Automatic Lung Surface Registration Using Selective Distance Measure in Temporal CT Scans
In this paper, we propose a novel technique of lung surface registration for investigating temporal changes such as growth rates of pulmonary nodules. For the registration of a pair of CT scans, a proper geometrical transformation is found through the following steps: First, optimal cube registration is performed for the initial gross registration. Second, for allowing fast and robust convergence on the optimal value, a 3D distance map is generated by the local distance propagation. Third, the distance measure between surface boundary points is repeatedly evaluated by the selective distance measure. Experimental results show that the performance of our registration method is very promising compared with conventional methods in the aspects of its computation time androbustness.
KeywordsTarget Volume Chest Compute Tomography Pulmonary Nodule Iterative Close Point Initial Registration
- 1.Yankelevitz, D.F., Reeves, A.P., Kostis, W.J., Binsheng, Z., henschke, C.I.: Small Pulmonary Nodules: Volumetrically Determined Growth Rates Based on CT Evaluation. Radiology 217, 251–256 (2000)Google Scholar
- 2.Betke, M., Hong, H., Ko, J.P.: Automatic 3D Registration of Lung Surfaces in Computed Tomography Scans. In: Proc. Of Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 725–733 (2001)Google Scholar
- 3.Betke, M., Hong, H., Ko, J.P.: Automatic 3D Registration of Lung Surfaces in Computed Tomography Scans, CS Technical Report 2001-004, Boston UniversityGoogle Scholar
- 5.Hong, H., Betke, M., Teng, S.: Multilevel 3D Registration of Lung Surfaces in Computed Tomography Scans – Preliminary Experience. In: Proc. Of International Conference on Diagnostic Imaging and Analysis (ICDIA), pp. 90–95 (2002)Google Scholar
- 6.Mullaly, W., Betke, M., Hong, H., Wang, J., Mann, K., Ko, J.P.: Multi-criterion 3D Segmentation and Registration of Pulmonary Nodules on CT: a Preliminary InvestigationGoogle Scholar