Classification of Alzheimer and MCI phenotypes on MRI data using SVM
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Classification of Alzheimer and MCI phenotypes on MRI data using SVM. / Alzheimer’s Disease Neuroimaging Initiative.
Advances in Signal Processing and Intelligent Recognition Systems: Proceedings of 3rd International Symposium on Signal Processing and Intelligent Recognition Systems, SIRS-2017. Springer, 2018. p. 263-275 (Advances in Intelligent Systems and Computing, Vol. 678).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Classification of Alzheimer and MCI phenotypes on MRI data using SVM
AU - Kruthika, K. R.
AU - Rajeswari, null
AU - Pai, Akshay
AU - Maheshappa, H. D.
AU - Alzheimer’s Disease Neuroimaging Initiative
PY - 2018
Y1 - 2018
N2 - Alzheimer disease (AD) is a common form of dementia affecting people older than the age of 65. Moreover, AD is commonly diagnosed by behavioural paradormants, cognitive tests, and is followed by brain scans. Computer Aided Diagnosis (CAD), applies medical imaging and machine learning algorithms, to aid in the early diagnosis of Alzheimer’s severity and advancement from prodromal stages i.e. Mild Cognitive Impairment (MCI) to diagnosed Alzheimer’s disease. In this work, SVM (support vector machine) is used for dementia stage classification. Anatomical structures of the brain were obtained from FreeSurfer’s processing of structural Magnetic Resonance Imaging (MRI) data and is utilized for as features for SVM. To be more precise, the system is processed using T1-weighted brain MRI datasets consisting of: 150 mild cognitive impairment (MCI) patients, 80 AD patients and 130 normal controls (NC) obtained from Alzheimer Disease Neuroimaging Initiative (ADNI) database. The volumes of brain structures (hippocampus, medial temporal lobe, whole brain, ventricular, cortical grey matter, entorhinal cortex and fusiform) are employed as biomarkers for multi-class classification of AD, MCI, and NC.
AB - Alzheimer disease (AD) is a common form of dementia affecting people older than the age of 65. Moreover, AD is commonly diagnosed by behavioural paradormants, cognitive tests, and is followed by brain scans. Computer Aided Diagnosis (CAD), applies medical imaging and machine learning algorithms, to aid in the early diagnosis of Alzheimer’s severity and advancement from prodromal stages i.e. Mild Cognitive Impairment (MCI) to diagnosed Alzheimer’s disease. In this work, SVM (support vector machine) is used for dementia stage classification. Anatomical structures of the brain were obtained from FreeSurfer’s processing of structural Magnetic Resonance Imaging (MRI) data and is utilized for as features for SVM. To be more precise, the system is processed using T1-weighted brain MRI datasets consisting of: 150 mild cognitive impairment (MCI) patients, 80 AD patients and 130 normal controls (NC) obtained from Alzheimer Disease Neuroimaging Initiative (ADNI) database. The volumes of brain structures (hippocampus, medial temporal lobe, whole brain, ventricular, cortical grey matter, entorhinal cortex and fusiform) are employed as biomarkers for multi-class classification of AD, MCI, and NC.
KW - Alzheimer disease
KW - FreeSurfer
KW - Machine learning
KW - Mild cognitive impairment
KW - Normal control
KW - Structural magnetic resonance imaging
KW - SVM
UR - http://www.scopus.com/inward/record.url?scp=85030162236&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-67934-1_23
DO - 10.1007/978-3-319-67934-1_23
M3 - Article in proceedings
AN - SCOPUS:85030162236
SN - 9783319679334
T3 - Advances in Intelligent Systems and Computing
SP - 263
EP - 275
BT - Advances in Signal Processing and Intelligent Recognition Systems
PB - Springer
T2 - 3rd International Symposium on Signal Processing and Intelligent Recognition Systems, SIRS 2017
Y2 - 13 September 2017 through 16 September 2017
ER -
ID: 203940895