Abstract—The variational level set model for piecewise
constant multiphase image segmentation on the plane and the
related Split-Augmented-Lagrangian Projection Method
(SALPM) are investigated in this paper. On the analysis of the
current problems based on the variational level set method for
image segmentation, we also design a rapid SALPM method
for two-phase image segmentation model, getting the general
model of multiple phase level set in order to facilitate the
generic design and program. In addition, the concrete formula
of the rapid split algorithms for multiphase image
segmentation with level set model and the calculation steps are
given, and simultaneously taking liver tumor CT image as
examples of the multiphase segmentation. Moreover, by
comparing with the traditional methods, the experiments show
that our algorithm presented in this paper have higher
computational efficiency and accuracy, and better the
extraction of liver contour.
Keywords-The variational level set; piecewise constant
multiphase; image segmentation; CT image
I. INTRODUCTION
Multiphase segmentation of medical image and three-
dimensional reconstruction are crucially important in
computer-aided diagnosis and virtual surgery. In particular,
multiphase image segmentation based on the characteristics
of the images is automatic divided into different areas,
which is a challenging difficulty and hot research field in
the image processing. Moreover, multiphase image
segmentation has an important application value in medical
images, remote sensing image and so on.
As the generality of the model, the flexibility of complex
topology expression and the stability of numerical
calculation method, variational level set method has become
one of the basic methods for image segmentation. The level
set method, originally used as numerical technique for
tracking interfaces and shapes [18], has been increasingly
applied to image segmentation in the past decade [3]. In the
level set method, contours or surfaces are represented as the
zero level set to a higher dimensional function, usually
called a level set function. With the level set represented,
the image segmentation problem can be formulated and
solved in a principled way based on well-established
mathematical theories, including calculus of variations and
partial differential equations (PDE). An advantage of the
level set method is that numerical computations involving
curves and surfaces can be performed on a fixed Cartesian
grid without having to parameterize these objects. Moreover,
the level set method is able to represent contours/surfaces
with complex topology and change their topology in a
natural way.
However, traditional technologies of image segmentation
can’t satisfy the actual demands because of the complexity
and diversity of medical image. Based on the variational
level set method, models and fast algorithms of multiphase
segmentation for medical images are presented in this paper
to satisfy clinical requirements by automatic methods.
The remainder of the paper is organized as follows: In
Section Ċ, we review the two-phase and multiphase image
segmentation variation level set method, the method for
two-phase image segmentation is extended to variational
multiphase image segmentation, and the gradient descent
method is designed for the proposed model. While in
Section ċ we detail the proposed fast numerical method for
multiphase image segmentation model, which overcomes
the difficulties of computation of traditional methods.
Finally, the experimental results are presented in Section Č.
II. T
WO-PHASE AND MULTIPHASE IMAGE SEGMENTATION
VARIATION LEVEL SET METHOD
The Chan-Vese model [1] is combined with the
simplified Munford-Shan model and the variational level set
method, which is a kind of ideal image segmentation model.
And it can be extended to multiphase image segmentation
[4], motion segmentation [5], texture image segmentation
[6], implicit surface image segmentation [7] etc.
Let
Ω be the image domain, and :
RΩ→
be a gray
level image. For the purpose of illustration, we consider for
the two-dimensional case. Moreover any dimension could be
considered. The level set method and variation level set
proposed an effective implicit representation for evolving
curves and surfaces, which has found many applications, as
it allows for automatic change of topology, such as merging
and breaking, and the calculations are made on a fixed
rectangular grid.
Multiphase Segmentation on CT liver Image Using Split-Augmented-Lagrangian
Projection Method
Wei Wang
College of Information
Engineering, Qingdao
University
Qingdao , China
wwandyking@163.com
Zhenkuan Pan
College of Information
Engineering, Qingdao
University
Qingdao, China
zkpan@126.com
Qian Dong
The Affilated Hospital
of Medical Collegeˈ
Qingdao University
Qingdao, China
dong.qian@sohu.com
Guodong Wang
College of Information
Engineering, Qingdao
University
Qingdao, China
doctorwgd@gmail.com
2013 Seventh International Conference on Image and Graphics
978-0-7695-5050-3/13 $26.00 © 2013 IEEE
DOI 10.1109/ICIG.2013.48
211
2013 Seventh International Conference on Image and Graphics
978-0-7695-5050-3/13 $26.00 © 2013 IEEE
DOI 10.1109/ICIG.2013.48
211
2013 Seventh International Conference on Image and Graphics
978-0-7695-5050-3/13 $26.00 © 2013 IEEE
DOI 10.1109/ICIG.2013.48
211
2013 Seventh International Conference on Image and Graphics
978-0-7695-5050-3/13 $26.00 © 2013 IEEE
DOI 10.1109/ICIG.2013.48
211
2013 Seventh International Conference on Image and Graphics
978-0-7695-5050-3/13 $26.00 © 2013 IEEE
DOI 10.1109/ICIG.2013.48
211