Neurocognitive disorder detection based on feature vectors extracted from VBM analysis of structural MRI

Savio, Alexandre; García-Sebastián, Maite; Chyzyk, D.; Hernández, Carmen Añez; Graña, Manuel; Sistiaga, Andone; Munáin, Adolfo López de; Villanúa, Jorge

doi:10.1016/j.compbiomed.2011.05.010

Cited by 48 publications

(24 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They reported an ACC of 78% for MRI data and 92.4% by combining MRI data with the MMSE. Savio et al [9] studied the feature-extraction process with VBM analysis on 98% female subjects only and achieved the best results with 86% accuracy for the RBF-AB-SVM classifier. Khedher et al [30] reported an ACC of 88.49% by combining GM and WM modalities in MRI.…”

Section: Performance Comparison To Other Methodsmentioning

confidence: 98%

“…In several papers, SVM is used to correctly classify unseen patterns [9,[34][35][36]. During SVM training, SVM maximizes the distance from patterns to the class-separating hyper-plane.…”

Section: The Svmmentioning

confidence: 99%

“…Some of these studies are based on morphometric methods [7][8][9], region of interest (ROI)/volume of interest (VOI) [10][11][12], and gray matter voxels in the automatic segmentation of images [13].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Probability distribution function-based classification of structural MRI for the detection of Alzheimer’s disease

Beheshti

Demirel

2015

Computers in Biology and Medicine

View full text Add to dashboard Cite

Section: Performance Comparison To Other Methodsmentioning

confidence: 98%

“…In several papers, SVM is used to correctly classify unseen patterns [9,[34][35][36]. During SVM training, SVM maximizes the distance from patterns to the class-separating hyper-plane.…”

Section: The Svmmentioning

confidence: 99%

See 1 more Smart Citation

Probability distribution function-based classification of structural MRI for the detection of Alzheimer’s disease

Beheshti

Demirel

2015

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…It is stated in studies that unmodulated images give better accuracy for classification and that mesoscopic differences can be better distinguished than modulated images [11] [12]. However, some classification studies use modulated normalized images [13,25]. In this work, GM output of the VBM8 was set to be unmodulated normalized according to [12].…”

Section: Preprocessingmentioning

confidence: 99%

Creation of 3D Volume Loss Mask and Mean Performance Analysis on 3d MR Images

Özi̇ç

Ekmekçi

Özşen

2017

JBEMI

View full text Add to dashboard Cite

Examination of changes in the brain during disease progression using numerical methods is one of the current topics investigated by neuroscience. One of the numerical methods developed for locally or globally analyzing changes in the brain is voxel based morphometry. With voxel based morphometry, volume differences between the intragroup and intergroup Magnetic Resonance images can be examined. The general voxel based morphometry studies performed in the literature are only mapped. However, tissue analysis and artificial intelligence studies using voxel based morphometry are inadequate. In this study, voxel based morphometry was used to create a three dimensional volume loss mask for Alzheimer's disease to use tissue analysis and artificial intelligence in the future studies. Two different masks were created for according to the usage of family wise error. Volume loss regions are cut from normalized segmented and smoothed normalized segmented gray matter images with the generated masks. The average values of the voxel values in these regions are statistically compared for four different scenarios. As a result of the comparison, segmentation made with normalized segmented and family wise error values have been more meaningful results than the other three scenarios.

show abstract

“…The experimental work in this paper focus on the design of computer assisted diagnosis of Alzheimer's disease (AD) based on feature vectors extracted from the analysis of structural MRI (sMRI) data. More specifically, we improve over previous works applying classifiers to the features obtained by a feature extraction method based on voxel-based morphometry (VBM) [16,[22][23][24].…”

mentioning

confidence: 99%

A Two Stage Sequential Ensemble Applied to the Classification of Alzheimer’s Disease Based on MRI Features

Termenon

Graña

2011

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

We present a two stage sequential ensemble where data samples whose output from the first classifier fall in a low confidence output interval (LCOI) are processed by a second stage classifier. Training is composed of three processes: training the first classifier, determining the LCOI of the first classifier, and training the second classifier upon the data items whose output fall in the LCOI. The LCOI is determined varying a threshold on the false positive rate (FPR) and false negative rate (FNR) curves. We have tested the approach on a database of feature vectors for the classification of Alzheimer's disease (AD) and control subjects extracted from structural magnetic resonance imaging (sMRI) data. In this paper, we focus on the combinations obtained when the first classifier is a relevance vector machine (RVM). Obtained results improve over previous results for this database.

show abstract

Neurocognitive disorder detection based on feature vectors extracted from VBM analysis of structural MRI

Cited by 48 publications

References 43 publications

Probability distribution function-based classification of structural MRI for the detection of Alzheimer’s disease

Probability distribution function-based classification of structural MRI for the detection of Alzheimer’s disease

Creation of 3D Volume Loss Mask and Mean Performance Analysis on 3d MR Images

A Two Stage Sequential Ensemble Applied to the Classification of Alzheimer’s Disease Based on MRI Features

Contact Info

Product

Resources

About