Abstract
The segmentation of anatomical structures from sonograms can help physicians evaluate organ morphology and realize quantitative measurement. It is an important but difficult issue in medical image analysis. In this paper, we propose a new method based on Laws' microtexture energies and maximum a posteriori (MAP) estimation to construct a probabilistic deformable model for kidney segmentation. First, using texture image features and MAP estimation, we classify each image pixel as inside or outside the boundary. Then, we design a deformable model to locate the actual boundary and maintain the smooth nature of the organ. Using gradient information subject to a smoothness constraint, the optimal contour is obtained by the dynamic programming technique. Experiments on different datasets are described. We find this method to be an effective approach.
| Original language | English |
|---|---|
| Pages (from-to) | 114-123 |
| Number of pages | 10 |
| Journal | Computer Methods and Programs in Biomedicine |
| Volume | 84 |
| Issue number | 2-3 |
| DOIs | |
| Publication status | Published - 2006 Dec 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Science Applications
- Health Informatics
Cite this
}
Segmentation of kidney from ultrasound B-mode images with texture-based classification. / Wu, Chia Hsiang; Sun, Yung-Nien.
In: Computer Methods and Programs in Biomedicine, Vol. 84, No. 2-3, 01.12.2006, p. 114-123.Research output: Contribution to journal › Article
TY - JOUR
T1 - Segmentation of kidney from ultrasound B-mode images with texture-based classification
AU - Wu, Chia Hsiang
AU - Sun, Yung-Nien
PY - 2006/12/1
Y1 - 2006/12/1
N2 - The segmentation of anatomical structures from sonograms can help physicians evaluate organ morphology and realize quantitative measurement. It is an important but difficult issue in medical image analysis. In this paper, we propose a new method based on Laws' microtexture energies and maximum a posteriori (MAP) estimation to construct a probabilistic deformable model for kidney segmentation. First, using texture image features and MAP estimation, we classify each image pixel as inside or outside the boundary. Then, we design a deformable model to locate the actual boundary and maintain the smooth nature of the organ. Using gradient information subject to a smoothness constraint, the optimal contour is obtained by the dynamic programming technique. Experiments on different datasets are described. We find this method to be an effective approach.
AB - The segmentation of anatomical structures from sonograms can help physicians evaluate organ morphology and realize quantitative measurement. It is an important but difficult issue in medical image analysis. In this paper, we propose a new method based on Laws' microtexture energies and maximum a posteriori (MAP) estimation to construct a probabilistic deformable model for kidney segmentation. First, using texture image features and MAP estimation, we classify each image pixel as inside or outside the boundary. Then, we design a deformable model to locate the actual boundary and maintain the smooth nature of the organ. Using gradient information subject to a smoothness constraint, the optimal contour is obtained by the dynamic programming technique. Experiments on different datasets are described. We find this method to be an effective approach.
UR - http://www.scopus.com/inward/record.url?scp=33846023717&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33846023717&partnerID=8YFLogxK
U2 - 10.1016/j.cmpb.2006.09.009
DO - 10.1016/j.cmpb.2006.09.009
M3 - Article
C2 - 17070959
AN - SCOPUS:33846023717
VL - 84
SP - 114
EP - 123
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
SN - 0169-2607
IS - 2-3
ER -