A Review of different method of Medical Image Segmentation
1 like285 views
The document reviews various methods of medical image segmentation, highlighting that it is crucial for image analysis in fields like healthcare. Key segmentation techniques discussed include edge detection, region-based methods, thresholding, and clustering. The paper identifies challenges in adapting segmentation methods for complex images and emphasizes ongoing research in developing a universal segmentation algorithm.
![IJSRD - International Journal for Scientific Research & Development| Vol. 1, Issue 9, 2013 | ISSN (online): 2321-0613
All rights reserved by www.ijsrd.com 1750
A Review of different method of Medical Image Segmentation
Kinjal Patel1
Avani Dave2
1, 2
Master of Computer Engineering
Abstract—Image Segmentation is a most important task of
image analysis. Number of method used for image
segmentation. Image segmentation mainly used in different
field like medical image analysis, character re-congestion
etc. A segmentation method finds the sets that are different
structure from each other and completion of segmentation
process that cover entire image.
Key words: Segmentation, Edge detection method, Region
based segmentation, Thresholding
I. INTRODUCTION
Segmentation refers to the process of partitioning a digital
image into multiple regions (sets of pixels) [2].The goal of
segmentation is to simplify and/or change the representation
of an image into something that is more meaningful and
easier to analyze [2].Image segmentation is the partitioning
of an image into non-overlapping, constituent regions that
are homogeneous with respect to some characteristics [3].A
segmentation method finds those sets that correspond to
distinct anatomical structures or regions of interest in the
image [3].The result of image segmentation is a set of
regions that collectively cover the entire image. Each of the
pixels in a region is similar with respect to some
characteristic or computed property, such as color, intensity,
or texture [2]. Adjacent regions are significantly different
with respect to the same characteristics. Several general-
purpose algorithms and techniques have been developed for
image segmentation [2].In an initial stage, the segmentation
is used to separate the image in parts that represents an
interest object that may be used in a specific study [2].
There are several methods that intend to perform such task,
but are difficult to find a method that can easily adapt to
different type of images, that often are very complex or
specific [2]. Medical images play vital role in assisting
health care providers to access patients for diagnosis and
treatment[1].Medical image segmentation is an important
application of image segmentation in medical research,
however there isn’t a common and effective segmentation
method to meet the command of the entire medical image
(CT,MRI and PET) [5]. Based on different technologies,
image segmentation approaches are currently divided into
following categories, based on two properties of image.
Detecting Discontinuities: It means to partition an image
based on abrupt changes in intensity, this includes image
segmentation algorithms like edge detection [9].
Detecting Similarities: It means to partition an image into
regions that are similar according to a set of predefined
criterion; this includes image segmentation algorithms like
thresholding, region growing, region splitting and merging
[9].
II. CLASSIFICATION OF SEGMENTATION
TECHNIQUES
In this section briefly describe various methods used for im-
ge segmentation. Some of those methods are Edge Detection
Method, Region Based Segmentation Method, Thresholding
Method, and Clustering Method.
Edge Detection MethodA.
There are two main edge based segmentation methods- gray
histogram and gradient based method [9]. Edge detection is
a term in image processing and computer vision, it refers to
algorithms which aim at identifying points in a digital image
at which there is an abrupt change in image brightness or
more formally, has discontinuities or simply where there is a
jump in intensity from one pixel to the next [9]. Gradient is
the first derivative for image f(x, y), when there is abrupt
change in intensity near edge and there is little image noise,
gradient based method works well. This method involves
convolving gradient operators with the image [1, 9].
Region Based Segmentation MethodB.
For image segmentation region growing method is a well-
developed technique [6]. The basic idea of region growing
method is a collection of pixels with similar properties to
form a region [9]. For region growing, seeds can be
automatically or manually selected [10]. Their automated
selection can be based on finding pixels that are of interest,
e.g. the brightest pixel in an image can serve as a seed pixel
[10]. An operator manually selects a seed point and extracts
all pixels that are connected to the initial seed based on
some predefined criteria [6]. Region growing can also be
sensitive to noise, causing extracted regions to have holes or
even become disconnected [6]. In Region Splitting and
Merging, the image Subdivided into a set of arbitrary
disjoints regions and then merge and/or split the region
according to the given condition for segmentation [9]. The
main purpose of image segmentation is to segment an image
into the homogenous regions [9].
Thresholding MethodC.
Threshold is one of the widely methods used for image
segmentation [4]. Image segmentation by Thresholding is a
simple but powerful approach for segmenting images having
light objects on dark background [1]. The segmentation is
done by grouping all pixels with intensity between two such
thresholds into one class [6]. A process to determinate more
than one threshold value is called multi-thresholding [6].
Thresholding operation convert a multilevel image into a
binary image i.e., it choose a proper threshold T, to divide
image pixels into several regions and separate objects from
background [1]. Any pixel (x, y) is considered as a part of
object if its intensity is greater than or equal to threshold
value i.e., f(x, y) ≥T, else pixel belong to background [1, 7].
As per the selection of Thresholding value, two types of
Thresholding methods are in existence [1, 8], global and
local Thresholding. When T is constant, the approach is
called global Thresholding otherwise it is called local
Thresholding [1].](https://image.slidesharecdn.com/ijsrdv1i9014-140811082702-phpapp02/85/A-Review-of-different-method-of-Medical-Image-Segmentation-1-320.jpg)
![A Review of Different method of Image Segmentation
(IJSRD/Vol. 1/Issue 9/2013/0014)
All rights reserved by www.ijsrd.com 1751
Clustering MethodD.
Clustering can be termed here as a grouping of similar
images in the database [9]. Clustering is done based on
different attributes of an image such as size, color, texture
etc [9]. Clustering use no training stages rather train
themselves using available data [1]. Two methods mainly
used for clustering based segmentation.
K-Means is one of the simplest unsupervised
learning algorithms. In K means objects are classified as
belonging to one of k groups exclusively, k is chosen priori
[11]. The main idea is to define k centroids, one for each
cluster [13]. These centroids should be placed in a cunning
way because of different location causes different result
[13].
Fuzzy C-Mean (FCM) is an unsupervised
clustering algorithm that has been applied to wide range of
problems involving feature analysis, clustering and classifier
design [12, 13]. FCM has a wide domain of applications
such as agricultural engineering, astronomy, chemistry,
geology, image analysis, medical diagnosis, shape analysis,
and target recognition [12, 13]. Fuzzy C-means (FCM)
algorithm is one of the most popular fuzzy clustering
methods widely used in various tasks of pattern recognition,
data mining, image processing, expression data Recognition
etc.
III. CONCLUSION
In this paper Describe number of method describe that used
for image segmentation. Image segmentation has a
promising future as the universal segmentation algorithm
and has become the focus of contemporary research. In
medical image analysis used method of image segmentation
like Region based segmentation; Level set method,
Thresholding method and Edge detection method etc.
REFERENCES
[1] Prof. Dinesh D. Patil, Ms. Sonal G. Deore, “Medical
Image Segmentation: A Review,” IJCSMC, Vol. 2,
Issue. 1, pg.22 – 27, January 2013.
[2] Pritee Gupta, Vandana Malik, Mallika Gandhi,
“Implementation of Multilevel Threshold Method for
Digital Images Used In Medical Image Processing,”
IJARCSSE, Volume 2, Issue 2, February 2012.
[3] Ayelet Dominitz, Introduction to Medical Imaging
[4] Jay Acharya, Sohil Gadhiya, Kapil Raviya,
“segmentation techniques for image analysis: a review,”
International Journal of Computer Science and
Management Research Vol 2 Issue 1 January 2013.
[5] Wankai Deng , Wei Xiao, He Deng, Jianguo Liu, “MRI
Brain Tumor Segmentation With Region Growing
Method Based On The Gradients And Variances Along
And Inside Of The Boundary Curve,” International
Conference on Biomedical Engineering and Informatics
(BMEI 2010)(IEEE), 3rd 2010
[6] Anamika Ahirwar, “Study of Techniques used for
Medical Image Segmentation and Computation of
Statistical Test for Region Classification of Brain
MRI,” I.J. Information Technology and Computer
Science, Volume 5 April 2013.
[7] Wahba Marian, “An Automated Modified Region
Growing Technique for Prostate Segmentation in Trans-
Rectal Ultrasound Images”, Master’s Thesis,
Department of Electrical and Computer Engineering,
University of Waterloo, Waterloo, Ontario, Canada,
2008.
[8] Y. Zhang, H. Qu, Y. Wang, “Adaptive Image
Segmentation Based on Fast Thresholding and Image
Merging”, Artificial reality and Telexistence-
Workshops, pp. 308-311, 1994.
[9] Salem Saleh Al-amri, N.V. Kalyankar and Khamitkar
S.D,” Image Segmentation by Using Threshold
Techniques,” JOURNAL OF COMPUTING,
VOLUME 2, ISSUE 5, MAY 2010, ISSN 2151-9617.
[10]R. B. Dubey, M. Hanmandlu, S. K. Gupta and S. K.
Gupta,” Region growing for MRI brain Tumor volume
analysis,” Indian Journal of Science and Technology,
Vol.2 No. 9, Sep 2009, ISSN: 0974- 6846.
[11]mansur rozmin, prof. chhaya suratwala, prof. vandana
shah,” implementation of hard c-means clustering
algorithm for medical image segmentation,” journal of
information, knowledge and research in electronics and
communication engineering, volume – 02, issue – 02,
nov 12 to oct 13, ISSN: 0975 – 6779
[12]Archana Lala, Jitendra Kumar Gupta , Mrinalini
Shringirishi, “ implementation of k-means clustering
and fuzzy c-means algorithm for brain Tumor
segmentation,” International Journal of Computer
Engineering & Science, Volume 3, Issue 1, pp. 27-33,
Sept 2013. ISSN: 2231–6590.
[13]Ms. Pritee Gupta, Ms Mrinalini Shringirishi ,Dr.
Yashpal singh, “Implementation of Brain Tumor
Segmentation in brain MR Images using K Means
Clustering and Fuzzy C-Means Algorithm,”
International Journal of Computers & Technology,
Volume 5, No. 1, May -June, 2013, ISSN 2277-3061.
[14]Mahesh Yambal, Hitesh Gupta, ” Image Segmentation
using Fuzzy C Means Clustering: A survey”,
International Journal of Advanced Research in
Computer and Communication Engineering, Vol. 2,
Issue 7, July 2013.](https://image.slidesharecdn.com/ijsrdv1i9014-140811082702-phpapp02/85/A-Review-of-different-method-of-Medical-Image-Segmentation-2-320.jpg)
A Review of different method of Medical Image Segmentation
- 1. IJSRD - International Journal for Scientific Research & Development| Vol. 1, Issue 9, 2013 | ISSN (online): 2321-0613 All rights reserved by www.ijsrd.com 1750 A Review of different method of Medical Image Segmentation Kinjal Patel1 Avani Dave2 1, 2 Master of Computer Engineering Abstract—Image Segmentation is a most important task of image analysis. Number of method used for image segmentation. Image segmentation mainly used in different field like medical image analysis, character re-congestion etc. A segmentation method finds the sets that are different structure from each other and completion of segmentation process that cover entire image. Key words: Segmentation, Edge detection method, Region based segmentation, Thresholding I. INTRODUCTION Segmentation refers to the process of partitioning a digital image into multiple regions (sets of pixels) [2].The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze [2].Image segmentation is the partitioning of an image into non-overlapping, constituent regions that are homogeneous with respect to some characteristics [3].A segmentation method finds those sets that correspond to distinct anatomical structures or regions of interest in the image [3].The result of image segmentation is a set of regions that collectively cover the entire image. Each of the pixels in a region is similar with respect to some characteristic or computed property, such as color, intensity, or texture [2]. Adjacent regions are significantly different with respect to the same characteristics. Several general- purpose algorithms and techniques have been developed for image segmentation [2].In an initial stage, the segmentation is used to separate the image in parts that represents an interest object that may be used in a specific study [2]. There are several methods that intend to perform such task, but are difficult to find a method that can easily adapt to different type of images, that often are very complex or specific [2]. Medical images play vital role in assisting health care providers to access patients for diagnosis and treatment[1].Medical image segmentation is an important application of image segmentation in medical research, however there isn’t a common and effective segmentation method to meet the command of the entire medical image (CT,MRI and PET) [5]. Based on different technologies, image segmentation approaches are currently divided into following categories, based on two properties of image. Detecting Discontinuities: It means to partition an image based on abrupt changes in intensity, this includes image segmentation algorithms like edge detection [9]. Detecting Similarities: It means to partition an image into regions that are similar according to a set of predefined criterion; this includes image segmentation algorithms like thresholding, region growing, region splitting and merging [9]. II. CLASSIFICATION OF SEGMENTATION TECHNIQUES In this section briefly describe various methods used for im- ge segmentation. Some of those methods are Edge Detection Method, Region Based Segmentation Method, Thresholding Method, and Clustering Method. Edge Detection MethodA. There are two main edge based segmentation methods- gray histogram and gradient based method [9]. Edge detection is a term in image processing and computer vision, it refers to algorithms which aim at identifying points in a digital image at which there is an abrupt change in image brightness or more formally, has discontinuities or simply where there is a jump in intensity from one pixel to the next [9]. Gradient is the first derivative for image f(x, y), when there is abrupt change in intensity near edge and there is little image noise, gradient based method works well. This method involves convolving gradient operators with the image [1, 9]. Region Based Segmentation MethodB. For image segmentation region growing method is a well- developed technique [6]. The basic idea of region growing method is a collection of pixels with similar properties to form a region [9]. For region growing, seeds can be automatically or manually selected [10]. Their automated selection can be based on finding pixels that are of interest, e.g. the brightest pixel in an image can serve as a seed pixel [10]. An operator manually selects a seed point and extracts all pixels that are connected to the initial seed based on some predefined criteria [6]. Region growing can also be sensitive to noise, causing extracted regions to have holes or even become disconnected [6]. In Region Splitting and Merging, the image Subdivided into a set of arbitrary disjoints regions and then merge and/or split the region according to the given condition for segmentation [9]. The main purpose of image segmentation is to segment an image into the homogenous regions [9]. Thresholding MethodC. Threshold is one of the widely methods used for image segmentation [4]. Image segmentation by Thresholding is a simple but powerful approach for segmenting images having light objects on dark background [1]. The segmentation is done by grouping all pixels with intensity between two such thresholds into one class [6]. A process to determinate more than one threshold value is called multi-thresholding [6]. Thresholding operation convert a multilevel image into a binary image i.e., it choose a proper threshold T, to divide image pixels into several regions and separate objects from background [1]. Any pixel (x, y) is considered as a part of object if its intensity is greater than or equal to threshold value i.e., f(x, y) ≥T, else pixel belong to background [1, 7]. As per the selection of Thresholding value, two types of Thresholding methods are in existence [1, 8], global and local Thresholding. When T is constant, the approach is called global Thresholding otherwise it is called local Thresholding [1].
- 2. A Review of Different method of Image Segmentation (IJSRD/Vol. 1/Issue 9/2013/0014) All rights reserved by www.ijsrd.com 1751 Clustering MethodD. Clustering can be termed here as a grouping of similar images in the database [9]. Clustering is done based on different attributes of an image such as size, color, texture etc [9]. Clustering use no training stages rather train themselves using available data [1]. Two methods mainly used for clustering based segmentation. K-Means is one of the simplest unsupervised learning algorithms. In K means objects are classified as belonging to one of k groups exclusively, k is chosen priori [11]. The main idea is to define k centroids, one for each cluster [13]. These centroids should be placed in a cunning way because of different location causes different result [13]. Fuzzy C-Mean (FCM) is an unsupervised clustering algorithm that has been applied to wide range of problems involving feature analysis, clustering and classifier design [12, 13]. FCM has a wide domain of applications such as agricultural engineering, astronomy, chemistry, geology, image analysis, medical diagnosis, shape analysis, and target recognition [12, 13]. Fuzzy C-means (FCM) algorithm is one of the most popular fuzzy clustering methods widely used in various tasks of pattern recognition, data mining, image processing, expression data Recognition etc. III. CONCLUSION In this paper Describe number of method describe that used for image segmentation. Image segmentation has a promising future as the universal segmentation algorithm and has become the focus of contemporary research. In medical image analysis used method of image segmentation like Region based segmentation; Level set method, Thresholding method and Edge detection method etc. REFERENCES [1] Prof. Dinesh D. Patil, Ms. Sonal G. Deore, “Medical Image Segmentation: A Review,” IJCSMC, Vol. 2, Issue. 1, pg.22 – 27, January 2013. [2] Pritee Gupta, Vandana Malik, Mallika Gandhi, “Implementation of Multilevel Threshold Method for Digital Images Used In Medical Image Processing,” IJARCSSE, Volume 2, Issue 2, February 2012. [3] Ayelet Dominitz, Introduction to Medical Imaging [4] Jay Acharya, Sohil Gadhiya, Kapil Raviya, “segmentation techniques for image analysis: a review,” International Journal of Computer Science and Management Research Vol 2 Issue 1 January 2013. [5] Wankai Deng , Wei Xiao, He Deng, Jianguo Liu, “MRI Brain Tumor Segmentation With Region Growing Method Based On The Gradients And Variances Along And Inside Of The Boundary Curve,” International Conference on Biomedical Engineering and Informatics (BMEI 2010)(IEEE), 3rd 2010 [6] Anamika Ahirwar, “Study of Techniques used for Medical Image Segmentation and Computation of Statistical Test for Region Classification of Brain MRI,” I.J. Information Technology and Computer Science, Volume 5 April 2013. [7] Wahba Marian, “An Automated Modified Region Growing Technique for Prostate Segmentation in Trans- Rectal Ultrasound Images”, Master’s Thesis, Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Ontario, Canada, 2008. [8] Y. Zhang, H. Qu, Y. Wang, “Adaptive Image Segmentation Based on Fast Thresholding and Image Merging”, Artificial reality and Telexistence- Workshops, pp. 308-311, 1994. [9] Salem Saleh Al-amri, N.V. Kalyankar and Khamitkar S.D,” Image Segmentation by Using Threshold Techniques,” JOURNAL OF COMPUTING, VOLUME 2, ISSUE 5, MAY 2010, ISSN 2151-9617. [10]R. B. Dubey, M. Hanmandlu, S. K. Gupta and S. K. Gupta,” Region growing for MRI brain Tumor volume analysis,” Indian Journal of Science and Technology, Vol.2 No. 9, Sep 2009, ISSN: 0974- 6846. [11]mansur rozmin, prof. chhaya suratwala, prof. vandana shah,” implementation of hard c-means clustering algorithm for medical image segmentation,” journal of information, knowledge and research in electronics and communication engineering, volume – 02, issue – 02, nov 12 to oct 13, ISSN: 0975 – 6779 [12]Archana Lala, Jitendra Kumar Gupta , Mrinalini Shringirishi, “ implementation of k-means clustering and fuzzy c-means algorithm for brain Tumor segmentation,” International Journal of Computer Engineering & Science, Volume 3, Issue 1, pp. 27-33, Sept 2013. ISSN: 2231–6590. [13]Ms. Pritee Gupta, Ms Mrinalini Shringirishi ,Dr. Yashpal singh, “Implementation of Brain Tumor Segmentation in brain MR Images using K Means Clustering and Fuzzy C-Means Algorithm,” International Journal of Computers & Technology, Volume 5, No. 1, May -June, 2013, ISSN 2277-3061. [14]Mahesh Yambal, Hitesh Gupta, ” Image Segmentation using Fuzzy C Means Clustering: A survey”, International Journal of Advanced Research in Computer and Communication Engineering, Vol. 2, Issue 7, July 2013.