Conference proceeding
Efficient optimal surface detection: theory, implementation, and experimental validation
Proceedings of SPIE, Vol.5370(1), pp.620-627
Medical Imaging 2004: Image Processing
05/12/2004
DOI: 10.1117/12.537048
Abstract
In this paper, a novel polynomial-time algorithm is described for solving the optimal net surface detection problem on proper ordered multi-column graphs in N-D space (N ≥ 3). The method is applied to searching for optimal object boundaries with arbitrary smoothness constraints in volumetric medical images. By simple transformations, such optimal surface detection problems can be simplified to a problem of computing the minimum s-t cuts in the transformed graphs. An efficient implementation for the 3-D case that can achieve near real-time performance on moderate-sized datasets is presented. We further examine our technique in experiments by segmenting the cylindrical surfaces of human airways from pulmonary volumetric CT images, and compare the results to those produced by previous methods. By allowing full specifications of the cost-function and smoothness constraints without degrading the performance, the new algorithm is more flexible than traditional methods and guarantees global optimality. The multi-dimensional nature of the algorithm maintains continuity in higher dimensions.
Details
- Title: Subtitle
- Efficient optimal surface detection: theory, implementation, and experimental validation
- Creators
- Kang Li - Univ. of Iowa (USA)Xiaodong Wu - Univ. of Texas/Pan American (USA)D. Z Chen - Univ. of Notre Dame (USA)Milan Sonka - Univ. of Iowa (USA)
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of SPIE, Vol.5370(1), pp.620-627
- Conference
- Medical Imaging 2004: Image Processing
- DOI
- 10.1117/12.537048
- ISSN
- 0277-786X
- Language
- English
- Date published
- 05/12/2004
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9984047639502771
Metrics
14 Record Views