Brain tumour segmentation based on local independent projection based classification

IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308
_______________________________________________________________________________________
Volume: 04 Issue: 07 | July-2015, Available @ http://www.ijret.org 9
BRAIN TUMOUR SEGMENTATION BASED ON LOCAL
INDEPENDENT PROJECTION BASED CLASSIFICATION
Priyanka S. Jadhav1
, Meeta Bakuli2
1
Student, E&TC Department, G.H.Raisoni COE & Management,Wagholi,Pune, Maharashtra, India
2
Professor, E&TC Department, G.H.Raisoni COE & Management,Wagholi,Pune, Maharashtra, India
Abstract
Brain tumour detection and segmentation is most important and challenging task in early tumour diagnosis. There are various
segmentation methods available but they are still challenging methods because of its complex characteristics such as ambiguous
boundaries and high diversity. To overcome this problem we are going to implement automatic brain tumour detection and
segmentation method by using local independent projection based classification. In this method we are going to consider tumour
segmentation as a classification problem. In this paper locality is important in calculations of projections. Also local anchor
embedding is used to solve linear projection weights. The softmax regression model is used to improve classification performance.
In this study we used MRI images as training and testing data. Finally the brain tumour is classified into tumour and edema
region. The area of tumour region is calculated in pixels.
Key Words: Brain tumour detection & segmentation, local independent projection based classification, local anchor
embedding and softmax regression.
--------------------------------------------------------------------***----------------------------------------------------------------------
1. INTRODUCTION
Brain tumor detection and segmentation is most challenging
task in early tumor diagnosis. Now days, brain tumor
detection and segmentation are done manually in clinic but
this is time consuming process also difficult and depends on
operator. Recently most people prefer MRI images for brain
tumor detection and segmentation because it gives more
information on tumor. The tumor area is divided into edema;
contrast enhancing, non-enhancing and necrosis. In different
MRI images these areas are different in size and shape. Fig
1 shows different areas in MRI image. The MRI images
provide large data about tumor but still it is challenging
because of different shapes and sizes of tumors. Brain
tumor in different MRI image located at different locations
so segmentation task becomes difficult. The noise present in
MRI makes segmentation process difficult. Therefore
semiautomatic or automatic method is needed for
segmentation of brain tumor. There are various methods
available for segmentation and detection of tumor but out of
which we choose supervised and unsupervised learning
method.
Fig -1: Different parts in the tumor area. (a) T1C-weighted
brain tumor MRI image. (b) T2-weighted brain tumor MRI
image. (c) Contour of the actual brain tumor “t” represents
the combination of contrast-enhancing and necrotic parts,
and “e” represents the edema part.
2. LITERATURE SURVEY
1. Meiyan Huang et.al discuss about problem of
segmentation of brain tumors. For solving this several
methods are available. In this Paper the aim of author is
to solve the segmentation problem by using LIPC based
method. Compared with other coding LAE method is
more suitable in solving linear reconstruction weights
under the locality constraint.
2. Dongjin Kwon et.al discusses about new method for
deformable registration of post-operative and pre-
operative brain MR scans of glioma patients. It matches
intensities of healthy tissue as well as glioma to
resection cavity. This method extracted pathological
information on both scans using scan specific
approaches and then registers scans by combining
image based matching with pathological information.
3. Andac Hamamci et.al discuss about fast tool for
segmentation of solid tumors with minimal user
interaction. Segmentation algorithm for problem of
tumor depiction which display varying tissue
characteristics. The author discusses a tumor cut
segmentation to divide the tumor tissue into its necrotic
tumor and enhancing parts.
4. Stefan Bauer et.al discuss about a new method which
makes use of sophisticated models of bio-
physiomechnical tumor growth to adapt a general brain
atlas to an individual tumor patient image. It can be
applied for solid tumors and gliomas with distinct
boundaries to capture important mass effect, while the
less pronounced infiltration effect is not considered in
this case.

_______________________________________________________________________________________
3. OVERVIEW OF THE PROPOSED METHOD
The proposed method consists of four major steps, first step
is preprocessing, second is feature extraction, third is tumor
segmentation using the LIPC method, and last step is post
processing. The multi-resolution framework is used to
reduce computational costs in this proposed method. The
block diagram and flowchart of the proposed method is
illustrated in Fig. 2 and 3.
Fig -2: Block Diagram of the proposed method
Algorithm:
1. Create training dictionary.
2. Apply Local anchor embedding and save features.
3. Apply Local independent projection based classification
and calculate reconstruction error (E).
4. Select testing sample and apply median filtering. Repeat
step 2 and 3.
5. Detect patch whose intensity is greater than threshold
value.
6. Divide patch into edema and tumour part.
7. Analyze tumour part.
Fig -3: Algorithm of the proposed method
3.1 Preprocessing: Image Filtering by using Median
Filter
Median filtering and averaging filter are similar, In
averaging filter each output pixel value is set to an average
of the pixel values in the neighborhood of the corresponding
input pixel and In median filtering, the value of an output
pixel is determined by the median of the neighborhood
pixels, rather than the mean. The major difference in
between median and mean is median is less sensitive than
the mean to extreme values. Therefore Median filtering is
better to remove these outliers without reducing the
sharpness of the image. The medfilt2 function is used to
implement median filtering. Also PSNR, MSE, contrast and
correlation values are calculated.
Fig -4: Filtered Image
Fig -5: Results after median filtering
3.2 Feature Extraction
Image intensities in MRI images do not have a fixed
meaning and widely vary within or between subjects so
before extracting image features, intensity normalization and
image inhomogeneity correction should be performed. In
this project, we are using a patch-based technique for
extracting the image feature. The intensity values in a patch
around a voxel v were obtained and rearranged as a feature
vector. The intensity values in patch are greater than
threshold value. All intensity values in patch are plotted on
graph.

_______________________________________________________________________________________
Fig -6: Patch Detection
Fig -7: Histogram of patch
4. LOCAL INDEPENDENT PROJECTION
BASED CLASSIFICATION
4.1 The basic principle of LIPC
The segmentation of brain tumor can be considered as a
multiclass classification problem. To solve this problem, a
one-versus-all (OvA) strategy can be used. In the One
versus all strategy, a classifier is trained per class to
distinguish a class from all other classes.
Therefore, N classifiers
N real classification scores are computed using
learned classifiers
For this proposed method, the following assumption was
considered as the base for LIPC:
Assumption I: Each Sample is located on different non-
linear sub manifolds according to their classes, and a sample
can be approximately represented as a linear combination of
several nearest neighbors from its corresponding sub
manifold.
4.2 LIPC Implementation
4.2.1 Dictionary Construction
Dictionary is constructed by using manually labeled original
samples in a training set. However, number of original
training samples produces large D, which increases
computational costs and memory. In the present study, more
samples for each class are available for training but when
we are going to implement this that time this process
becomes impractical. For learning a compact representation
of the original training samples, it is necessary to apply a
dictionary learning method. The k-means method is used in
this proposed method.
4.2.2 Locally Linear Representation
There are several methods are available for representation of
sample which is linearly based on training sample. These
methods are sparse coding, locally constrained linear coding
and local anchor embedding. Sparse coding attempts to use
the smallest number of training samples in
reconstruction.LLC and LAE approaches focus on locality.
To obtain solution for LAE, firstly select K nearest
neighbors from dictionary. Here we can vary value of K
from 5 to 100 and observe effect of this on reconstruction
error.
Considering the concrete task in this paper, we formally re-
formulize the cost function of LAE as
s.t.
Three steps were performed to obtain the solution of LAE.
1. Select k nearest neighbors of x from D and construct
2. For the samples that do not belong to ,associated
ajs were set to0
3. For samples that belong to ,calculate
4.2.3 Classification Score Computation
Softmax regression model is used for computation. Softmax
regression model uses Relation between Data distribution
and reconstruction error. If distribution is uniform and noise
is low then classification may be performed well. This
model generalizes logistic regression to classification
problems where the class label y can take on more than two
possible values. Recall that in logistic regression, we had a
training set of m labeled examples. With logistic regression,
we were in the binary classification setting, so the labels
were
In the softmax regression setting, we are interested in multi-
class classification (as opposed to only binary
classification), and so the label y can take on k different
values, rather than only two. Thus, in our training set
; we now have that
Classification score

_______________________________________________________________________________________
Fig -8: Results after LIPC
Fig -9: Classification into tumor and edema parts
5. POSTPROCESSING
In LIPC step we separated tumor and edema part. In post
processing we analyze tumor part. Here we calculated area
and perimeter of tumor in pixels. Also we can find in which
lobe tumor is present and its stage.
Fig -10: Tumor Analysis
6. CONCLUSIONS
This method is proposed to solve segmentation problem of
brain tumor. Here we apply local independent projection
based classification. Finally features are extracted by using
threshold value and patch is detected which contain tumor
and edema part. After analyzing tumor part we get area and
perimeter of tumor region as well as we detected exactly in
which lobe tumor is present and its stage.
REFERENCES
[1] Meiyan Huang, Wei Yang, Yao Wu, Jun Jiang, Wufan
Chen, Senior Member, IEEE, and Qianjin Feng*, Member,"
Brain Tumor Segmentation Based on Local Independent
Projection-based Classification” IEEE Transactions on
Biomedical Engineering DOI 10.1109/TBME.2014.2325410
, 2014.
[2] Dongjin Kwon*, Member, IEEE, Marc Niethammer,
Member, IEEE, Hamed Akbari, Michel Bilello,Christos
Davatzikos, Fellow, IEEE, and Kilian M. Pohl, Member,
“PORTR: Pre-Operative and Post-Recurrence Brain Tumor
Registration", IEEE Transactions on Medical Imaging, Vol.
33, No.3, March 2014
[3] Hamamci, N. Kucuk, K. Karaman, K. Engin, and G.
Unal, "Tumor-Cut: segmentation of brain tumors on contrast
enhanced MR images for radio- surgery applications", IEEE
Transactions on Medical Imaging, vol. 31, no. 3, pp. 790-
804, Mar 2012.
[4] Stefan Bauer*, Student Member, IEEE, Christian May,
Dimitra Dionysiou, Georgios Stamatakos, Member, IEEE,
Philippe, and Mauricio Reyes, Member, IEEE," Multiscale
Modeling for Image Analysis of Brain Tumor Studies",
IEEE Transactions on Biomedical Engineering, vol. 59, no.
1, january 2012
[5] T. Wang, I. Cheng, and A. Basu, "Fluid vector ow and
applications in brain tumor segmentation," IEEE
Transactions on Bio-medical Engineering, vol. 56, no. 3, pp.
781-9, Mar 2009.
[6] J. J. Corso, E. Sharon, S. Dube, S. El-Saden, U. Sinha,
and A. Yuille, "Efficient multilevel brain tumor
segmentation with integrated bayesian model classification,"
IEEE Transactions on Medical Imaging, vol. 27, no. 5, pp.
629-40, May 2008.
[7] M. B. Cuadra, C. Pollo, A. Bardera, O. Cuisenaire, J. G.
Villemure, and J. P. Thiran, "Atlas-based segmentation of
pathological MR brain images using a model of lesion
growth," IEEE Transactions on Medical Imaging, vol. 23,
no. 10, pp. 1301-1314, 2004.
BIOGRAPHIES
Priyanka S. Jadhav Student,
E&TC department,
G.H.Raisoni COE & Management,
Wagholi, Pune.

Brain tumour segmentation based on local independent projection based classification

Recommended

More Related Content

What's hot (20)

Similar to Brain tumour segmentation based on local independent projection based classification (20)

More from eSAT Journals (20)

Recently uploaded (20)

Brain tumour segmentation based on local independent projection based classification