate guidance in the planning and delivery of lung tumor radiothearpy.

    3. H. Xu, P. Chen, W. Yu, A. Sawant, S. Iyengar, Xin Li, " Feature-aligned 4D Spatiotemporal Image Registration. ," International Conference on Pattern Recognition (ICPR) 2012 (Oral Paper), pages 2639-2642 , [PDF] [Talk Slides] [Video] [Bibtex]

    We develop a feature-aware 4D spatiotemporal image registration method. Our model is based on a 4D (3D+time) free-form B-spline deformation model which has both spatial and temporal smoothness. We first introduce an automatic 3D feature extraction and matching method based on an improved 3D SIFT descriptor, which is scale- and rotation- invariant. Then we use the results of feature correspondence to guide an intensity-based deformable image registration. Experimental results show that our method can lead to smooth temporal registration with good matching accuracy; therefore this registration model is potentially suitable for dynamic tumor tracking.

    4. H. Xu, W. Yu, S. Gu, Xin Li, Biharmonic Volumetric Mapping using Fundamental Solutions , IEEE Trans. on Visualization and Computer Graphics, in press, 2013.

    We propose a biharmonic model for cross-object volumetric mapping. This new computational model aims to facilitate the mapping of solid models with complicated geometry or heterogeneous inner structure. We demonstrate its effectiveness on the temporally scanned lung data collected during multiple respiratory cycles of some patient having the lung tumor.

    [Paper][Bibtex]

    Video

    Videos