Content uploaded by Christo Ananth
Author content
All content in this area was uploaded by Christo Ananth on Oct 30, 2017
Content may be subject to copyright.
ISSN (ONLINE):
2454-9762
ISSN (PRINT):
2454-9762
Available online at www.ijarmate.com
International Journal of Advanced Research in Management, Architecture, Technology and Engineering(IJARMATE)
Vol. 2, Issue 3, March 2016
122
All Rights Reserved © 2016 IJARMATE
Geo-cutting Liver Tumor
Christo Ananth
*
Associate Professor,ECE,Francis Xavier Engineering College,
Tirunelveli -627003,India
Abstract
—
The issue of intuitive frontal area/foundation division in still pictures is of awesome down to earth significance in picture
altering. They maintain a strategic distance from the limit length predisposition of chart cut strategies and results in expanded
affectability to seed situation. Another proposed technique for completely programmed handling structures is given taking into
account Graph-cut and Geodesic Graph cut calculations. This paper addresses the issue of dividing liver and tumor locales from the
stomach CT pictures. The absence of edge displaying in geodesic or comparable methodologies confines their capacity to exactly
restrict object limits, something at which chart cut strategies by and large exceed expectations. A predicate is characterized for
measuring the confirmation for a limit between two locales utilizing Geodesic Graph-based representation of the picture. The
calculation is connected to picture division utilizing two various types of nearby neighborhoods in building the chart. Liver and
hepatic tumor division can be naturally prepared by the Geodesic chart cut based strategy. This framework has focused on finding a
quick and intuitive division strategy for liver and tumor division. In the pre-handling stage, Mean movement channel is connected to
CT picture process and factual thresholding technique is connected for diminishing preparing zone with enhancing discoveries rate.
In the Second stage, the liver area has been divided utilizing the calculation of the proposed strategy. Next, the tumor district has been
portioned utilizing Geodesic Graph cut strategy. Results demonstrate that the proposed strategy is less inclined to shortcutting than
run of the mill diagram cut techniques while being less delicate to seed position and preferable at edge restriction over geodesic
strategies. This prompts expanded division exactness and decreased exertion with respect to the client. At long last Segmented Liver
and Tumor Regions were appeared from the stomach Computed Tomographic picture.
Keywords
—
Automatic Segmentation; Interactive Segmentation; Graph cuts; Geodesic Graph cuts; Hepatic tumor and liver;
I. I
NTRODUCTION
Development of Medical diagnosis imaging technologies is the first step towards improvement of diagnosis accuracy
and patient quality of life. With increasing use of Computed topography (CT) and Magnetic resonance (MR) imaging for
diagnosis, treatment planning and clinical studies, it has become almost compulsory to use computers to assist radiological
experts in clinical diagnosis and treatment planning. Surgical resection of hepatic tumors remains the first choice for treatment
of primary and secondary liver malignancies. The goal of image segmentation is to cluster pixels into salient image regions, i.e.,
regions corresponding to individual surfaces, objects, or natural parts of objects. By interactive image segmentation, the user
outlines the region of interest and algorithms are applied so that the path best fits the edge of the image. Automatic image
segmentation has become a prominent objective in image analysis and computer vision. A geodesic framework was developed
for fast interactive image which used Geodesics-based algorithm for (interactive) natural image. Narrow band trimap was
quickly generated from a few scribbles. It better handles objects that cross each other in video temporal domain, but it produced
poor performance when the distributions overlap. Moreover there is no regularization term in the model. Christo Ananth et al.
[1] proposed a method in which the minimization is per-formed in a sequential manner by the fusion move algorithm that uses
the QPBO min-cut algorithm. Multi-shape GCs are proven to be more beneficial than single-shape GCs. Hence, the
segmentation methods are validated by calculating statistical measures. The false positive (FP) is reduced and sensitivity and
specificity improved by multiple MTANN.
Christo Ananth et al. [2] proposed a system, this system has concentrated on finding a fast and interactive
segmentation method for liver and tumor segmentation. In the pre-processing stage, Mean shift filter is applied to CT image
process and statistical thresholding method is applied for reducing processing area with improving detections rate. In the
Second stage, the liver region has been segmented using the algorithm of the proposed method. Next, the tumor region has been
segmented using Geodesic Graph cut method. Results show that the proposed method is less prone to shortcutting than typical
graph cut methods while being less sensitive to seed placement and better at edge localization than geodesic methods. This
leads to increased segmentation accuracy and reduced effort on the part of the user. Finally Segmented Liver and Tumor
Regions were shown from the abdominal Computed Tomographic image.Geo-cuts method models gradient flows of contours
and surfaces. The approach was flexible with respect to distance metrics on the space of contours/surfaces. But the approach
ISSN (ONLINE):
2454-9762
ISSN (PRINT):
2454-9762
Available online at www.ijarmate.com
International Journal of Advanced Research in Management, Architecture, Technology and Engineering(IJARMATE)
Vol. 2, Issue 3, March 2016
123
All Rights Reserved © 2016 IJARMATE
was mainly theoretical. Moreover the distance map can be determined only with precision of 0.5 and time steps remains to be
controlled.
Christo Ananth et al. [3] proposed a system, in which a predicate is defined for measuring the evidence for a boundary
between two regions using Geodesic Graph-based representation of the image. The algorithm is applied to image segmentation
using two different kinds of local neighborhoods in constructing the graph. Liver and hepatic tumor segmentation can be
automatically processed by the Geodesic graph-cut based method. This system has concentrated on finding a fast and interactive
segmentation method for liver and tumor segmentation. In the preprocessing stage, the CT image process is carried over with
mean shift filter and statistical thresholding method for reducing processing area with improving detections rate. Second stage is
liver segmentation; the liver region has been segmented using the algorithm of the proposed method. The next stage tumor
segmentation also followed the same steps. Finally the liver and tumor regions are separately segmented from the computer
tomography image.
General framework encompassing graph cuts, random walker, shortest-path segmentation and watersheds approach
was also developed which uses energy minimization algorithm. However it is not applicable to large systems and it is not a fast
and an effective approach. Random Walker approach for general image segmentation was based on small set of pre-labeled
pixels. It is robust to weak object boundaries and it takes account of user’s pre-labelling choices. But it consumes enormous
large computation time and it is only an Initial solution for an iterative matrix solver. Christo Ananth et al. [4] proposed a
system in which this study presented the implementation of two fully automatic liver and tumors segmentation techniques and
their comparative assessment. The described adaptive initialization method enabled fully automatic liver surface segmentation
with both GVF active contour and graph-cut techniques, demonstrating the feasibility of two different approaches. The
comparative assessment showed that the graph-cut method provided superior results in terms of accuracy and did not present
the described main limitations related to the GVF method. The proposed image processing method will improve computerized
CT-based 3-D visualizations enabling noninvasive diagnosis of hepatic tumors. The described imaging approach might be
valuable also for monitoring of postoperative outcomes through CT-volumetric assessments. Processing time is an important
feature for any computer-aided diagnosis system, especially in the intra-operative phase. Christo Ananth et al. [5] proposed a
system in which an automatic anatomy segmentation method is proposed which effectively combines the Active Appearance
Model, Live Wire and Graph Cut (ALG) ideas to exploit their complementary strengths. It consists of three main parts: model
building, initialization, and delineation. For the initialization (recognition) part, a pseudo strategy is employed and the organs
are segmented slice by slice via the OAAM (Oriented Active Appearance method). The purpose of initialization is to provide
rough object localization and shape constraints for a latter GC method, which will produce refined delineation. It is better to
have a fast and robust method than a slow and more accurate technique for initialization.
A graph cut approach to image segmentation was also developed in tensor space which enabled segmentation of tensor
valued images by natural Riemannian structure of the tensor. The approach captures true variation of object and background.
However the method may fail when two textures differ only in scale and it does not give satisfactory performance as like the
Gradient vector flow active contour technique. Interactive image segmentation via adaptive weighted distances was used which
used soft image segmentation approach. Here, Automatic weighting of different channels was adaptable to wide range of
images. The approach produced greater time linearity and better Image labelling but it had greater computational complexity
and there is no proper definition of appropriate weights which does not fit image modality. The existing approach also used
Curvature Regularity method for boundary smoothening. It does not use edge component to localize edges and it consumes
more time. Christo Ananth et al. [6] presented an automatic segmentation method which effectively combines Active Contour
Model, Live Wire method and Graph Cut approach (CLG). The aim of Live wire method is to provide control to the user on
segmentation process during execution. Active Contour Model provides a statistical model of object shape and appearance to a
new image which are built during a training phase. In the graph cut technique, each pixel is represented as a node and the
distance between those nodes is represented as edges. In graph theory, a cut is a partition of the nodes that divides the graph into
two disjoint subsets. For initialization, a pseudo strategy is employed and the organs are segmented slice by slice through the
OACAM (Oriented Active Contour Appearance Model). Initialization provides rough object localization and shape constraints
which produce refined delineation. This method is tested with different set of images including CT and MR images especially
3D images and produced perfect segmentation results. Christo Ananth et al. [7] discussed about a model, a new model is
designed for boundary detection and applied it to object segmentation problem in medical images. Our edge following
technique incorporates a vector image model and the edge map information. The proposed technique was applied to detect the
object boundaries in several types of noisy images where the ill-defined edges were encountered. The proposed techniques
performances on object segmentation and computation time were evaluated by comparing with the popular methods, i.e., the
ISSN (ONLINE):
2454-9762
ISSN (PRINT):
2454-9762
Available online at www.ijarmate.com
International Journal of Advanced Research in Management, Architecture, Technology and Engineering(IJARMATE)
Vol. 2, Issue 3, March 2016
124
All Rights Reserved © 2016 IJARMATE
ACM, GVF snake models. Several synthetic noisy images were created and tested. The method is successfully tested in
different types of medical images including aortas in cardiovascular MR images, and heart in CT images.
In this new study, the same graph cut segmentation method is applied for liver. The initialization method is further
developed making it suitable for the graph cut algorithm. The aims of this comparative evaluation were: 1) verify the feasibility
of two different segmentation approaches – graph cut method and geodesic graph cut method and their automation starting
from the same adaptive initialization method; 2) apply graph cut segmentation approach to the liver and geodesic graph cut
method to hepatic tumors employing the same initialization method for liver and then for tumor initialization;
In this study, datasets of different patients were processed using the above automatic mentioned methods and the
results were compared. The paper is organized as follows: Proposed Methodology for liver and tumor segmentation were
discussed in Section II. Section III discusses the simulation results of Graph cut and Geodesic Graph cut Segmentation
approaches. Section IV concludes this paper with some ideas for improvements.
II.
METHODOLOGY
Various algorithms have been developed using pixel-based or/and contour-based methods. Currently, two approaches are
under investigation. The first one is Geodesic Graph cut approach and the second method is Graph cuts method that is one of
the current cutting edge techniques in image segmentation.
A. Automatic Liver Initialization Method
Figure 1 shows the flowchart of an automatic initialization method applied to both Geodesic Graph cut and Graph cut
techniques. This method is based on a statistical model distribution of liver average intensity and its standard deviation. First of
all, a pre-processing filter needs to be applied to the original volumetric image for noise removal from homogenous areas while
keeping clear and sharp edges. The best results were obtained with the mean shift filter most suitable for these purposes. Each
slice of the filtered volume was divided into 64 squared sub regions. For each abdominal sub region, the mean image intensity
and its standard deviation were calculated to identify most homogeneous regions in terms of pixel intensity (i.e., regions with
standard deviation lower than 1% of the peak value of corresponding histogram). By adaptive threshold, images were
partitioned and then liver regions were identified.
B. Automatic Tumor Initialization Method
This step was applied only to liver volume. It was used as a mask in order to prevent processing overloads and avoids errors
related to the presence of surrounding tissues presenting similar gray scale distributions. Voxels belonging to intensity range
domain were also removed from the segmented liver volume. This intensity range domain is selected because the data fitted to
Gaussian distribution and nearly all (99.7%) of the values lied within three standard deviations of the mean. This choice allowed
the correct identification of liver respect to other organs, optimizing the calculation resources and increasing the tumor
segmentation accuracy.
No
Y
ES
Fig. 1 Flow chart of Initialization method
Read the
CT input
image
Liver Region
Identification
Region growing by
Geodesic Graph cut
method
Segmented
Liver Region
Until
Tumor Region
Identification
Tumor
?
Region growing by
Geodesic Graph cut
method
Until
Segmented
Tumor
Region
Segmented
Output
ISSN (ONLINE):
2454-9762
ISSN (PRINT):
2454-9762
Available online at www.ijarmate.com
International Journal of Advanced Research in Management, Architecture, Technology and Engineering(IJARMATE)
Vol. 2, Issue 3, March 2016
125
All Rights Reserved © 2016 IJARMATE
C. Geodesic Segmentation of Liver and Tumors
Geodesic segmentation can be improved by inclusion of explicit edge information to encourage placement of selection
boundaries on edges in the image and allow user more freedom in placing strokes. The region term alone can often carry the
segmentation in such cases, but global color models without spatial locality information can often select disjoint regions. The
use of geodesic distance can avoid selection of disjoint regions. This section presents how geodesic distances and edge
information can be combined in a graph cut optimization framework, and then presents a way to use the predicted
classification accuracy from the inferred color models to automatically tune the trade off between the strengths and
weaknesses of the two.
The unary region term can be computed as follows:
R
l
(x
i
) = s
l
(x
i
) + M
l
(x
i
) + G
l
(x
i
) (2.1)
where M
l
(x
i
) is based on global color model as it is used for graph-cut segmentation, G
l
(x
i
) is based on geodesic distance,
and
s
l
(x
i
) = ∞ , if x
i Є
Ω
l
0, otherwise (2.2)
indicates the presence of a user stroke where Ī is the label opposite l (i.e. if l = F, then Ī = B). Fast Gauss Transform is used
to compute foreground/background color models. P
l
(c) is used for both global similarity and geodesic distances. M
l
(xi) is
computed by
M
l
(x
i
) = P
ĺ
(C ( x
I
) ) ) (2.3)
G
l
(xi) is computed by normalizing the relative foreground/background geodesic distances
G
l
(x
i
) = D
l
(x
i
)
------------------------------- (2.4)
D
F
(x
i
) + D
B
(x
i
)
For boundary term we use:
B (x
i
, x
j
) = 1
------------------------------------- (2.5)
1 + || C ( x
i
) – C ( x
j
) ||
2
where C(x) € [0,255].
To allow for global weighting of relative importance of the region and boundary components,
E (L) = λ
R
Σ R
L i
( x
i
) + λ
B
Σ B (x
i,
x
j
)|
L
i
- L
j
| (2.6)
The boundary weight serves the role of the traditional fixed region/boundary weighting in graph cut methods, and adjusted
to individual images by considering only the size of the image (due to the disproportionate scaling of an objects area (unary
term) and perimeter (boundary term)). The region weight λ
R
is the relative weighting of the geodesic distance and other
region components. Posterior probability of a pixel with color c belonging to foreground (F) or background (B) respectively
is considered, assuming equal priority. This functions as a simple Bayesian classifier in which error can be estimated by
ε = (1 /2) [ ({ Σ
x Є F
P
B
(C(x)) } / {| Ω
F
|} ) + ( { Σ
x Є B
P
F
(C(x)) } / {| Ω
B
|}) ] (2.7)
When there is no error (ε = 0), Color-based terms (M and G) are given full weight, and when the color models become
indistinct (ε ≥0.5), they are given no weight:
λ
R =
1 - 2 ε, if ε < 0.5
0, otherwise (2.8)
The geodesic and boundary terms are further weighted based on the local confidence u(x) of the geodesic components:
u ( x
i
) = ( | D
F
(x
i
) - D
B
(x
i
) | / | D
F
(x
i
) + D
B
(x
i
) | )
γ
(2.9)
ISSN (ONLINE):
2454-9762
ISSN (PRINT):
2454-9762
Available online at www.ijarmate.com
International Journal of Advanced Research in Management, Architecture, Technology and Engineering(IJARMATE)
Vol. 2, Issue 3, March 2016
126
All Rights Reserved © 2016 IJARMATE
where empirically γ= 2 to 2.5 works well.
To weight the geodesic component by u(xi), the region terms are redefined as follows:
R
l
(x
i
) = s
l
( x
i
) + M
l
( x
i
) + u (x
I
) G
l
( x
i
) (2.10)
This maintains the weight of geodesic distance term
Weighting of boundary costs are spatially adapted based on u(x) as follows:
B(xi,xj) = 1+ ( u ( x
i
) + u ( x
j
) ) / 2
----------------------------------- (2.11)
1+ || C ( x
i
) – C ( x
j
) ||
2
When this geodesic confidence is low, this suggests that geodesic segmentation alone would consider this to be near a
boundary, and the effect of the geodesic component is reduced, shifting control to the more accurate edge-finding term. The
net effect of this spatially adaptive weighting is to both increase the relative weighting of the unary geodesic distance term
and increase the cost of a boundary cut in what are clearly interior/exterior regions.
D. Graph cut Segmentation of Liver and Tumors
The Graph-Cut Technique solutions allow avoiding local minima, providing numerical robustness and do not use any
shape-prior characteristics that would constrain too strongly recoverable shapes. The Graph-Cut Algorithm produces also
better segmentation results than other fully automatic methods found in literature in both terms of accuracy and time
processing. To discriminate liver from background, we set a range threshold equal to 2σ. The initialization rules are as
follows:
• v (voxel) Є liver, if I(v) (image intensity of voxel) Є L2 (liver domain) and v Є BIG.
• v Є Background if I(v) Є B2 (Background domain) or if I(v) Є L2 and v does not belong to BIG (biggest 18
connected component after thresholding).
• v Є undetermined otherwise.
Here, Energy function relies on Region term and Boundary term. I (v) stands for the image intensity of voxel, and BIG
for the biggest 18-connected component after similar thresholding. Graph-cut method is not iterative and is based on global
minimization of defined energy function classes on a discrete graph.
III. SIMULATION
RESULTS
Automatic liver segmentation by the Geodesic graph-cut algorithm succeeds to include the tumors inside liver
segmentation. The reason is that the Geodesic graph-cuts include neighboring contextual information enabling to overstep
edges between tumors or vessel and liver parenchyma.
A. Liver and Tumor Segmentation Results
Liver and Tumor Segmentation results by Geodesic Graph cut method are given below in Figure 2:
ISSN (ONLINE):
2454-9762
ISSN (PRINT):
2454-9762
Available online at www.ijarmate.com
International Journal of Advanced Research in Management, Architecture, Technology and Engineering(IJARMATE)
Vol. 2, Issue 3, March 2016
127
All Rights Reserved © 2016 IJARMATE
Fig. 2 (a) Input Image. (b) Liver Seed Region. (c) Histogram of the Liver Region
(d)Segmented Liver Region. (e)Final Tumor Contour (f) Finally Segmented Liver and Tumor
B. Segmentation Accuracy of Liver and Tumor
Geodesic Graph Cut algorithms and Graph-cut Algorithms produced a liver volume with a high level of overlapping given
by an average DSC of 96.17% ± 0.87 and of 95.49 ± 0.66, respectively. Geodesic Graph Cut algorithm reached therefore a
slightly better average DSC, but on nine cases over 25 (36%) Geodesic Graph Cut algorithm produced a liver surface
segmentation with a higher DSC than Graph cuts. Geodesic graph-cut algorithm detected 48 tumors leading to a detection rate
of 92.31%, while Graph cut algorithm detected 44 tumors for a detection rate of 84.62%. Regarding the volume overlapping of
hepatic tumors, Geodesic graph-cut algorithm provided an average DSC of 88.65% ± 3.01, while Graph cut method reached a
lower average DSC equal to 87.10% ± 2.99.These values are shown in Table – I.
TABLE
I
COMPARISON OF LIVER AND TUMOR SEGMENT ATION
Liver Tumor
Performance
parameters
GRAPH CUT GEODESIC
GRAPH-CUT GRAPH CUT GEODESIC
GRAPH-CUT
Mean Standard
Deviation Mean Standard
Deviation Mean Standard
Deviation Mean Standard
Deviation
DSC 96.16% 0.87% 87.1 % 2.99 % 87.1 % 2.99 % 88.65 % 3.01 %
FNR 3.87% 0.98% 8.97 % 2.26 % 8.97 % 2.26 % 9.89 % 2.93 %
FPR 3.35% 1.19% 8.99 % 3.95 % 8.99 % 3.95 % 6.10 % 2.52 %
Processing time 1.505s 0.196s 1.009s 0.096s 1.796s 0.128s 1.945s 0.308s
IV. C
ONCLUSIONS
This study presented the implementation of two fully automatic liver and tumors segmentation techniques and their
comparative assessment. The described adaptive initialization method enabled fully automatic liver surface segmentation with
both Graph cut technique and Geodesic graph-cut techniques, demonstrating the feasibility of two different approaches. The
comparative assessment showed that the Geodesic graph-cut method provided superior results in terms of accuracy and did
ISSN (ONLINE):
2454-9762
ISSN (PRINT):
2454-9762
Available online at www.ijarmate.com
International Journal of Advanced Research in Management, Architecture, Technology and Engineering(IJARMATE)
Vol. 2, Issue 3, March 2016
128
All Rights Reserved © 2016 IJARMATE
not present the described main limitations related to the Graph cuts method. The proposed image processing method will
improve computerized CT-based visualizations enabling non invasive diagnosis of hepatic tumors.
R
EFERENCES
[1] Christo Ananth, G.Gayathri, M.Majitha Barvin, N.Juki Parsana, M.Parvin Banu, “Image Segmentation by Multi-shape
GC-OAAM”, American Journal of Sustainable Cities and Society (AJSCS), Vol. 1, Issue 3, January 2014, pp 274-280
[2] Christo Ananth, D.L.Roshni Bai , K.Renuka, C.Savithra, A.Vidhya, “Interactive Automatic Hepatic Tumor CT Image
Segmentation”, International Journal of Emerging Research in Management &Technology (IJERMT), Volume-3, Issue-1,
January 2014,pp 16-20
[3] Christo Ananth, D.L.Roshni Bai, K.Renuka, A.Vidhya, C.Savithra, “Liver and Hepatic Tumor Segmentation in 3D CT
Images”, International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), Volume
3,Issue-2, February 2014,pp 496-503
[4] Christo Ananth, Karthika.S, Shivangi Singh, Jennifer Christa.J, Gracelyn Ida.I, “Graph Cutting Tumor Images”,
International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE), Volume 4,
Issue 3, March 2014,pp 309-314
[5] Christo Ananth, G.Gayathri, I.Uma Sankari, A.Vidhya, P.Karthiga, “Automatic Image Segmentation method based on
ALG”, International Journal of Innovative Research in Computer and Communication Engineering (IJIRCCE), Vol. 2,
Issue 4, April 2014,pp- 3716-3721
[6] Christo Ananth, S.Santhana Priya, S.Manisha, T.Ezhil Jothi, M.S.Ramasubhaeswari, “CLG for Automatic Image
Segmentation”, International Journal of Electrical and Electronics Research (IJEER), Vol. 2, Issue 3, Month: July -
September 2014, pp: 51-57
[7] Christo Ananth, S.Suryakala, I.V.Sushmitha Dani, I.Shibiya Sherlin, S.Sheba Monic, A.Sushma Thavakumari, “Vector
Image Model to Object Boundary Detection in Noisy Images”, International Journal of Advanced Research in
Management, Architecture, Technology and Engineering (IJARMATE), Volume 1,Issue 2,September 2015, pp:13-15