In order to reduce the computational complexity and expedite the

University of Miami
Scholarly Repository
Open Access Dissertations Electronic Teses and Dissertations
2015-05-04
Automated Brain Lesion Detection and
Segmentation Using Magnetic Resonance Images
Nooshin Nabizadeh
University of Miami, nooshin.zade@gmail.com
Follow this and additional works at: htps://scholarlyrepository.miami.edu/oa_dissertations
Tis Open access is brought to you for free and open access by the Electronic Teses and Dissertations at Scholarly Repository. It has been accepted for
inclusion in Open Access Dissertations by an authorized administrator of Scholarly Repository. For more information, please contact
repository.library@miami.edu.
Recommended Citation
Nabizadeh, Nooshin, “Automated Brain Lesion Detection and Segmentation Using Magnetic Resonance Images” (2015). Open Access
Dissertations. 1409.
htps://scholarlyrepository.miami.edu/oa_dissertations/1409
UNIVERSITY OF MIAMI
AUTOMATED BRAIN LESION DETECTION AND SEGMENTATION USING
MAGNETIC RESONANCE IMAGES
By
Nooshin Nabizadeh
A DISSERTATION
Submitted to the Faculty
of the University of Miami
in partial fulfillment of the requirements for
the degree of Doctor of Philosophy
Coral Gables, Florida
May 2015
c 2015
Nooshin Nabizadeh
All Rights Reserved
UNIVERSITY OF MIAMI
A dissertation submitted in partial fulfillment of
the requirements for the degree of
Doctor of Philosophy
AUTOMATED BRAIN LESION DETECTION AND SEGMENTATION USING
MAGNETIC RESONANCE IMAGES
Nooshin Nabizadeh
Approved:
Miroslav Kubat, Ph.D.
Associate Professor of Electrical
and Computer Engineering
Kamal Premaratne, Ph.D.
Professor of Electrical and Computer
Engineering
Mei-Ling Shyu, Ph.D.
Professor and Associate Chair of
Electrical and Computer Engineering
Nigel John, Ph.D.
Lecturer of Electrical and
Computer Engineering
Pradip Pattany, Ph.D.
Research Associate Professor of
Radiology
M. Brian Blake, Ph.D.
Dean of the Graduate School
NABIZADEH, NOOSHIN (Ph.D., Electrical and Computer Engineering)

Automated Brain Lesion Detection and Segmentation	(May 2015)
Using Magnetic Resonance Images

Abstract of a dissertation at the University of Miami.
Dissertation supervised by Professor Miroslav Kubat.
No. of pages in text. (175)
Automated segmentation of brain lesions in magnetic resonance images (MRI)
is a difficult procedure due to the variability and complexity of the location, size,
shape, and texture of these lesions. In this study, four algorithms for brain lesion
detection and segmentation using MRI are proposed. In the first algorithm, an
automatic algorithm for brain stroke lesion detection and segmentation using singlespectral MRI is proposed, which is called histogram-based gravitational optimization
algorithm (HGOA). HGOA is a novel intensity-based segmentation technique that
applies enhanced gravitational optimization algorithm on histogram analysis results
to segment the brain lesion. The ischemic stroke lesions are segmented with 91:5%
accuracy and tumor lesions are segmented with 88% accuracy.
Since histogram analysis limits the extracted information to the number of pixels
in specific gray levels and does not include any region based information, the accuracy of a histogram-based method is limited. In the second algorithm, in order
to increase the accuracy of brain tumor segmentation, a texture-based automated
approach is presented. The experimental results on T1-weighted, T2-weighted, and
fluid-attenuated inversion recovery (FLAIR) images on both simulated and real brain
MRI data prove the efficacy of our technique in successfully segmentation of brain
tumor tissues with high accuracy (95:9 ± 0:4% for database of simulated MR images,
and 93:2 ± 0:3% for database of real MR images).
In order to reduce the computational complexity and expedite the segmentation
algorithm, and also to improve the system performance, some modifications are applied in the algorithm presented in previous algorithm. In the third algorithm, we
present a fully automatic tumor system which is combination of texture-based and
contour-based algorithms. Skippy greedy snake algorithm is capable of segmenting the
tumor area; however, the algorithm’s accuracy and performance depends significantly
on its initial points. Here, we modify the previous algorithm to automatically find
proper initial points which not only obviates the requirement of manual interference,
but also increase the accuracy and speed of optimization convergence. Comparing
with previous method, this method achieves higher accuracy in tumor segmentation
(96:8 ± 0:3% for database of simulated MR images, and 93:8 ± 0:1% for database of
real MR images) and lower computational complexity.
The intensity similarities between brain lesions and some normal tissues result in
confusion within segmentation algorithms, specially in the database of real MR images. In order to improve the system performance for this database, a multi-spectral
approach based on feature-level fusion is presented in forth algorithm. Even though
using multi-spectral MRI has several drawbacks and limitations, since it makes use of
complementary information, it increases the accuracy of the system. Here, a featurelevel fusion technique based on canonical correlation analysis (CCA) is proposed. It is
worth mentioning that for the first time CCA is applied for combining MRI sequences
in order to segment tumors. Even though data fusion increases computational comv
plexity of the segmentation algorithm, it results in a higher accuracy (95:8±0:2% for
database of real MR images).
vi
Dedicated to Francis,
Peanut, Badoum and April
iii
Acknowledgements
I would like to thank my advisor Dr. Miroslav Kubat and my co-advisor Dr. Nigel
John who supported me in the past few years through the research and completion of
my degree. I believe their personality and technical capability was an indispensable
factor for me to finish this endeavor.
Nooshin Nabizadeh
University of Miami
May 2015
iv
Table of Contents
LIST OF FIGURES x
LIST OF TABLES xviii
1 INTRODUCTION 1
2 MAGNETIC RESONANCE IMAGING 11
2.1 Gradient Echo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.2 Spin Echo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3 Inversion Recovery . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.4 Fluid Attenuated Inversion Recovery . . . . . . . . . . . . . . . . . . 14
2.5 T1-Weighted . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.6 T2-Weighted . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.7 Proton Density . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3 RELATED WORK 17
v
4 STROKE LESION DETECTION USING HISTOGRAM-BASED
GRAVITATIONAL OPTIMIZATION ALGORITHM 28
4.1 System Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.2 Histogram-Based Gravitational Optimization Algorithm . . . . . . . . 32
4.2.1 Histogram-based Brain Segmentation Algorithm . . . . . . . . 34
4.2.2 N-Dimensional Gravitational Optimization Algorithm . . . . . 40
4.2.3 Convergence of N-Dimensional Gravitational Optimization Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
4.3 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
4.3.1 Database and Image Acquisition . . . . . . . . . . . . . . . . . 44
4.3.2 Pre-processing . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
4.3.3 Brain MRI Segmentation . . . . . . . . . . . . . . . . . . . . . 46
4.3.4 Stroke Lesion Detection . . . . . . . . . . . . . . . . . . . . . 47
4.3.5 Stroke Lesion Segmentation . . . . . . . . . . . . . . . . . . . 48
4.3.6 Decreasing False Positives . . . . . . . . . . . . . . . . . . . . 49
4.3.7 Tumor Lesion Detection and Segmentation . . . . . . . . . . . 51
4.4 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64
5 TUMOR LESION DETECTION AND SEGMENTATION USING
TEXTURE-BASED STATISTICAL CHARACTERIZATION 67
5.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 67
5.2 Texture-Based Feature Extraction Methods . . . . . . . . . . . . . . . 70
vi
5.2.1 First-Order Statistical Features .

The post In order to reduce the computational complexity and expedite the appeared first on My Assignment Tutor.

• • Assignment status: Resolved by our Writing Team
  • Source@PrimeWritersBay.com

GET THIS PAPER COMPLETED FOR YOU FROM THE WRITING EXPERTS  CLICK HERE TO ORDER 100% ORIGINAL PAPERS AT PrimeWritersBay.com

• • • • NO PLAGIARISM