A Deformable Surface Model Based on Boundary and Region Information for Pulmonary Nobule Segmentation from 3-D Thoracic CT Images
-
- KAWATA Yoshiki
- the Department of Optical Science and Technology, The University of Tokushima
-
- NIKI Noboru
- the Department of Optical Science and Technology, The University of Tokushima
-
- OHMATSU Hironobu
- National Cancer Hospital East.
-
- MORIYAMA Noriyuki
- National Cancer Hospital
Search this article
Description
Accurately segmenting and quantifying pulmonary nodule structure is a key issue in three-dimensional (3-D) computer-aided diagnosis (CAD) schemes. This paper presents a nodule segmentation method from 3-D thoracic CT images based on a deformable surface model. In this method, first, a statistical analysis of the observed intensity is performaed to measure differences between the nodule and other regions. Based on this analysis, the boundary and region information are represented by boundary and region likelihood, respectively. Second, an initial surface in the nodule is manually set. Finally, the deformable surface model moves the initial surface so that the surface provides high boundary likelihood and high posterior segmentation probability with respect to the nodule. For the purpose, the deformable surface model integrates the boundary and region information. This integration makes it possible to cope with inappropriate position or size of an initial surface in the nodule. Using the practical 3-D thoracic CT images, we demonstrate the effectiveness of the proposed method.
Journal
-
- IEICE transactions on information and systems
-
IEICE transactions on information and systems 86 (9), 1921-1930, 2003-09-01
The Institute of Electronics, Information and Communication Engineers
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1573105976790435200
-
- NII Article ID
- 110004069217
-
- NII Book ID
- AA10826272
-
- ISSN
- 09168532
-
- Text Lang
- en
-
- Data Source
-
- CiNii Articles
