Morphological classification of brains via high-dimensional shape transformations and machine learning methods

Lao, Zhiqiang; Shen, Dinggang; Xue, Zhong; Karaçali, B.; Resnick, Susan M.; Davatzikos, Christos

doi:10.1016/j.neuroimage.2003.09.027

Cited by 314 publications

(240 citation statements)

References 44 publications

Supporting

Mentioning

225

Contrasting

Unclassified

Order By: Relevance

“…Euclidean wavelet approaches have been used to classify structural brain data (Canales-Rodriguez et al, 2013;Lao et al, 2004) as a means to assess structural morphometric differences between different populations of subjects. They have also been used to discriminate between healthy and pathological tissue by characterizing subtle changes in brain structure in a variety of diseases such as Alzheimer's disease, mild cognitive impairment and multiple sclerosis (Hackmack et al, 2012;Harrison et al, 2010).…”

Section: Extension To Structural Studiesmentioning

confidence: 99%

Anatomically-adapted graph wavelets for improved group-level fMRI activation mapping

et al. 2015

View full text Add to dashboard Cite

A graph based framework for fMRI brain activation mapping is presented. The approach exploits the spectral graph wavelet transform (SGWT) for the purpose of defining an advanced multi-resolutional spatial transformation for fMRI data. The framework extends wavelet based SPM (WSPM), which is an alternative to the conventional approach of statistical parametric mapping (SPM), and is developed specifically for group-level analysis. We present a novel procedure for constructing brain graphs, with subgraphs that separately encode the structural connectivity of the cerebral and cerebellar gray matter (GM), and address the inter-subject GM variability by the use of template GM representations. Graph wavelets tailored to the convoluted boundaries of GM are then constructed as a means to implement a GM-based spatial transformation on fMRI data. The proposed approach is evaluated using real as well as semi-synthetic multi-subject data. Compared to SPM and WSPM using classical wavelets, the proposed approach shows superior type-I error control. The results on real data suggest a higher detection sensitivity as well as the capability to capture subtle, connected patterns of brain activity.

show abstract

Section: Extension To Structural Studiesmentioning

confidence: 99%

Anatomically-adapted graph wavelets for improved group-level fMRI activation mapping

et al. 2015

View full text Add to dashboard Cite

show abstract

“…For participants who developed dementia over the course of the study, the most recent MRI prior to the diagnosis was used, with a mean (SD) interval of 1.9 (1.9) years between most recent scan and diagnosis. Volumetric measurements from these brain regions were then used to build a classifier [35,47], which produced an abnormality score: positive values indicate a structural pattern resembling MCI, whereas negative values indicate brain structure in unimpaired individuals. A value of 0 would indicate a structural profile that is in-between normal and abnormal.…”

Section: Pattern Analysis and Classificationmentioning

confidence: 99%

Detection of prodromal Alzheimer's disease via pattern classification of magnetic resonance imaging

Davatzikos

Fan

et al. 2008

Neurobiology of Aging

Self Cite

351

237

View full text Add to dashboard Cite

We report evidence that computer-based high-dimensional pattern classification of MRI detects patterns of brain structure characterizing mild cognitive impairment (MCI), often a prodromal phase of Alzheimer's Disease (AD). 90% diagnostic accuracy was achieved, using cross-validation, for 30 participants in the Baltimore Longitudinal Study of Aging. Retrospective evaluation of serial scans obtained during prior years revealed gradual increases in structural abnormality for the MCI group, often before clinical symptoms, but slower increase for individuals remaining cognitively normal. Detecting complex patterns of brain abnormality in very early stages of cognitive impairment has pivotal importance for the detection and management of AD.

show abstract

“…However differential diagnosis between FTD and AD based on structural, rather than functional, scans is a greater challenge. The development of sophisticated high-dimensional image analysis and classification methods in the field of computational neuroanatomy during the past decade can potentially help overcome this challenge (Golland 2002;Lao, Shen et al 2004;Csernansky, Wang et al 2005;Davatzikos, Ruparel et al 2005;Davatzikos, Fan et al 2006, epub;Fan, Batmanghelich et al 2008;Lerch, Pruessner et al 2008;Vemuri, Gunter et al 2008). …”

Section: Introductionmentioning

confidence: 99%

Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI

Davatzikos¹,

Resnick²,

Wu³

et al. 2008

NeuroImage

221

177

View full text Add to dashboard Cite

The purpose of this study is to determine the diagnostic accuracy of MRI-based high-dimensional pattern classification in differentiating between patients with Alzheimer's Disease (AD), Frontotemporal Dementia (FTD), and healthy controls, on an individual patient basis. MRI scans of 37 patients with AD and 37 age-matched cognitively normal elderly individuals, as well as 12 patients with FTD and 12 age-matched cognitively normal elderly individuals, were analyzed using voxelbased analysis and high-dimensional pattern classification. Diagnostic sensitivity and specificity of spatial patterns of regional brain atrophy found to be characteristic of AD and FTD were determined via cross-validation and via split-sample methods. Complex spatial patterns of relatively reduced brain volumes were identified, including temporal, orbitofrontal, parietal and cingulate regions, which were predominantly characteristic of either AD or FTD. These patterns provided 100% diagnostic accuracy, when used to separate AD or FTD from healthy controls. The ability to correctly distinguish AD from FTD averaged 84.3%. All estimates of diagnostic accuracy were determined via cross-validation. In conclusion, AD-and FTD-specific patterns of brain atrophy can be detected with high accuracy using high-dimensional pattern classification of MRI scans obtained in a typical clinical setting.

show abstract

Morphological classification of brains via high-dimensional shape transformations and machine learning methods

Cited by 314 publications

References 44 publications

Anatomically-adapted graph wavelets for improved group-level fMRI activation mapping

Anatomically-adapted graph wavelets for improved group-level fMRI activation mapping

Detection of prodromal Alzheimer's disease via pattern classification of magnetic resonance imaging

Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI

Contact Info

Product

Resources

About