MEDICAL IMAGE TEXTURE SEGMENTATION USINGRANGE FILTER

Natarajan Meghanathan, et al. (Eds): ITCS, SIP, JSE-2012, CS & IT 04, pp. 273–280, 2012.
© CS & IT-CSCP 2012 DOI : 10.5121/csit.2012.2125
MEDICAL IMAGE TEXTURE SEGMENTATION
USINGRANGE FILTER
Amir Rajaei, LalithaRangarajan and ElhamDallalzadeh
Department of Studies in Computer Science, Mansagangothri,
University of Mysore, Mysore, India
rajaei80amir@gmail.com,lali85arun@yahoo.co.in,
elhamdallalzadeh@gmail.com
ABSTRACT
Medical image segmentation is a frequent processing step in image understanding and computer
aided diagnosis. In this paper, we propose medical image texture segmentation using texture
filter. Three different image enhancement techniques are utilized to remove strong speckle noise
as well enhance the weak boundaries of medical images. We propose to exploit the concept of
range filtering to extract the texture content of medical image. Experiment is conducted on
ImageCLEF2010 database. Results show the efficacy of our proposed medical image texture
segmentation.
KEYWORDS
Medical Image Texture Segmentation, Image Enhancement, Texture Filter, Range Filter
1. INTRODUCTION
Computer Aided Diagnosis (CAD) is an effective tool for analyzing the particular anatomical
structure of medical images leading to better diagnosis and decision-making. The number of
medical images has grown significantly in the recent years. These images are very important for
clinical diagnosis, localization of pathology, study of anatomical structure, treatment planning,
evolution of therapy, computer integrated surgery, surgical planning, post surgical assessment and
abnormality detection. It is well-established fact that segmentation plays an important role in
anatomical structure recognition. Segmentation is used to extract the anatomical structure in
medical images.
There exist many methods for automatic and semi-automatic medical image segmentation.
However, medical image segmentation may fail to segment well the anatomical structure, the
region of interest. Unknown noise, poor image contrast, inhomogeneity and weak boundaries
existing in medical images have made the segmentation process extremely difficult. Further,
medical images contain complicated structures.
The techniques such as thresholding[12], region growing[13], fast greedy algorithm[5], Fuzzy C-
mean (FCM) and statistical models[14], active contour model [4], watershed segmentation[9,10]
and clustering[8] have been proposed for medical image segmentation. Felzenszwalb and Daniel
[1] proposed Minimum Spanning Tree (MST) for segmentation of medical images. MST is one of

274 Computer Science & Information Technology (CS & IT)
the graph-based segmentation methods that it is computationally efficient for capturing
perceptually the important aspects of image regions. However, it is prone to cause the problem of
over segmentation with some long and narrow redundant areas between two regions. In [2],
authors describe an improved segmentation algorithm based on Minimum Spanning Tree (MST).
To overcome the problem of over segmentation, an adaptive neighbour mode is defined by
adding links between non-neighbour pixels of an image. They explored their proposed segmented
method on three different modalities of medical images such as MR, CT and X-ray.
Gradient Vector Flow (GVF) snake model is used in image segmentation. In [3], GVF snake is
proposed to overcome the inability of tracking concavityat boundary. However, noise existing in
medical images may cause the boundaries of medical images not to converge.Hence, in these
complicated images GVF still fails to capture object contours. To improve GVF snake model,
Chuag and Li [11] proposed a new downstream algorithm based on Extended Gradient Vector
Flow (E-GVF) for segmentation of multi-objects.In [7], they focused on texture features as well
as region growing algorithm to automate segmentation of the MR images. Co-occurrence texture
features and semi-variogram texture features are extracted from the image and then the seeded
region growing algorithm is run on these feature spaces. With a given region of interest, a seed
point is automatically picked up based on three homogeneity criteria. Medical ultrasound images
are poor in contrast and they have strong speckle noise. Hence, traditional image segmentation
methods fail to segment the ultrasound images satisfactorily. In [6], the ultrasound images are
segmented using texture feature and graph cut method. The texture feature parameters are
obtained according to the Gary level Co-occurrence Matrix (GLCM).
From the literature survey it is observed that a number of segmentation methods are applied on
only specific anatomical structure such as the use of GVF for segmentation of kidney images.
Moreover, the proposed methods are exploited on particular medical imaging modalities.
Furthermore, the well-known characteristics of medical images such as unknown noise, poor
image contrast, inhomogenity and weak boundaries affect the anatomical structure resulting in
poor segmentation. In this direction, we propose an algorithm to segment medical images that
include various anatomical structures belonging to different medical imaging modalities such as
X-ray, CT, MR, US, PET, PET-CT, Xr-Angio, NM, Micro. Besides, the poor characteristics of
medical images are moderated to have accurate medical image segmentation. The characteristic
of regions in an image are analyzed by their texture content.
The rest of the paper is organized as follows. Image filtering is discussed in section 2. Our
proposed algorithm for texture segmentation of medical images is explained in section 3. Section
4 gives the details of the experiments followed by the results. The paper is concluded in section 5.
2. IMAGE FILTERING
Filtering is perhaps the most fundamental operation of image processing. The term filtering can
be defined as the value of the filtered image at a given location. It is a function of the values of
the input image in a small neighbourhood of the same location. Filter operations can be used to
sharpen or blur images, to selectively suppress image noise, to detect and enhance edges, or to
alter the contrast of the image. The filters use the local statistical variations in an image to reveal
elements of the image texture.
2.1. Analyzing the Texture of an Image
Texture analysis refers to the characterization of regions in an image by their texture content.
Texture analysis attempts to quantify intuitive qualities described by terms such as rough,

Computer Science & Information Technology (CS & IT) 275
smooth, silky or bumpy as a function of the spatial variation in pixel intensities. In this sense, the
roughness or bumpiness refers to variations in the intensity values or gray levels.
Texture analysis is used in a variety of applications, including remote sensing, automated
inspection and medical image processing. Texture analysis can be used to find the texture
boundaries and texture segmentation. Texture analysis can be helpful when objects in an image
are more characterized by their texture than by intensity and hence, traditional thresholding
techniques cannot be used effectively. The texture analysis functions such as range filtering,
standard deviation filtering and entropy filtering, filter an image using standard statistical
measures. These statistics can characterize the texture of an image. They provide information
about the local variability of the pixels intensity values in an image. In the areas with smooth
texture, the range values in the neighbourhood around a pixel will be small and similarity,the
range values are large in the areas of rough texture.
The texture functions all operate in a similar way. They define a neighbourhood around the pixel
of interest calculate the statistic for that neighbourhood and use the computed statistic value as
the value of the pixel of interest in the output image. The example shown in Figure 1 illustrates
how the range filtering function operates on a simple matrix. In this example, the value of
element B (2, 4) is calculated from A (2, 4). Range filtering function use m by n pixels, in this
example 3 × 3, neighbourhood around the pixels.
Figure1.Range filtering function
3. PROPOSED METHOD
Image texture includes the local spatial pattern, scale and magnitude of brightness variations,
smoothness or roughness of the image. The output image can be used as the basis for further
image analysis such as image texture segmentation. Hence, in this paper we exploit 3 different
kinds of image enhancement technique to remove the strong speckle noise existing in a medical
image as well image edge enhancement. The details are explained in section 3.1. We propose
texture filtering to segment medical image texture. We propose to utilize the range filtering for
segmentation.Image texture segmentation using range filtering is discussed in section 3.2.
3.1. Pre-processing
The contrast of medical images is very low and these images have strong speckle noise. We apply
2D adaptive noise-removal, median and 2D order-statistic filtering to remove the noise and
enhance the weak boundaries of medical images. 2D adaptive noise removal is a low-pass filter
on gray scale images. 2D adaptive noise removal uses a pixel wise adaptive wiener method based
on the statistics estimated, mean and standard deviation, from a local neighbourhood of size m by
n for each pixel. Result of image enhancement using 2D adaptive noise removal is shown in
Figure 2(b). To remove ‘salt and pepper’ noise existing in medical images, we use median
filtering. Median filtering is a nonlinear operation which is very effective to simultaneously

reduce noise and preserve edges. Each output pixel contains the median value in p by q
neighbourhood around the corresponding pixel of the input image. Figure 2(c) shows removal of
“salt and pepper” noise from a medical image using median filtering. The order statistic filter is
then applied to enhance the regions of an anatomical structure. The 2D order-statistic filtering
replaces each pixel of an image by the nth
order element in the sorted set of neighbours of size r by
s specified by the nonzero elements in domain. Image edge enhancement using 2D order-statistics
filtering is shown in Figure 2(d). In this paper, the medical image pre-processing step is done by
the three discussed image enhancement functions as shown in Figure 2(e).
(a)
(b) (c) (d)
(e)
Figure2.(a) Original image. (b) Applied adaptive noise removal on an image.
(c) Applied median filtering on an image. (d) Applied order-statistic filtering on an image.
(e) Pre-processedimage.
3.2. Image Texture Segmentation
Medical image segmentation is a critical task for analyzing the structural content of the images.
Surgical planning, early disease detection and 3D visualization can be provided for the physicians
by proper image segmentation. Medical image texture segmentation can be widely applicable to
evaluate an area of body that is not externally visible. The texture filter function can detect the
texture regions of a medical image. It can be argued that there is a little variation in the gray level
values of the background of medical imagessince the background is smooth.Hence in the
foreground the surface contours of the anatomical structure exhibit more texture. Therefore, the
foreground pixels of medical images have more variability and thus higher range values. Range

filtering is one of the texture analysis methods that filter an image. Range filtering makes the
edges and contours of the anatomical structures of medical images become more
apparent.Consequently, the range filtering is explored for medical image texture segmentation as
explained in the following sub section.
3.2.1. Range Filtering
A local sub range filtering uses the statistical sub range of the pixel intensities within the window.
The range distance is often used in statistics as a measure of the sample variation. Edges are
typically characterized by discontinuities in mean intensity. If the variations existing among the
local intensity values are low then the local range distance is small. Similarly, the local range
distance is large if a region has large discontinuities in intensity values. Hence, range filtering is
able to detect pixel intensity values of the edges within a window.The output of the range filtering
is the difference between maximum and minimum range values of the filtered window. The range
values in the filtered window are multiplied by a constant value to provide strong edges. Local
range filtering tend to have short calculation time as it operates on only a small number of
input for each output pixel.Moreover, range filtering can have better segmentation through
creating a structure element to extract the neighbourhood for the local range of values. Hence a
structuring element is created to extract the neighbourhood for the local range of values. Figure 3
illustrates the range filtered medical image using the defined structure element.
(a) (b) (c)
Figure 3.(a) Pre-processedimage. (b) Range filtered medical image using horizontal
linestructure. (c) Range filtered image using vertical line structure.
4. EXPERIMENTAL RESULTS
4.1 Image Dataset
In this paper, ImageCLEF2010 database is used for segmentation of medical images. Experiments
are conducted on different medical imaging modalities having different sizes. The medical
imaging modalities are nine in number namely, Compute Tomography (CT), Magnetic
Resonance (MR), Ultrasound (US), Nuclear Medicine (NM), Xr-Angio, Positron Emission
Tomography (PET), PET-CT, Micro and X-ray. Medical images include various anatomical
structures and image orientation.
4.2 EXPERIMENTAL SETUP
Medical images contain strong speckle noise. To remove noise and smooth the images we have
applied 2D adaptive noise removal using neighbourhood of size 3 by 3. Moreover, medical
images suffer from “salt and paper” noise. We remove the existing ‘salt and paper’ noise using
median filtering. Each output pixel contains the median value of 9 by 9 neighbourhoods

surrounding the pixel of the input image. Further, It is well known that the content of medical
images are inhomogeneous having weak boundaries. We use 2D order-statistic filtering by the 3rd
order element in the sorted set of neighbours of size 3 by 3 in domain.
We have exploited range filtering using ‘line’ structure element of size 1×2 and 2×1 in horizontal
and vertical directions respectively. Next, we have applied sum operation on the images extracted
using range filtering in both horizontal and vertical directions. Figure 4(a) shows the added image
obtained from the medical images illustrated in Figure 3(b) and 3(c) respectively. In addition, to
improve the extracted edges of the ranged filtered medical image shown in Figure 4(a) we scale
the image by multiplying with the fix value of ‘k’. In this experiment, the value of ‘k’ is set to 20
empirically. Figure 4(b) illustrates the scaled range filtered medical image.
+
(a) (b)
Figure 4.(a) Range filteredmedical images after filtering in horizontal and vertical directions are
added. (b) Scaled range filtered medical image.
Next, we have used ‘clean’ morphological operation to remove all detected isolated pixels. Figure
5 demonstrates the segmentation of the anatomical structure medical image using our proposed
texture segmentation method.
(a) (b)
Figure 5.(a) Original image. (b) Medical imagesegmentation.
In this paper, experiments are conducted on nine different medical imaging modalities having
different anatomical structures. The proposed medical image texture segmentation using range
filtering is shown in Figure 6.
5. CONCLUSION
In this paper, 2D adaptive noise removal, median and 2D order-statistic filtering are applied to
remove strong speckle noise and enhance the weak boundaries of medical images. We segment
various anatomical structures of different medical imaging modalities using texture filtering. The

range filtering is exploited for medical image texture segmentation.Results show the efficiency,
simplicity and robustness of medical image texture segmentation
(a)CT (b)MR (c)Xray
(d)US (e)Xr-Angio (f)PET
(g)PET-CT (h)Micro (i)NM
Figure 6.(a-i)Segmented anatomical structures of differentmedical imagingmodalities.

REFERENCE
[1] Pedro F. Felzenszwalb and P, Daniel, (2004) “Efficient Graph-Based Image Segmentation,”
International Journal of Computer Vision, Vol.59 (2), pp. 167-181.
[2] Y. Lu, Y. Quan, Z. Zhang and G. Wang, (2009) “MST Segmentation for Content-Based Medical
Image Retrieval”, International Conference on Computational Intelligent and Software Engineering,
pp.1-4.
[3] J. Cheng, R. Xue, W. Lu and R. Jia,(2008) “Segmentation of Medical Images with Canny Operator
and GVF Snake Model”, 7th World Congress on Intelligent Control and Automation, pp.1777-1780,
chaina
[4] L.D. Cohen, I.Cohen, (1993) “Finite-element Methods for Active Contour models and Balloons for
2D and 3D Images,” IEEE Transaction on Image Processing on Pattern Analysis & Machine
Intelligence Vol.25, pp.1131-1147.
[5] D.J.Williams, M.Shah, (1991) “A Fast Algorithm for Active Contours and Curvature Estimation,”
CVGIP: Image Understanding, vol.55, pp.14-26, Jan.
[6] Z. Chang-ming, G. Guo-chang, L. Hai-bo, S. Jing and Y. Hualong, “Segmentation of Ultrasound
Image Based on Texture Feature and Graph Cut”, International Conference on Computer Science and
Software Engineering, pp.795-798.
[7] J. Wu, S. Poehlman, M. Nosewrthy and M.V. Kamath, (2008) “Texture Feature based Automated
Seeded Region Growing in Abdominal MRI Segmentation”, International Conference on Biomedical
Engineering and Informatics, pp.263-267.
[8] TianD, Fan L,( 2007) “ A Brain MR Images Segmentation Method Based on SOM Neural Network”,
in the First International Conference on Bioinformatics and Biomedical Engineering, pp.868-689.
[9] Adalsteinsson D, Sethian JA, (1995) “A Fast Level Set Method for Propagating Interfaces,” Journal
of Computing Physics, 118, pp.269-277.
[10] Li N, Liu M and Li Y,( 2007) ” Image Segmentation Algorithm using Watershed Transform and
Level Set Method,” IEEE Transaction International Conference on Acoustics, Speech and Signal
Processing, pp.613-616.
[11] C.Chuang, W.Lie, (2004) “A Downstream Algorithm Based on Extended Gradient Vector Fellow
Field for Object Segmentation,” IEEE Transaction on Image Processing, Vol.13, pp.1379-1392,
October.
[12] Suzuki H, Toriwaki J,(1991) “Automatic Segmentation of Head MRI Images by Knowledge Guided
Thresholding”, Computer Medical Imaging Graph.Vol.15(4), pp.233-40.
[13] Robb RA, (2000) “Biomedical Imaging, Visualization and Analysis”, edited by Wiley-Liss, USA.
[14] Hall Lo, Bensaid AM, Clarke LP, Velthuizen RP, Silbeger MS., Bezdek J, “ A Comparison of Neural
Network and Fuzzy Clustering Techniques in Segmenting Magnetic Resonance Images of the Brain ”,
IEEE Transaction Neural Networks, Vol.26(4), pp. 479-486.

MEDICAL IMAGE TEXTURE SEGMENTATION USINGRANGE FILTER

More Related Content

What's hot (19)

Similar to MEDICAL IMAGE TEXTURE SEGMENTATION USINGRANGE FILTER (20)

More from cscpconf (20)

Recently uploaded (20)

MEDICAL IMAGE TEXTURE SEGMENTATION USINGRANGE FILTER