Abstract
A novel and robust method for accurate segmentation of liver lesions is discussed in this paper. The initial contour for the snake is formed using edge and region information. The modified snake, guided by fuzzy edge information deforms from this initial position, providing an accurate representation of the lesion boundary with few iterations and minimal user interaction. Results obtained from this algorithm are comparable to those obtained from manual segmentation by a trained radiologist.
Original language | English (US) |
---|---|
Pages | 187-191 |
Number of pages | 5 |
State | Published - 2004 |
Event | 2004 IEEE Southwest Symposium on Image Analysis and Interpretation - Lake Tahoe, NV, United States Duration: Mar 28 2004 → Mar 30 2004 |
Other
Other | 2004 IEEE Southwest Symposium on Image Analysis and Interpretation |
---|---|
Country/Territory | United States |
City | Lake Tahoe, NV |
Period | 3/28/04 → 3/30/04 |
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Computer Science Applications