Automated categorization of multi-class brain abnormalities using decomposition techniques with MRI images

A comparative study

Anjan Gudigar, U. Raghavendra, Edward J. Ciaccio, N. Arunkumar, Enas Abdulhay, U. Rajendra Acharya

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Medical imaging and analysis are useful to visualize anatomic structure. However, analysis of the pathologic substrate is difficult and inefficient when using simple imaging tools. The manual detection and classification of brain abnormality is particularly tedious. Moreover, the currently used methodology suffers from interobserver variability during image interpretation. Magnetic resonance imaging (MRI) is an efficient imaging technique for revealing complex anatomical architecture, and it is highly efficacious for precise brain imaging. Herein, we describe a novel computer aided diagnosis method for automated processing of brain MRI images. The performances of two decomposition techniques, namely, bidimensional empirical mode decomposition and variational mode decomposition (VMD), are compared. Thereafter, bispectral feature extraction and supervised neighborhood projection embedding are implemented to represent each feature in a new subspace, for the automated classification of various categories of disease. A support vector machine classifier is used to train and test the performance accuracy. The level of classification accuracy of 90.68%, 99.43% sensitivity and 87.95% specificity is obtained using the VMD technique. Hence, the developed system can be used as an adjunct tool by radiologists to confirm their screening.

Original languageEnglish
Article number8649639
Pages (from-to)28498-28509
Number of pages12
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 01-01-2019

Fingerprint

Magnetic resonance imaging
Brain
Decomposition
Imaging techniques
Computer aided diagnosis
Medical imaging
Support vector machines
Feature extraction
Screening
Classifiers
Substrates
Processing

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Gudigar, Anjan ; Raghavendra, U. ; Ciaccio, Edward J. ; Arunkumar, N. ; Abdulhay, Enas ; Acharya, U. Rajendra. / Automated categorization of multi-class brain abnormalities using decomposition techniques with MRI images : A comparative study. In: IEEE Access. 2019 ; Vol. 7. pp. 28498-28509.
@article{eaf8ae1cb2d342d5861195356b71b4ba,
title = "Automated categorization of multi-class brain abnormalities using decomposition techniques with MRI images: A comparative study",
abstract = "Medical imaging and analysis are useful to visualize anatomic structure. However, analysis of the pathologic substrate is difficult and inefficient when using simple imaging tools. The manual detection and classification of brain abnormality is particularly tedious. Moreover, the currently used methodology suffers from interobserver variability during image interpretation. Magnetic resonance imaging (MRI) is an efficient imaging technique for revealing complex anatomical architecture, and it is highly efficacious for precise brain imaging. Herein, we describe a novel computer aided diagnosis method for automated processing of brain MRI images. The performances of two decomposition techniques, namely, bidimensional empirical mode decomposition and variational mode decomposition (VMD), are compared. Thereafter, bispectral feature extraction and supervised neighborhood projection embedding are implemented to represent each feature in a new subspace, for the automated classification of various categories of disease. A support vector machine classifier is used to train and test the performance accuracy. The level of classification accuracy of 90.68{\%}, 99.43{\%} sensitivity and 87.95{\%} specificity is obtained using the VMD technique. Hence, the developed system can be used as an adjunct tool by radiologists to confirm their screening.",
author = "Anjan Gudigar and U. Raghavendra and Ciaccio, {Edward J.} and N. Arunkumar and Enas Abdulhay and Acharya, {U. Rajendra}",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2901055",
language = "English",
volume = "7",
pages = "28498--28509",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Automated categorization of multi-class brain abnormalities using decomposition techniques with MRI images : A comparative study. / Gudigar, Anjan; Raghavendra, U.; Ciaccio, Edward J.; Arunkumar, N.; Abdulhay, Enas; Acharya, U. Rajendra.

In: IEEE Access, Vol. 7, 8649639, 01.01.2019, p. 28498-28509.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated categorization of multi-class brain abnormalities using decomposition techniques with MRI images

T2 - A comparative study

AU - Gudigar, Anjan

AU - Raghavendra, U.

AU - Ciaccio, Edward J.

AU - Arunkumar, N.

AU - Abdulhay, Enas

AU - Acharya, U. Rajendra

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Medical imaging and analysis are useful to visualize anatomic structure. However, analysis of the pathologic substrate is difficult and inefficient when using simple imaging tools. The manual detection and classification of brain abnormality is particularly tedious. Moreover, the currently used methodology suffers from interobserver variability during image interpretation. Magnetic resonance imaging (MRI) is an efficient imaging technique for revealing complex anatomical architecture, and it is highly efficacious for precise brain imaging. Herein, we describe a novel computer aided diagnosis method for automated processing of brain MRI images. The performances of two decomposition techniques, namely, bidimensional empirical mode decomposition and variational mode decomposition (VMD), are compared. Thereafter, bispectral feature extraction and supervised neighborhood projection embedding are implemented to represent each feature in a new subspace, for the automated classification of various categories of disease. A support vector machine classifier is used to train and test the performance accuracy. The level of classification accuracy of 90.68%, 99.43% sensitivity and 87.95% specificity is obtained using the VMD technique. Hence, the developed system can be used as an adjunct tool by radiologists to confirm their screening.

AB - Medical imaging and analysis are useful to visualize anatomic structure. However, analysis of the pathologic substrate is difficult and inefficient when using simple imaging tools. The manual detection and classification of brain abnormality is particularly tedious. Moreover, the currently used methodology suffers from interobserver variability during image interpretation. Magnetic resonance imaging (MRI) is an efficient imaging technique for revealing complex anatomical architecture, and it is highly efficacious for precise brain imaging. Herein, we describe a novel computer aided diagnosis method for automated processing of brain MRI images. The performances of two decomposition techniques, namely, bidimensional empirical mode decomposition and variational mode decomposition (VMD), are compared. Thereafter, bispectral feature extraction and supervised neighborhood projection embedding are implemented to represent each feature in a new subspace, for the automated classification of various categories of disease. A support vector machine classifier is used to train and test the performance accuracy. The level of classification accuracy of 90.68%, 99.43% sensitivity and 87.95% specificity is obtained using the VMD technique. Hence, the developed system can be used as an adjunct tool by radiologists to confirm their screening.

UR - http://www.scopus.com/inward/record.url?scp=85063282339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063282339&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2901055

DO - 10.1109/ACCESS.2019.2901055

M3 - Article

VL - 7

SP - 28498

EP - 28509

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8649639

ER -