Morphological and texture based classification of dementia from mr images

Gaurav V. Bhalerao, Radek Hrabuska, Niranjana Sampathila

Research output: Contribution to journalArticle

Abstract

With degradation in quality of life, threat of brain disorders has become a serious concern from past few decades. Dementia is one such abnormality which includes a group of symptoms that deteriorate cognitive functions of the brain. The use of neuroimaging techniques has revealed the abnormal anatomy of Corpus callosum (CC) for diagnosing various brain disorders. This paper focuses on classification of magnetic resonance (MR) images of dementia using CC features. CC is segmented from each mid-sagittal brain MR image using K-means clustering algorithm and then used for feature extraction. Significant features between demented and normal groups are identified using statistical analysis. Depending upon the statistical significance, hybrid feature vectors are designed for male and female dataset. Support vector machine (SVM) and Back propagation neural network (BPNN) classifiers are trained and tested using the designed feature vectors. Considering the sexual dimorphism of CC structure, feature classification is performed separately for male and female data. This paper reports the highest classification accuracy of 97% for male data and 95% for female data.

Original languageEnglish
Pages (from-to)293-304
Number of pages12
JournalJournal of Medical Imaging and Health Informatics
Volume7
Issue number2
DOIs
Publication statusPublished - 01-04-2017

Fingerprint

Corpus Callosum
Dementia
Brain Diseases
Magnetic Resonance Spectroscopy
Brain
Neuroimaging
Sex Characteristics
Cognition
Cluster Analysis
Anatomy
Quality of Life

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

Bhalerao, Gaurav V. ; Hrabuska, Radek ; Sampathila, Niranjana. / Morphological and texture based classification of dementia from mr images. In: Journal of Medical Imaging and Health Informatics. 2017 ; Vol. 7, No. 2. pp. 293-304.
@article{043bd419d0e248e5bcf25da08831a602,
title = "Morphological and texture based classification of dementia from mr images",
abstract = "With degradation in quality of life, threat of brain disorders has become a serious concern from past few decades. Dementia is one such abnormality which includes a group of symptoms that deteriorate cognitive functions of the brain. The use of neuroimaging techniques has revealed the abnormal anatomy of Corpus callosum (CC) for diagnosing various brain disorders. This paper focuses on classification of magnetic resonance (MR) images of dementia using CC features. CC is segmented from each mid-sagittal brain MR image using K-means clustering algorithm and then used for feature extraction. Significant features between demented and normal groups are identified using statistical analysis. Depending upon the statistical significance, hybrid feature vectors are designed for male and female dataset. Support vector machine (SVM) and Back propagation neural network (BPNN) classifiers are trained and tested using the designed feature vectors. Considering the sexual dimorphism of CC structure, feature classification is performed separately for male and female data. This paper reports the highest classification accuracy of 97{\%} for male data and 95{\%} for female data.",
author = "Bhalerao, {Gaurav V.} and Radek Hrabuska and Niranjana Sampathila",
year = "2017",
month = "4",
day = "1",
doi = "10.1166/jmihi.2017.2058",
language = "English",
volume = "7",
pages = "293--304",
journal = "Journal of Medical Imaging and Health Informatics",
issn = "2156-7018",
publisher = "American Scientific Publishers",
number = "2",

}

Morphological and texture based classification of dementia from mr images. / Bhalerao, Gaurav V.; Hrabuska, Radek; Sampathila, Niranjana.

In: Journal of Medical Imaging and Health Informatics, Vol. 7, No. 2, 01.04.2017, p. 293-304.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Morphological and texture based classification of dementia from mr images

AU - Bhalerao, Gaurav V.

AU - Hrabuska, Radek

AU - Sampathila, Niranjana

PY - 2017/4/1

Y1 - 2017/4/1

N2 - With degradation in quality of life, threat of brain disorders has become a serious concern from past few decades. Dementia is one such abnormality which includes a group of symptoms that deteriorate cognitive functions of the brain. The use of neuroimaging techniques has revealed the abnormal anatomy of Corpus callosum (CC) for diagnosing various brain disorders. This paper focuses on classification of magnetic resonance (MR) images of dementia using CC features. CC is segmented from each mid-sagittal brain MR image using K-means clustering algorithm and then used for feature extraction. Significant features between demented and normal groups are identified using statistical analysis. Depending upon the statistical significance, hybrid feature vectors are designed for male and female dataset. Support vector machine (SVM) and Back propagation neural network (BPNN) classifiers are trained and tested using the designed feature vectors. Considering the sexual dimorphism of CC structure, feature classification is performed separately for male and female data. This paper reports the highest classification accuracy of 97% for male data and 95% for female data.

AB - With degradation in quality of life, threat of brain disorders has become a serious concern from past few decades. Dementia is one such abnormality which includes a group of symptoms that deteriorate cognitive functions of the brain. The use of neuroimaging techniques has revealed the abnormal anatomy of Corpus callosum (CC) for diagnosing various brain disorders. This paper focuses on classification of magnetic resonance (MR) images of dementia using CC features. CC is segmented from each mid-sagittal brain MR image using K-means clustering algorithm and then used for feature extraction. Significant features between demented and normal groups are identified using statistical analysis. Depending upon the statistical significance, hybrid feature vectors are designed for male and female dataset. Support vector machine (SVM) and Back propagation neural network (BPNN) classifiers are trained and tested using the designed feature vectors. Considering the sexual dimorphism of CC structure, feature classification is performed separately for male and female data. This paper reports the highest classification accuracy of 97% for male data and 95% for female data.

UR - http://www.scopus.com/inward/record.url?scp=85019711754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019711754&partnerID=8YFLogxK

U2 - 10.1166/jmihi.2017.2058

DO - 10.1166/jmihi.2017.2058

M3 - Article

VL - 7

SP - 293

EP - 304

JO - Journal of Medical Imaging and Health Informatics

JF - Journal of Medical Imaging and Health Informatics

SN - 2156-7018

IS - 2

ER -