High Dimensional Classification of Structural MRI Alzheimer?s Disease Data Based on Large Scale Regularization

Casanova, Ramon; Whitlow, Christopher T.; Wagner, Benjamin; Williamson, Jeff D.; Shumaker, Sally A.; Maldjian, Joseph A.; Espeland, Mark A.

doi:10.3389/fninf.2011.00022

Cited by 85 publications

(79 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the classification performance obtained on the MCI population (AUC = 70.7%, sensitivity of 70% and specificity of 62%, accuracy of 66%) being comparable to values found in recent papers [15,19,20,22–26], as reported in Table 4, it can not be considered fully adequate to set up a MRI-based automated tool for the early diagnosis of the Alzheimer’s disease. A direct comparison is possible with the classification performance obtained in the study by Chincarini et al .…”

Section: Conclusion and Discussionmentioning

confidence: 48%

Predictive Models Based on Support Vector Machines: Whole‐Brain versus Regional Analysis of Structural MRI in the Alzheimer's Disease

Retico

Bosco

Cerello

et al. 2014

Journal of Neuroimaging

View full text Add to dashboard Cite

Decision-making systems trained on structural Magnetic Resonance Imaging (MRI) data of subjects affected by the Alzheimer’s disease (AD) and healthy controls (CTRL) are becoming widespread prognostic tools for subjects with Mild Cognitive Impairment (MCI). This study compares the performance of three classification methods based on Support Vector Machines (SVMs), using as initial sets of brain voxels (i.e. features): 1) the segmented grey matter (GM); 2) regions of interest (ROIs) by voxel-wise t-test filtering; 3) parceled ROIs, according to prior knowledge. The recursive feature elimination (RFE) is applied in all cases in order to investigate whether feature reduction improves the classification accuracy. We analyzed more than 600 ADNI subjects, training the SVMs on the AD/CTRL dataset, and evaluating them on a trial MCI dataset. The classification performance, evaluated as the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC), reaches AUC=(88.9±0.5)% in 20-fold cross-validation on the AD/CTRL dataset, when the GM is classified as a whole. The highest discrimination accuracy between MCI converters and non-converters is achieved when the SVM-RFE is applied to the whole GM: with AUC reaching (70.7±0.9)%, it outperforms both ROI-based approaches in predicting the AD conversion.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 48%

Predictive Models Based on Support Vector Machines: Whole‐Brain versus Regional Analysis of Structural MRI in the Alzheimer's Disease

Retico

Bosco

Cerello

et al. 2014

Journal of Neuroimaging

View full text Add to dashboard Cite

show abstract

“…An alternative approach that operates directly in the voxel space was proposed by Casanova et al [241] who used penalized logistic regression and coordinate-wise descent optimization to overcome these problems of large scale classification.…”

Section: Methods Papersmentioning

confidence: 99%

“…The penalized logistic regression approach of Casanova et al [241] to the high dimensional classification of patients from MRI data discriminated between AD patients and controls with accuracies, specificities and sensitivities of 85.7%, 90% and 82.9%, respectively, using GM and 81.1%, 82.5% and 80.6%, respectively, using WM. The effect of registration to multiple templates on classification accuracy of TBM was investigated by Koikkalainen et al [234] who found that all 4 multi-template methods investigated resulted in better discrimination of both AD from controls patients and MCI converters from non-converters (Table 8).…”

Section: Studies Of the Adni Cohortmentioning

confidence: 99%

The Alzheimer's Disease Neuroimaging Initiative: A review of papers published since its inception

Weiner

Veitch

Aisen

et al. 2013

Alzheimer's & Dementia

664

428

View full text Add to dashboard Cite

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is an ongoing, longitudinal, multicenter study designed to develop clinical, imaging, genetic, and biochemical biomarkers for the early detection and tracking of Alzheimer's disease (AD). The study aimed to enroll 400 subjects with early mild cognitive impairment (MCI), 200 subjects with early AD, and 200 normal control subjects; $67 million funding was provided by both the public and private sectors, including the National Institute on Aging, 13 pharmaceutical companies, and 2 foundations that provided support through the Foundation for the National Institutes of Health. This article reviews all papers published since the inception of the initiative and summarizes the results as of February 2011. The major accomplishments of ADNI have been as follows: (1) the development of standardized methods for clinical tests, magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF) biomarkers in a multicenter setting; (2) elucidation of the patterns and rates of change of imaging and CSF biomarker measurements in control subjects, MCI patients, and AD patients. CSF biomarkers are consistent with disease trajectories predicted by β-amyloid cascade (Hardy, J Alzheimers Dis 2006;9(Suppl 3):151–3) and tau-mediated neurodegeneration hypotheses for AD, whereas brain atrophy and hypometabolism levels show predicted patterns but exhibit differing rates of change depending on region and disease severity; (3) the assessment of alternative methods of diagnostic categorization. Currently, the best classifiers combine optimum features from multiple modalities, including MRI, [18F]-fluorodeoxyglucose-PET, CSF biomarkers, and clinical tests; (4) the development of methods for the early detection of AD. CSF biomarkers, β-amyloid 42 and tau, as well as amyloid PET may reflect the earliest steps in AD pathology in mildly symptomatic or even nonsymptomatic subjects, and are leading candidates for the detection of AD in its preclinical stages; (5) the improvement of clinical trial efficiency through the identification of subjects most likely to undergo imminent future clinical decline and the use of more sensitive outcome measures to reduce sample sizes. Baseline cognitive and/or MRI measures generally predicted future decline better than other modalities, whereas MRI measures of change were shown to be the most efficient outcome measures; (6) the confirmation of the AD risk loci CLU, CR1, and PICALM and the identification of novel candidate risk loci; (7) worldwide impact through the establishment of ADNI-like programs in Europe, Asia, and Australia; (8) understanding the biology and pathobiology of normal aging, MCI, and AD through integration of ADNI biomarker data with clinical data from ADNI to stimulate research that will resolve controversies about competing hypotheses on the etiopathogenesis of AD, thereby advancing efforts to find disease-modifying drugs for AD; and (9) the establishment of infrastructure to allow sharing of all raw and ...

show abstract

“…Second, the LASSO is able to cope with situations where there are a large number of predictor variables (voxels) and fewer observations (subjects) as is the case in majority of neuroimaging studies (Bunea et al 2011). Previous applications of feature selection using LASSO in neuroimaging machine learning tasks include: AD classification (Casanova et al 2011; Kohannim et al 2012b; Rao et al 2011; Vounou et al 2011; Yan et al 2012), prediction of video stimulus scores in fMRI (Carroll et al 2009), ASD classification (Duchesnay et al 2011), prediction of brain characteristics using genetic data (Kohannim et al 2012a; Kohannim et al 2012b), prediction of pain stimuli in fMRI (Rish et al 2010) and Gender classification (Casanova et al 2012). …”

Section: 0 Supervised Feature Reduction Techniquesmentioning

confidence: 99%

A Review of Feature Reduction Techniques in Neuroimaging

2013

View full text Add to dashboard Cite

Machine learning techniques are increasingly being used in making relevant predictions and inferences on individual subjects neuroimaging scan data. Previous studies have mostly focused on categorical discrimination of patients and matched healthy controls and more recently, on prediction of individual continuous variables such as clinical scores or age. However, these studies are greatly hampered by the large number of predictor variables (voxels) and low observations (subjects) also known as the curse-of-dimensionality or small-n-large-p problem. As a result, feature reduction techniques such as feature subset selection and dimensionality reduction are used to remove redundant predictor variables and experimental noise, a process which mitigates the curse-of-dimensionality and small-n-large-p effects. Feature reduction is an essential step before training a machine learning model to avoid overfitting and therefore improving model prediction accuracy and generalization ability. In this review, we discuss feature reduction techniques used with machine learning in neuroimaging studies.

show abstract

High Dimensional Classification of Structural MRI Alzheimer?s Disease Data Based on Large Scale Regularization

Cited by 85 publications

References 71 publications

Predictive Models Based on Support Vector Machines: Whole‐Brain versus Regional Analysis of Structural MRI in the Alzheimer's Disease

Predictive Models Based on Support Vector Machines: Whole‐Brain versus Regional Analysis of Structural MRI in the Alzheimer's Disease

The Alzheimer's Disease Neuroimaging Initiative: A review of papers published since its inception

A Review of Feature Reduction Techniques in Neuroimaging

Contact Info

Product

Resources

About