| US 7,477,768 B2 | ||
| System and method for performing a three-dimensional virtual examination of objects, such as internal organs | ||
| Arie E. Kaufman, Plainview, N.Y. (US); Zhengrong Liang, Stony Brook, N.Y. (US); Mark R. Wax, Greenlawn, N.Y. (US); Ming Wan, Stony Brook, N.Y. (US); Dongqing Chen, Lake Ronkonkoma, N.Y. (US); and Bin Li, Lake Grove, N.Y. (US) | ||
| Assigned to The Research Foundation of State University of New York, Stony Brook, N.Y. (US) | ||
| Filed on Dec. 20, 2006, as Appl. No. 11/613,306. | ||
| Application 11/613306 is a continuation in part of application No. 09/493559, filed on Jan. 28, 2000, granted, now 6,343,936. | ||
| Application 09/493559 is a continuation in part of application No. 09/343012, filed on Jun. 29, 1999, granted, now 6,331,116. | ||
| Application 09/343012 is a continuation in part of application No. 08/714697, filed on Sep. 16, 1996, granted, now 5,971,767. | ||
| Prior Publication US 2007/0103464 A1, May 10, 2007 | ||
| Int. Cl. G06K 9/00 (2006.01) | ||
| U.S. Cl. 382—128 [382/154; 378/41] | 6 Claims |
| 1. A computer-based method of defining a skeleton for a three dimensional image representation of a hollow object formed with
a plurality of voxels comprising:
identifying a root voxel within the hollow object;
generating a distance map for all voxels within the hollow object, the distance map being formed using a 26-connected cubic
plate of neighboring voxels having Euclidian weighted distances;
identifying voxels having a local maxima in the distance map as endpoints of branches in the hollow object;
for each local maxima voxel, determining a shortest connected path to one of the root voxel or a previously defined shortest
path; and
centralizing the shortest paths within the respective branches of the object.
|