Evaluating the Impact of Different Factors on Voxel-Based Classification Methods of ADNI Structural MRI Brain Images

Casanova, Ramon; Maldjian, Joseph A.; Espeland, Mark A.

doi:10.4172/2090-4924.1000102

Cited by 5 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interestingly, Hastie and colleagues have noted that another non-regularized technique the HM-SVM often shows similar performance to its regularized counterpart SM-SVM in high dimensional problems [43](page 658). HM-SVM works relatively well when classifying AD MRI images in the voxel space as reported before in the neuroimaging literature [14], [18], [52]. In additional experiments we noted similar patterns of performance of HM-SVM and LRC when compared to regularized methods (See upper left panel in Figure S1).…”

Section: Discussionsupporting

confidence: 81%

“…The MCI subjects were included only to generate the study- customized template. In previous work, we observed increases in classifiers' performance when MCI subjects were also used to generate the study-customized template [18]. All classification analyses were carried out using only CN and AD participants.…”

Section: Methodsmentioning

confidence: 99%

“…Unlike other approaches these classification methods operate directly in the voxel space using regularization with sparsity properties. In previous work using ADNI data we varied the number of variables between by using different study customized templates [17], [18] while keeping the sample size fixed (N = 98), and obtained excellent prediction performance and interpretability. Different versions of regularization methods with sparsity properties have been applied before in the context of fMRI data analysis to solve problems of much lower dimensions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Structural MRI Images in Alzheimer's Disease from the Perspective of Ill-Posed Problems

Casanova

Hsu

2012

PLoS ONE

Self Cite

View full text Add to dashboard Cite

BackgroundMachine learning neuroimaging researchers have often relied on regularization techniques when classifying MRI images. Although these were originally introduced to deal with “ill-posed” problems it is rare to find studies that evaluate the ill-posedness of MRI image classification problems. In addition, to avoid the effects of the “curse of dimensionality” very often dimension reduction is applied to the data.MethodologyBaseline structural MRI data from cognitively normal and Alzheimer's disease (AD) patients from the AD Neuroimaging Initiative database were used in this study. We evaluated here the ill-posedness of this classification problem across different dimensions and sample sizes and its relationship to the performance of regularized logistic regression (RLR), linear support vector machine (SVM) and linear regression classifier (LRC). In addition, these methods were compared with their principal components space counterparts.Principal FindingsIn voxel space the prediction performance of all methods increased as sample sizes increased. They were not only relatively robust to the increase of dimension, but they often showed improvements in accuracy. We linked this behavior to improvements in conditioning of the linear kernels matrices. In general the RLR and SVM performed similarly. Surprisingly, the LRC was often very competitive when the linear kernel matrices were best conditioned. Finally, when comparing these methods in voxel and principal component spaces, we did not find large differences in prediction performance.Conclusions and SignificanceWe analyzed the problem of classifying AD MRI images from the perspective of linear ill-posed problems. We demonstrate empirically the impact of the linear kernel matrix conditioning on different classifiers' performance. This dependence is characterized across sample sizes and dimensions. In this context we also show that increased dimensionality does not necessarily degrade performance of machine learning methods. In general, this depends on the nature of the problem and the type of machine learning method.

show abstract

Section: Discussionsupporting

confidence: 81%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Structural MRI Images in Alzheimer's Disease from the Perspective of Ill-Posed Problems

Casanova

Hsu

2012

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…This allowed us to detect all the voxels which may be thought to provide relevant information for the classification task with concrete evidence that they indeed are useful for the discrimination. The regularized logistic regression was chosen as a model selection method because it has been widely used in multi-voxel pattern analyses of functional neuroimaging data as well as MRI based AD classification approaches and shown to outperform many other feature selection methods (Huttunen et al, 2012, 2013; Ryali et al, 2010; Ye et al, 2012; Casanova et al, 2011a,b; Janoušová et al, 2012). According to the results presented here (see Table 3), elastic-net RLR was able to select relevant voxels corresponding to AD in the high dimensional MRI data.…”

Section: Discussionmentioning

confidence: 99%

“…The feature selection uses the regularized logistic regression framework (Friedman et al, 2010) that produces a path of feature subsets with different cardinalities (called regularization path ), and has been used widely in previous works (Huttunen et al, 2012, 2013; Ryali et al, 2010) for the multi-voxel pattern analyses of functional neuroimaging data as well as for AD related studies using structural MRI data (Ye et al, 2012; Casanova et al, 2011a,b, 2012; Shen et al, 2011; Janoušová et al, 2012). As the RLR procedure is a supervised learning method, the input has to be fully labeled data.…”

Section: Methodsmentioning

confidence: 99%

Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects

et al. 2015

View full text Add to dashboard Cite

Mild cognitive impairment (MCI) is a transitional stage between age-related cognitive decline and Alzheimer’s disease (AD). For the effective treatment of AD, it would be important to identify MCI patients at high risk for conversion to AD. In this study, we present a novel magnetic resonance imaging (MRI)-based method for predicting the MCI-to-AD conversion from one to three years before the clinical diagnosis. First, we developed a novel MRI biomarker of MCI-to-AD conversion using semi-supervised learning and then integrated it with age and cognitive measures about the subjects using a supervised learning algorithm resulting in what we call the aggregate biomarker. The novel characteristics of the methods for learning the biomarkers are as follows: 1) We used a semi-supervised learning method (low density separation) for the construction of MRI biomarker as opposed to more typical supervised methods; 2) We performed a feature selection on MRI data from AD subjects and normal controls without using data from MCI subjects via regularized logistic regression; 3) We removed the aging effects from the MRI data before the classifier training to prevent possible confounding between AD and age related atrophies; and 4) We constructed the aggregate biomarker by first learning a separate MRI biomarker and then combining it with age and cognitive measures about the MCI subjects at the baseline by applying a random forest classifier. We experimentally demonstrated the added value of these novel characteristics in predicting the MCI-to-AD conversion on data obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. With the ADNI data, the MRI biomarker achieved a 10-fold cross-validated area under the receiver operating characteristic curve (AUC) of 0.7661 in discriminating progressive MCI patients (pMCI) from stable MCI patients (sMCI). Our aggregate biomarker based on MRI data together with baseline cognitive measurements and age achieved a 10-fold cross-validated AUC score of 0.9020 in discriminating pMCI from sMCI. The results presented in this study demonstrate the potential of the suggested approach for early AD diagnosis and an important role of MRI in the MCI-to-AD conversion prediction. However, it is evident based on our results that combining MRI data with cognitive test results improved the accuracy of the MCI-to-AD conversion prediction.

show abstract

Comparing data‐driven and hypothesis‐driven MRI‐based predictors of cognitive impairment in individuals from the Atherosclerosis Risk in Communities (ARIC) study

Casanova

Hsu

Barnard

et al. 2021

Alzheimer's & Dementia

Self Cite

View full text Add to dashboard Cite

Introduction:A data-driven index of dementia risk based on magnetic resonance imaging (MRI), the Alzheimer's Disease Pattern Similarity (AD-PS) score, was estimated for participants in the Atherosclerosis Risk in Communities (ARIC) study.Methods: AD-PS scores were generated for 839 cognitively non-impaired individuals with a mean follow-up of 4.86 years. The scores and a hypothesis-driven volumetric measure based on several brain regions susceptible to AD were compared as predictors of incident cognitive impairment in different settings.Results: Logistic regression analyses suggest the data-driven AD-PS scores to be more predictive of incident cognitive impairment than its counterpart. Both biomarkers were more predictive of incident cognitive impairment in participants who were White, female, and apolipoprotein E gene (APOE) ε4 carriers. Random forest analyses including predictors from different domains ranked the AD-PS scores as the most relevant MRI predictor of cognitive impairment. Conclusions:Overall, the AD-PS scores were the stronger MRI-derived predictors of incident cognitive impairment in cognitively non-impaired individuals.

show abstract

Evaluating the Impact of Different Factors on Voxel-Based Classification Methods of ADNI Structural MRI Brain Images

Cited by 5 publications

References 47 publications

Classification of Structural MRI Images in Alzheimer's Disease from the Perspective of Ill-Posed Problems

Classification of Structural MRI Images in Alzheimer's Disease from the Perspective of Ill-Posed Problems

Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects

Comparing data‐driven and hypothesis‐driven MRI‐based predictors of cognitive impairment in individuals from the Atherosclerosis Risk in Communities (ARIC) study

Contact Info

Product

Resources

About