Brain tumors detection and segmentation in MR images: Gabor wavelet vs. statistical features

Nooshin Nabizadeh, Miroslav Kubat

Research output: Contribution to journalArticle

78 Citations (Scopus)

Abstract

Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure owing to the variability and complexity of the location, size, shape, and texture of these lesions. Because of intensity similarities between brain lesions and normal tissues, some approaches make use of multi-spectral anatomical MRI scans. However, the time and cost restrictions for collecting multi-spectral MRI scans and some other difficulties necessitate developing an approach that can detect tumor tissues using a single-spectral anatomical MRI images. In this paper, we present a fully automatic system, which is able to detect slices that include tumor and, to delineate the tumor area. The experimental results on single contrast mechanism demonstrate the efficacy of our proposed technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity. Moreover, we include a study evaluating the efficacy of statistical features over Gabor wavelet features using several classifiers. This contribution fills the gap in the literature, as is the first to compare these sets of features for tumor segmentation applications.

Original languageEnglish (US)
Pages (from-to)286-301
Number of pages16
JournalComputers and Electrical Engineering
Volume45
DOIs
StatePublished - Jul 1 2015

Fingerprint

Tumors
Brain
Magnetic resonance
Tissue
Computational complexity
Classifiers
Textures
Costs

Keywords

  • Fluid-attenuated inversion recovery
  • Gabor wavelet features
  • Lesion detection/segmentation
  • MR imaging
  • Statistical features
  • T1-weighted

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

Brain tumors detection and segmentation in MR images : Gabor wavelet vs. statistical features. / Nabizadeh, Nooshin; Kubat, Miroslav.

In: Computers and Electrical Engineering, Vol. 45, 01.07.2015, p. 286-301.

Research output: Contribution to journalArticle

@article{22f73619aa8d4ecf9b5b537fbf577cde,
title = "Brain tumors detection and segmentation in MR images: Gabor wavelet vs. statistical features",
abstract = "Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure owing to the variability and complexity of the location, size, shape, and texture of these lesions. Because of intensity similarities between brain lesions and normal tissues, some approaches make use of multi-spectral anatomical MRI scans. However, the time and cost restrictions for collecting multi-spectral MRI scans and some other difficulties necessitate developing an approach that can detect tumor tissues using a single-spectral anatomical MRI images. In this paper, we present a fully automatic system, which is able to detect slices that include tumor and, to delineate the tumor area. The experimental results on single contrast mechanism demonstrate the efficacy of our proposed technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity. Moreover, we include a study evaluating the efficacy of statistical features over Gabor wavelet features using several classifiers. This contribution fills the gap in the literature, as is the first to compare these sets of features for tumor segmentation applications.",
keywords = "Fluid-attenuated inversion recovery, Gabor wavelet features, Lesion detection/segmentation, MR imaging, Statistical features, T1-weighted",
author = "Nooshin Nabizadeh and Miroslav Kubat",
year = "2015",
month = "7",
day = "1",
doi = "10.1016/j.compeleceng.2015.02.007",
language = "English (US)",
volume = "45",
pages = "286--301",
journal = "Computers and Electrical Engineering",
issn = "0045-7906",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Brain tumors detection and segmentation in MR images

T2 - Gabor wavelet vs. statistical features

AU - Nabizadeh, Nooshin

AU - Kubat, Miroslav

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure owing to the variability and complexity of the location, size, shape, and texture of these lesions. Because of intensity similarities between brain lesions and normal tissues, some approaches make use of multi-spectral anatomical MRI scans. However, the time and cost restrictions for collecting multi-spectral MRI scans and some other difficulties necessitate developing an approach that can detect tumor tissues using a single-spectral anatomical MRI images. In this paper, we present a fully automatic system, which is able to detect slices that include tumor and, to delineate the tumor area. The experimental results on single contrast mechanism demonstrate the efficacy of our proposed technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity. Moreover, we include a study evaluating the efficacy of statistical features over Gabor wavelet features using several classifiers. This contribution fills the gap in the literature, as is the first to compare these sets of features for tumor segmentation applications.

AB - Automated recognition of brain tumors in magnetic resonance images (MRI) is a difficult procedure owing to the variability and complexity of the location, size, shape, and texture of these lesions. Because of intensity similarities between brain lesions and normal tissues, some approaches make use of multi-spectral anatomical MRI scans. However, the time and cost restrictions for collecting multi-spectral MRI scans and some other difficulties necessitate developing an approach that can detect tumor tissues using a single-spectral anatomical MRI images. In this paper, we present a fully automatic system, which is able to detect slices that include tumor and, to delineate the tumor area. The experimental results on single contrast mechanism demonstrate the efficacy of our proposed technique in successfully segmenting brain tumor tissues with high accuracy and low computational complexity. Moreover, we include a study evaluating the efficacy of statistical features over Gabor wavelet features using several classifiers. This contribution fills the gap in the literature, as is the first to compare these sets of features for tumor segmentation applications.

KW - Fluid-attenuated inversion recovery

KW - Gabor wavelet features

KW - Lesion detection/segmentation

KW - MR imaging

KW - Statistical features

KW - T1-weighted

UR - http://www.scopus.com/inward/record.url?scp=84942368836&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942368836&partnerID=8YFLogxK

U2 - 10.1016/j.compeleceng.2015.02.007

DO - 10.1016/j.compeleceng.2015.02.007

M3 - Article

AN - SCOPUS:84942368836

VL - 45

SP - 286

EP - 301

JO - Computers and Electrical Engineering

JF - Computers and Electrical Engineering

SN - 0045-7906

ER -