Abstract | ||
---|---|---|
In this paper, we modified GrabCut for gray-scale slice-stacked medical image segmentation. First, GrabCut was extended from planar to volume image processing. Second, we simplified manual interaction by drawing a polygon for one volume instead of a rectangle. After that, twenty human brain computerized tomography images were analyzed. Experimental results show that the modified algorithm is simple and fast, and enhances segmentation accuracy compared with the confidence connection algorithm. Moreover, the algorithm is reproducible with respect to different users and consequently it can release physicians from this kind of time-consuming and laborious tasks. In addition, this method can be used for other types of medical volume image segmentation. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-48335-1_3 | HEALTH INFORMATION SCIENCE, HIS 2016 |
Keywords | Field | DocType |
Image segmentation, Computerized tomography, GrabCut | Computer vision,Polygon,Segmentation,Computer science,Rectangle,GrabCut,Image processing,Tomography,Image segmentation,Artificial intelligence | Conference |
Volume | ISSN | Citations |
10038 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 14 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhihua Ji | 1 | 0 | 0.34 |
Shaode Yu | 2 | 19 | 5.60 |
Shibin Wu | 3 | 2 | 1.47 |
Yaoqin Xie | 4 | 125 | 21.70 |
Fashun Yang | 5 | 0 | 0.34 |